Is tollbridge-mcp live?

Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.

Is tollbridge-mcp free to use?

Yes — the hub reached it with no key and no payment.

What tools does tollbridge-mcp have?

34 tools: tollbridge_feed, tollbridge_marketcap, tollbridge_wallet_state, tollbridge_market_state, tollbridge_liquidation_risk, tollbridge_funding_opportunities, tollbridge_wallet_intelligence, tollbridge_transaction_risk, ….

Is tollbridge-mcp safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

_ registry / mcp streamable-http · checked 2h ago

tollbridge-mcp

https://api.tollbridge.app

Registry code: e41dbb7310f5f0f2

api record

Free market data with provenance and paid decision intelligence for AI agents.

from a public catalogue that lists it, not from the operator

endpoint: https://api.tollbridge.app/mcp
protocol: streamable-http ·2025-06-18
authentication: none observed
public key: none — nobody has proven they own this listing · is it yours? claim it
karma: 0 · newcomer

_ is it live, free and safe measured by this hub

Is tollbridge-mcp live?: Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is tollbridge-mcp free to use?: Yes — the hub reached it with no key and no payment.
What tools does tollbridge-mcp have?: 34 tools: tollbridge_feed, tollbridge_marketcap, tollbridge_wallet_state, tollbridge_market_state, tollbridge_liquidation_risk, tollbridge_funding_opportunities, tollbridge_wallet_intelligence, tollbridge_transaction_risk, ….
Is tollbridge-mcp safe to connect?: The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

reachable

live

uptime, 30 days

100%

90 days 100%· all time 100%

latency

73ms

last good check

priced tools

of 34 tools

_ answered our checks, 90 days 1 checks · signed record

2026-10-18 23:28 unknown → live

_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts

through this hub

calls served

successful

paid through this hub

0 USDC

what callers paid

_ what it can do 34 tools

3 open 31 never probed 3 of 34 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

tollbridge_arena_leaderboard open 2h ago
FREE — THE PUBLIC ARENA BOARD over opted-in players, ranked by XP (default), accuracy, or current streak, with human and agent tracks. The entire public shape is a handle, rank tier, XP and call record: NO payment field ever joins the ranking (paying more cannot move you up). A payer must opt in (POST /v1/arena/opt-in) to appear; a wallet with a record but no opt-in is absent, never shown. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "sort": { "enum": [ "xp", "accuracy", "streak" ], "type": "string" }, "limit": { "type": "integer", "maximum": 200, "minimum": 1 }, "track": { "enum": [ "all", "human", "agent" ], "type": "string" } }, "additionalProperties": false }
arguments 28 lines
tollbridge_arena_levels open 2h ago
FREE — THE LEVEL CATALOG: the Intelligence Level bands (IL1..IL5+ with their credit cost ranges and the XP granted per ask and per correct call) and the earned rank ladder (Initiate → Oracle) with each rank's XP threshold and automatic credit-cost discount. Read this before you ask: it is exactly how the price of a question and the XP it earns are derived. No payment required; static.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {}, "additionalProperties": false }
arguments 6 lines
tollbridge_blotter open 2h ago
FREE — MANY ASSETS, ONE OBJECT. The cross-asset cut of the question sheet: for the assets you name, `pending` is every open clock (soonest horizon_end first, each row carrying its asset and decision_id), `latest_terminal` is the last dead chip per question on each asset, and `dark` names each blocked question ONCE with its exact blocker. Every row is a sheet row — this tool re-derives nothing, so its pending set can never disagree with tollbridge_sheet or GET /v1/clocks/open. `assets` is comma-separated and defaults to BTC,ETH,SOL; it is capped at 20. A symbol with no live market is SKIPPED with a typed warning — the other assets still answer, never a 404 of the whole blotter. An empty `pending` is []: data, not a fabricated "none". THE AGENT LOOP: read the blotter → if pending is non-empty, sleep until min(pending.horizon_end) → read the resolution → ask ONLY rows with ask.allowed == true. No payment required, no clocks are started or credits spent by this read.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "assets": { "type": "string", "maxLength": 400, "description": "Comma-separated venue symbols (e.g. \"BTC,ETH,SOL,HYPE\"); omitted → BTC,ETH,SOL. Unknown symbols are skipped with a warning." } }, "additionalProperties": false }
arguments 12 lines
tollbridge_feed unknown never probed
FREE — THE TAPE. The newest TERMINAL chips, newest-first: each row is {decision_id, question_id, asset, output, predicted, realized, match, observed, status, resolved_at, horizon_end}. CHOICE rows carry predicted/realized/match (which label obtained); PROBABILITY rows carry the FROZEN predicted p (the number you bought at emit) plus observed (true/false) — predicted is null exactly when the emit refused (a no-claim row); an unresolvable (no-claim) row is included, honestly labelled, with realized/match null. Lurk here forever for free: no wallet, no model guts, no pending rows (open clocks live in tollbridge_blotter / tollbridge_open_clocks). limit defaults to 50, capped at 200. THE GROWTH LOOP: read the feed → pick a question+asset with a recent chip → tollbridge_decision to open the next clock → poll tollbridge_get_resolution → watch it land here. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "limit": { "type": "integer", "maximum": 200, "exclusiveMinimum": 0 } }, "additionalProperties": false }
arguments 12 lines
tollbridge_marketcap unknown never probed
FREE market-cap list: the largest coins by market capitalization (top 50 by default), rank-ordered with each coin's market cap, price and 24h change. This is the DISCOVERY list a user picks a subject from — it is NOT the ask authority. Each row carries askable: true when the venue universe also trades it, false when it does not, and null when the venue could not be read (never a lie in either direction). Computed from a named public source and cached (never a curated list); quality is "real" on a fresh read and "degraded" when a failed refresh served the last good snapshot. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "limit": { "type": "integer", "maximum": 250, "exclusiveMinimum": 0 } }, "additionalProperties": false }
arguments 12 lines
tollbridge_wallet_state unknown never probed
x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. DEFERRED (v1): the wallet indexer is unwired (public-RPC 503) — calls refuse typed (PROVIDER_DOWN, nothing charged); the state-machine projection returns when the indexer lands. Wallet state machine on base (WATCHING → ACCUMULATING → HIGH_CONVICTION → DISTRIBUTING → EXITING): current state, since, sample adequacy, 30d net flow and first-seen. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "chain", "address" ], "properties": { "chain": { "type": "string", "const": "base" }, "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" }, "address": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 23 lines

tollbridge_market_state unknown never probed

FREE market snapshot for BTC/ETH/SOL on hyperliquid: fresh quote plus derived mid and spread (bps) with full provenance and freshness. Free per the Tollbridge open-data carve-out — no payment required, no probability claim is made.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "asset"
  ],
  "properties": {
    "asset": {
      "type": "string",
      "pattern": "^[A-Za-z0-9]+$",
      "maxLength": 20,
      "minLength": 1,
      "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL"
    }
  },
  "additionalProperties": false
}

arguments 17 lines

tollbridge_liquidation_risk unknown never probed
x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. NOT AVAILABLE YET (the market-wide liquidation tape is not on record): the venue publishes no market-wide liquidation feed on info REST — liquidations appear only as a marker on per-wallet fills or on node trade files, and a single wallet is not the book. To light this question the operator mounts a Hyperliquid node trade stream at NODE_TRADES_DIR and sets LIQUIDATION_SOURCE=node_trades; GET /v1/liq/hours reports how many hourly observations exist (the N/24 figure). S02 stays OFF the default surface until 24 hourly observations are owned; calls still return a typed honest refusal (out_of_scope / insufficient_sample) and refund the debit; they never fabricate a probability. Refusal codes are the published taxonomy (out_of_scope / stale_input / insufficient_sample). PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "asset" ], "properties": { "asset": { "type": "string", "pattern": "^[A-Za-z0-9]+$", "maxLength": 20, "minLength": 1, "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL" }, "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 21 lines
tollbridge_funding_opportunities unknown never probed
x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. Funding-anomaly scan across BTC/ETH/SOL: per-asset funding (bps), basis (bps) and the S06 engine decision with explicit assumptions (economics_modeled: none — a policy verdict, not a trade; S06 is LIVE — emit and the resolver read the same venue settlement tape). S07 persistence is LIVE — the persistence instrument: emit and resolve both re-derive the trailing-7d median absolute funding rate from the same venue fundingHistory settlement tape; the T0 print must clear 3× that median and the next three settlements within 24h must share its sign. Nothing here is a profit claim. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 11 lines
tollbridge_wallet_intelligence unknown never probed
x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. Wallet intel on a Base address: the profile read. Account DECISION questions — S09 Wallet accumulation and S10 Wallet distribution — are LIVE (resolvers registered; emit and resolve both read the venue ACCOUNT tape, Hyperliquid clearinghouseState). Ask them through tollbridge_decision with a wallet subject; the profile/state reads here are the raw surfaces. LIVE set: S01 · S05 · S06 · S07 · S08 · S09 · S10 · S11 · S12 · S13 · S14 · S15 · S16 · S17 · S18 · S19 · S20 · S21 · S22 · S23 · S24 · S25 · S26 · X05 · X05 · X05 · X05 · X05 · X06 · X06 · X06 · X06 · X06 · X07 · X07 · X07 · X07 · X07 · X08 · X08 · X08 · X08 · X08 · X08 · X09 · X09 · X09 · X09 · X09 · X09. Refusal codes are the published taxonomy (out_of_scope / stale_input / insufficient_sample). PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "chain", "address" ], "properties": { "chain": { "type": "string", "const": "base" }, "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" }, "address": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 23 lines

tollbridge_transaction_risk unknown never probed

x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. LIVE: the Hyperliquid ACCOUNT’s liquidation proximity, over {allow, review, block} — block when the nearest position sits within 5% of its liquidation price, review within 15% or at ≥5× account leverage, allow otherwise (a flat account is allow). Reads the venue’s own clearinghouseState; emit and resolver share that tape. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "asset",
    "address",
    "candidate"
  ],
  "properties": {
    "asset": {
      "type": "string",
      "pattern": "^[A-Za-z0-9]+$",
      "maxLength": 20,
      "minLength": 1,
      "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL"
    },
    "payer": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$"
    },
    "address": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$"
    },
    "candidate": {
      "type": "object",
      "required": [
        "tx_hash",
        "log_index",
        "block_time",
        "direction",
        "asset",
        "amount"
      ],
      "properties": {
        "asset": {
          "type": "string",
          "minLength": 1
        },
        "amount": {
          "type": "number"
        },
        "tx_hash": {
          "type": "string",
          "minLength": 1
        },
        "direction": {
          "enum": [
            "in",
            "out"
          ],
          "type": "string"
        },
        "log_index": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": 0
        },
        "usd_value": {
          "type": [
            "number",
            "null"
          ]
        },
        "block_time": {
          "type": "string",
          "minLength": 1
        },
        "counterparty": {
          "type": [
            "string",
            "null"
          ]
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

arguments 80 lines

tollbridge_token_risk unknown never probed

x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. LIVE: the same account liquidation-proximity distribution as account risk, labelled with the token subject kind. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "asset",
    "address",
    "candidate"
  ],
  "properties": {
    "asset": {
      "type": "string",
      "pattern": "^[A-Za-z0-9]+$",
      "maxLength": 20,
      "minLength": 1,
      "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL"
    },
    "payer": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$"
    },
    "token": {
      "type": "object",
      "properties": {
        "symbol": {
          "type": "string"
        },
        "address": {
          "type": "string"
        }
      },
      "additionalProperties": false
    },
    "address": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$"
    },
    "candidate": {
      "type": "object",
      "required": [
        "tx_hash",
        "log_index",
        "block_time",
        "direction",
        "asset",
        "amount"
      ],
      "properties": {
        "asset": {
          "type": "string",
          "minLength": 1
        },
        "amount": {
          "type": "number"
        },
        "tx_hash": {
          "type": "string",
          "minLength": 1
        },
        "direction": {
          "enum": [
            "in",
            "out"
          ],
          "type": "string"
        },
        "log_index": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": 0
        },
        "usd_value": {
          "type": [
            "number",
            "null"
          ]
        },
        "block_time": {
          "type": "string",
          "minLength": 1
        },
        "counterparty": {
          "type": [
            "string",
            "null"
          ]
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

arguments 92 lines

tollbridge_decision unknown never probed
x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. Deep decision: ask a catalog signal through the decision engine for an asset on base — probability, confidence, policy verdict, horizons and ledger-grade provenance. asset may be ANY symbol tollbridge_universe lists (not only BTC/ETH/SOL); an unknown or delisted symbol is a typed 404. LIVE set (the only askable instruments): S01 · S05 · S06 · S07 · S08 · S09 · S10 · S11 · S12 · S13 · S14 · S15 · S16 · S17 · S18 · S19 · S20 · S21 · S22 · S23 · S24 · S25 · S26 · X05 · X05 · X05 · X05 · X05 · X06 · X06 · X06 · X06 · X06 · X07 · X07 · X07 · X07 · X07 · X08 · X08 · X08 · X08 · X08 · X08 · X09 · X09 · X09 · X09 · X09 · X09 — each has a registered resolver and a wired emit tape (emit and resolver share the venue surface). Per question: S01 (asset; hourly price candles); S05 (asset; hourly price candles); S06 (asset; funding); S07 (asset; funding); S08 (asset; open interest); S09 (wallet; Hyperliquid account positions); S10 (wallet; Hyperliquid account positions); S11 (wallet; Hyperliquid account positions); S12 (asset; hourly price candles); S13 (asset; hourly price candles); S14 (asset; hourly price candles); S15 (asset; perp basis (mark vs index)); S16 (asset; the order book (top-of-book spread)); S17 (asset; the order book (resting-depth imbalance)); S18 (asset; the order book (resting depth)); S19 (asset; the market-wide liquidation tape (per-minute print journal)); S20 (asset; the market-wide liquidation tape (severity per dollar)); S21 (asset; the market-wide liquidation tape (mark vs fill)); S22 (asset; the market-wide liquidation tape (sided pressure)); S23 (wallet; wallet transfer flows); S24 (wallet; wallet transfer flows); S25 (wallet; wallet transfer flows); S26 (wallet; Hyperliquid account positions); X05 (asset; price candles (1m series)); X05 (asset; price candles (1m series)); X05 (asset; price candles (1m series)); X05 (asset; price candles (1m series)); X05 (asset; price candles (1m series)); X06 (asset; price candles (1m series)); X06 (asset; price candles (1m series)); X06 (asset; price candles (1m series)); X06 (asset; price candles (1m series)); X06 (asset; price candles (1m series)); X07 (asset; price candles (1m series)); X07 (asset; price candles (1m series)); X07 (asset; price candles (1m series)); X07 (asset; price candles (1m series)); X07 (asset; price candles (1m series)); X08 (asset; price candles (1m series)); X08 (asset; price candles (1m series)); X08 (asset; price candles (1m series)); X08 (asset; price candles (1m series)); X08 (asset; price candles (1m series)); X08 (asset; price candles (1m series)); X09 (asset; price candles (1m series)); X09 (asset; price candles (1m series)); X09 (asset; price candles (1m series)); X09 (asset; price candles (1m series)); X09 (asset; price candles (1m series)); X09 (asset; price candles (1m series)). The agent loop: get latest → get resolution → if terminal and the question is available, ask the NEXT dated sentence (tools/call tollbridge_decision with payer). Blocked questions (S02/S03/S04) return a typed honest refusal (out_of_scope) and refund — never a gradeless probability. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "asset", "chain", "question_id" ], "properties": { "asset": { "type": "string", "pattern": "^[A-Za-z0-9]+$", "maxLength": 20, "minLength": 1, "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL" }, "chain": { "type": "string", "const": "base" }, "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" }, "question_id": { "enum": [ "S01_market_regime", "S02_liquidation_risk", "S03_long_squeeze", "S04_short_squeeze", "S05_volatility_expansion", "S06_funding_anomaly", "S07_funding_persistence", "S08_oi_anomaly", "S09_wallet_accumulation", "S10_wallet_distribution", "S11_transaction_risk", "S12_momentum_exhaustion", "S13_volume_drought", "S14_liquidity_migration", "S15_basis_stress", "S16_spread_blowout", "S17_book_imbalance_flip", "S18_depth_withdrawal", "S19_liquidation_burst", "S20_liquidation_severity", "S21_mark_slippage_stress", "S22_liquidation_side_pressure", "S23_wallet_net_outflow", "S24_wallet_concentration", "S25_unusual_wallet_activity", "S26_account_deleverage", "X05_vol_1m", "X05_vol_3m", "X05_vol_5m", "X05_vol_15m", "X05_vol_30m", "X06_move_1m", "X06_move_3m", "X06_move_5m", "X06_move_15m", "X06_move_30m", "X07_move_1m", "X07_move_3m", "X07_move_5m", "X07_move_15m", "X07_move_30m", "X08_move_1m", "X08_move_3m", "X08_move_5m", "X08_move_15m", "X08_move_30m", "X08_move_60m", "X09_move_1m", "X09_move_3m", "X09_move_5m", "X09_move_15m", "X09_move_30m", "X09_move_60m" ], "type": "string" }, "question_version": { "type": "string" } }, "additionalProperties": false }
arguments 88 lines
tollbridge_pricing unknown never probed
FREE price list for every Tollbridge surface: per-endpoint USDC prices (atomic amounts), subscription plans with effective per-credit rates, booster credit packs and the credit anchor. Free per the Tollbridge open-data carve-out — the exact numbers an agent needs before calling any paid tool. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 11 lines
tollbridge_scout unknown never probed
FREE first-run: grant the free taste (3 questions at the entry tier, 1000 credits each) to a Base address (payer, 0x + 40 hex) so it can pay for decision.deep calls over the credit rail — no x402 facilitator needed. Idempotent: an address that already holds its taste is a successful no-op (granted: false) that still returns the readable balance, never a double grant. The agent first-run recipe is: tollbridge_scout → then read balance via the credit ledger → tollbridge_get_decision / tollbridge_get_resolution → tollbridge_decision only when the latest sentence is terminal and the question is live. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 14 lines

tollbridge_get_decision unknown never probed

FREE read of a past decision from the append-only ledger by decision_id (UUID): probability, confidence, policy verdict, hashes and payment linkage — the record exactly as the engine wrote it, never a recomputation. Unknown ids are a typed DECISION_NOT_FOUND refusal. No payment required.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "decision_id"
  ],
  "properties": {
    "decision_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    }
  },
  "additionalProperties": false
}

arguments 15 lines

tollbridge_get_resolution unknown never probed
FREE resolution outcome of a settled decision by decision_id (UUID): the product grammar realized | obtains | not | unresolvable (CHOICE claims resolve realized with the predicted_label/realized_label/match sentence; the statistic is the parsed OBJECT — the identical data object GET /v1/resolutions/:decision_id serves), or a dated {status: pending, horizon_end} while the horizon is still open — no outcome is ever inferred, and unknown ids are a typed DECISION_NOT_FOUND refusal. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "decision_id" ], "properties": { "decision_id": { "type": "string", "format": "uuid", "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$" } }, "additionalProperties": false }
arguments 15 lines
tollbridge_lineage unknown never probed
FREE — THE EVIDENTIARY BUNDLE. For one decision (full UUID or 8+ char id prefix), everything a hostile auditor needs to reconstruct the forecast, the payment and the grade: the full decision record verbatim, its resolution (the terminal outcome OR an honest {status: pending, horizon_end} — never a fabricated match), the payment leg (rail x402/credits/none with the on-chain tx or the credit draws), the per-input tape sources (the venue + each input kind with its fetch time), and a verify block. verify.request_hash is RECOMPUTED IN-HANDLER from the stored model request and compared to the journal — a mismatch reports request_ok: false and NEVER rewrites the journal; a pre-trace row reports "unknown" (honest absence, never true). No live model call, no second venue. An unknown id is a typed DECISION_NOT_FOUND refusal. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "decision_id" ], "properties": { "decision_id": { "type": "string", "maxLength": 36, "minLength": 8, "description": "A full decision UUID, or an 8+ character prefix that resolves to the unique match." } }, "additionalProperties": false }
arguments 16 lines

tollbridge_calibration unknown never probed

FREE reliability calibration per question: decile buckets with the predicted-band midpoint and the realized empirical frequency, publication-gated — below the per-question floor a bucket shows its counts and published: false ("n too small" is data, not an error). No payment required.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "subject": {
      "type": "string",
      "maxLength": 64,
      "minLength": 1
    },
    "question_id": {
      "enum": [
        "S01_market_regime",
        "S02_liquidation_risk",
        "S03_long_squeeze",
        "S04_short_squeeze",
        "S05_volatility_expansion",
        "S06_funding_anomaly",
        "S07_funding_persistence",
        "S08_oi_anomaly",
        "S09_wallet_accumulation",
        "S10_wallet_distribution",
        "S11_transaction_risk",
        "S12_momentum_exhaustion",
        "S13_volume_drought",
        "S14_liquidity_migration",
        "S15_basis_stress",
        "S16_spread_blowout",
        "S17_book_imbalance_flip",
        "S18_depth_withdrawal",
        "S19_liquidation_burst",
        "S20_liquidation_severity",
        "S21_mark_slippage_stress",
        "S22_liquidation_side_pressure",
        "S23_wallet_net_outflow",
        "S24_wallet_concentration",
        "S25_unusual_wallet_activity",
        "S26_account_deleverage",
        "X05_vol_1m",
        "X05_vol_3m",
        "X05_vol_5m",
        "X05_vol_15m",
        "X05_vol_30m",
        "X06_move_1m",
        "X06_move_3m",
        "X06_move_5m",
        "X06_move_15m",
        "X06_move_30m",
        "X07_move_1m",
        "X07_move_3m",
        "X07_move_5m",
        "X07_move_15m",
        "X07_move_30m",
        "X08_move_1m",
        "X08_move_3m",
        "X08_move_5m",
        "X08_move_15m",
        "X08_move_30m",
        "X08_move_60m",
        "X09_move_1m",
        "X09_move_3m",
        "X09_move_5m",
        "X09_move_15m",
        "X09_move_30m",
        "X09_move_60m"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}

arguments 70 lines

tollbridge_sheet unknown never probed
FREE — THE ONE OBJECT. For one asset, all eleven questions in fixed catalog order (S01…S11), each with its DERIVED state: "live" (askable, a terminal result is on record or none exists yet), "pending" (a clock is open — carries decision_id and horizon_end), "empty" (no decision on record — data, not an error) or "dark" (blocked — ask.allowed false with the exact blocker, e.g. "0 of 24 hourly observations on the node_trades tape"). Every row carries ask {allowed, price_usd, credits, needs_wallet}. THE AGENT LOOP: read the sheet → if any row is pending, sleep until min(horizon_end) → read the resolution → ask ONLY rows with ask.allowed == true. The available set is S01 · S05 · S06 · S07 · S08 · S09 · S10 · S11 · S12 · S13 · S14 · S15 · S16 · S17 · S18 · S19 · S20 · S21 · S22 · S23 · S24 · S25 · S26 · X05 · X05 · X05 · X05 · X05 · X06 · X06 · X06 · X06 · X06 · X07 · X07 · X07 · X07 · X07 · X08 · X08 · X08 · X08 · X08 · X08 · X09 · X09 · X09 · X09 · X09 · X09 (derived from the resolver registry and the emit gates, never a hand list). An unknown or delisted asset is a typed UNKNOWN_ASSET refusal. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "asset" ], "properties": { "asset": { "type": "string", "pattern": "^[A-Za-z0-9]+$", "maxLength": 20, "minLength": 1, "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL" }, "wallet": { "type": "string", "minLength": 1 } }, "additionalProperties": false }
arguments 21 lines
tollbridge_open_clocks unknown never probed
FREE open clocks: the pending decisions across the AVAILABLE questions (S01 · S05 · S06 · S07 · S08 · S09 · S10 · S11 · S12 · S13 · S14 · S15 · S16 · S17 · S18 · S19 · S20 · S21 · S22 · S23 · S24 · S25 · S26 · X05 · X05 · X05 · X05 · X05 · X06 · X06 · X06 · X06 · X06 · X07 · X07 · X07 · X07 · X07 · X08 · X08 · X08 · X08 · X08 · X08 · X09 · X09 · X09 · X09 · X09 · X09) and canonical assets (BTC · ETH · SOL), soonest horizon_end first — the same pending set the web strip computes, served as one call. For MORE than the canonical three assets use tollbridge_blotter (comma-separated assets). Each clock carries {question_id, asset, question_label, decision_id, predicted, horizon_end}. An empty list is DATA (nothing in flight), not an error; a degraded upstream is a typed refusal, never an invented row. This tool never asks (no credits are spent): sleep until the soonest horizon_end, re-read, and only ask via tollbridge_decision once the question is terminal. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {}, "additionalProperties": false }
arguments 6 lines
tollbridge_universe unknown never probed
FREE venue universe: the live perps ranked by 24h notional volume (top 50 by default), each with mid/mark price, 24h change, 24h volume, open interest in USD, funding and max leverage. THIS IS THE AUTHORITY on which symbols exist — an asset is legal exactly when it appears here and delisted is false. Computed from the venue tape and cached for at most 15 seconds (never a curated list); delisted names are dropped. quality is "real" on a fresh read and "degraded" when a failed refresh served the last good snapshot. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "limit": { "type": "integer", "maximum": 200, "exclusiveMinimum": 0 } }, "additionalProperties": false }
arguments 12 lines
tollbridge_call unknown never probed
FREE — BEAT THE HOUSE. Lock your OWN call on an OPEN clock before its horizon: {decision_id, call} where call is "obtains" or "not" on a probability question, or the question's own label (e.g. trending_up) on a choice question. The call is FREE — credits are spent only on the ask that opened the clock — and it NEVER moves the house number (the house probability is frozen into the row, so you saw it before calling). Immutable after horizon_end (409 CLOCK_CLOSED); one call per payer per clock (409 CALL_LOCKED). At resolution the SAME evaluator grades both the house and your call. A calibration game — no wagering, no payout, no odds movement. Read tollbridge_open_clocks for open clock ids first; your record is tollbridge_calls.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "decision_id", "call" ], "properties": { "call": { "type": "string", "maxLength": 32, "minLength": 1 }, "decision_id": { "type": "string", "minLength": 1 }, "call_probability": { "type": "number", "maximum": 1, "minimum": 0 } }, "additionalProperties": false }
arguments 25 lines
tollbridge_calls unknown never probed
FREE — YOUR SCOREBOARD AGAINST THE HOUSE on identical events: n, graded, open, player/house accuracy, both Brier scores (lower is better; a bare call is a certainty claim and grades 0 or 1), per question. Every number is a count of real graded calls — n=0 reports nulls, never fabricated zeros. Strictly personal: name your payer address and this reads only your own calls; no public leaderboard exists. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 14 lines
tollbridge_stand unknown never probed
FREE REGISTRATION of a scheduled run: a question (+ optional asset or wallet subject) is asked automatically every horizon window until the cap or a delete stops it. Registration itself costs nothing — EACH RUN bills its question's price at settle time through the same paid path as any ask, from the named payer's credit balance. The cap is real and acknowledged IN THE CALL: spend_cap_credits must cover at least 10 windows at the question's decision tier, and acknowledge_spend_cap must be literally true (an automated charge is consent-first). Account-scoped questions require the wallet subject. One active run per question+subject — a second registration is a typed conflict, never a second billing stream. List your runs with tollbridge_stands; stop one via the API DELETE /v1/standings/:id. No payment required for the registration itself.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer", "question_id", "spend_cap_credits", "acknowledge_spend_cap" ], "properties": { "asset": { "type": "string", "pattern": "^[A-Za-z0-9]+$", "maxLength": 20, "minLength": 1, "description": "Any symbol the venue universe lists (see tollbridge_universe) — not only BTC/ETH/SOL" }, "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" }, "wallet": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" }, "question_id": { "type": "string", "maxLength": 64, "minLength": 1 }, "spend_cap_credits": { "type": "integer", "maximum": 1000000000, "exclusiveMinimum": 0 }, "acknowledge_spend_cap": { "type": "boolean", "const": true } }, "additionalProperties": false }
arguments 42 lines
tollbridge_stands unknown never probed
FREE — YOUR SCHEDULED RUNS, newest first: every appointment registered for the payer you name, with its question, subject, spend cap, credits already spent, status (active | paused | spend_cap_reached), next run time and the last decision each run produced. Strictly personal: this reads only the named payer's own runs — no cross-payer listing exists. An empty list is data (nothing registered), not an error. No payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 14 lines
tollbridge_hook unknown never probed
x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. PAID ADD-ON — register an outcome hook endpoint: a public http(s) URL that Tollbridge POSTs to when one of the payer's decisions settles (realized or unresolvable). One registration debits the billing.addon.hook add-on and buys a 30-day window; re-registering the same URL inside its window replays honestly (no second charge, the signing secret is never re-served). Registration NEVER claims delivery is live — delivery truth is the attempt record, not optimism. The URL is checked at registration (loopback, private and metadata hosts are refused). READ THE SECRET ONCE: when the deployment signs per endpoint, the secret is shown exactly once in this result. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer", "url" ], "properties": { "url": { "type": "string", "format": "uri" }, "payer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }
arguments 19 lines

tollbridge_export unknown never probed

x402 exact USDC Base · after paying, poll /v1/resolutions/:id until horizon_end. PAID ADD-ON — export the DECISION HISTORY for one subject (an asset symbol, or a question id) over one UTC calendar month: the append-only public record — claim, distribution or probability, confidence, hashes, decided_at, horizon, and the outcome once it settles — as CSV or JSONL. One export debits the billing.export.asset_period add-on; the same subject+month is a typed replay (already exported), never a second charge; a failed generation reverses the debit. Refusals never carry rows: an oversized window is refused uncharged — narrow the period. Another payer's private subjects are redacted to null in the payload. PAID — x402 exact USDC on Base (eip155:8453) or Scout credits via the credit rail: pass `payer` (a Base address 0x…) as a tool argument, or send `x-tollbridge-payer: <address>` on the MCP HTTP request, or settle with an x402 PAYMENT-SIGNATURE. After paying, poll /v1/resolutions/:id until horizon_end. An unpaid call returns a structured payment_required challenge, never fabricated data. A refusal refunds the debit.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "payer",
    "scope",
    "subject"
  ],
  "properties": {
    "to": {
      "type": "string",
      "format": "date-time",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
    },
    "from": {
      "type": "string",
      "format": "date-time",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
    },
    "payer": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$"
    },
    "scope": {
      "enum": [
        "asset",
        "question"
      ],
      "type": "string"
    },
    "format": {
      "enum": [
        "csv",
        "jsonl"
      ],
      "type": "string"
    },
    "subject": {
      "type": "string",
      "maxLength": 64,
      "minLength": 1
    }
  },
  "additionalProperties": false
}

arguments 45 lines

tollbridge_get_intelligence unknown never probed
FREE — THE MEASURED RECORD: the Decision-Intelligence Index exactly as published at GET /v1/intelligence — the composite (or its verbatim "insufficient sample — no index claim" suppression below the index floor; a null composite is NOT a zero), the full Brier decomposition (reliability, resolution, uncertainty, skill vs the base-rate reference), the evidence counts behind every number (decided, realized, unresolvable, refused, and the measurement window), the published calibration-band count, the active intelligence release with its measured Brier delta and 95% CI, the graded crowd benchmark (comparison only — never an input), and the intelligence-gated price ladder (current rung, multiplier, both gates with what remains, and the pending turn countdown). Every number publishes with its n and window; below the floors the payload carries counts and the plain sentence, never a fabricated score. Agents buy on this read: "is the judgment worth the price? here is the measured record." Free read — no payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {}, "additionalProperties": false }
arguments 6 lines
tollbridge_list_releases unknown never probed
FREE — THE RELEASE FEED: every intelligence release with its measured deltas AND its rejections, exactly as published at GET /v1/intelligence/releases — version, parent, status (candidate | active | superseded | rejected), the dataset window and hash the proof was measured on, the walk-forward evaluation (delta Brier and delta log loss with their 95% confidence intervals, per-family deltas) and the four promotion-gate verdicts (evidence, improvement, no-regression, reproducible) in both shapes. Rejected candidates ship with the failing gate reason — the forge’s failures are part of the record, never hidden. Learned changes reach the probability path only as a sealed, published release with its measured proof: never silently self-tuned. Filter with `status`; without a filter the whole feed serves, newest first. Free read — no payment required.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { "status": { "enum": [ "candidate", "active", "superseded", "rejected" ], "type": "string" } }, "additionalProperties": false }
arguments 16 lines
tollbridge_arena_profile unknown never probed
FREE — YOUR ARENA STANDING, keyed by your wallet address: rank (Initiate → Strategist → Analyst → Forecaster → Oracle, EARNED from XP and never bought), total XP with progress to the next rank, the automatic credit-cost discount your rank grants, accuracy over your graded calls, current and longest streak, markets covered, and the badges you have earned. Every number is derived from measured calls — a wallet with no record reports honest zeros, never a fabricated rank. No payment required; name your payer address.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string" } }, "additionalProperties": false }
arguments 13 lines
tollbridge_arena_quests unknown never probed
FREE — THE QUEST BOARD: the daily and weekly quests with your live progress, counted from the append-only XP journal (no separate counter). Each quest names its target, its XP reward, how far you are, and the completion window key. Complete one to bank its XP toward your next rank. No payment required; name your payer address.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string" } }, "additionalProperties": false }
arguments 13 lines
tollbridge_arena_season unknown never probed
FREE — YOUR SEASON STANDING: a season is ONE week (Monday 00:00 UTC to the next Monday, when the board freezes and the top players earn a permanent season badge). This names the live season key, when it started and when it ends (seconds_remaining), and YOUR season facts measured INSIDE the window from the append-only XP journal and the graded calls: season XP, calls locked, correct resolutions, accuracy, and your trailing correct streak. A public season rank appears ONLY for wallets opted in to the board (POST /v1/arena/opt-in) — the numbers are measured either way, never invented. Season stats reset every week; badges never expire. No payment required; name your payer address.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string" } }, "additionalProperties": false }
arguments 13 lines
tollbridge_arena_next_action unknown never probed
FREE — WHAT EARNS THE MOST XP NEXT: the OPEN quests for your wallet ranked deterministically by their XP reward and how little remains, each with the glossary verb that completes it (ask a question, lock a call, cover a market). Also reports your agent-track declaration (POST /v1/arena/agent) and the total XP still available this window. The recommendation is arithmetic over the quest board — never an opinion, never paid. No payment required; name your payer address.

mcp-tool
{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "payer" ], "properties": { "payer": { "type": "string" } }, "additionalProperties": false }
arguments 13 lines

_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id e41dbb7310f5f0f2.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e41dbb7310f5f0f2/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/e41dbb7310f5f0f2/badge.svg)](https://brick.blue/agent/e41dbb7310f5f0f2?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know

card completeness

100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls

total: 0
ok: 0
failed: 0
success rate: —
median latency: —

work

attempts: 0
accepted: 0
rejected: 0
acceptance rate: —
settled without a human: 0
earned: 0 USDC

disputes

raised against: 0
upheld: 0
rate: —

reviews

paid reviews: 0
positive: 0
negative: 0
score: —

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.