_ registry / mcp streamable-http · checked 7m ago

AgentSLA

https://agentsla.io

Registry code: 3333f8d9166438c1

api record

AgentSLA checks whether APIs and MCP servers are up before an agent relies on or pays them. Typical flow: discover_monitored_apis to find candidates, get_api_details for one listing's check history, check_endpoint for a free live check, and verify_endpoint_sla when a signed (EIP-712) result is needed. Signed checks need a 7-day pass: check_pass, then buy_pass. To pay a provider only if its endpoint meets an SLA: create_escrow_job, register_escrow_terms, then get_escrow_job. Tools never hold keys or move funds: paid steps return unsigned Base Mainnet transactions for the caller's own wallet.…

endpoint
https://agentsla.io/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 AgentSLA live?
Yes — it answered the hub's last check (checked 7m ago). It answered 100% of checks over the last 30 days.
Is AgentSLA free to use?
Yes — the hub reached it with no key and no payment.
What tools does AgentSLA have?
10 tools: check_endpoint, buy_pass, register_escrow_terms, verify_endpoint_sla, check_pass, create_escrow_job, get_escrow_job, get_api_details, ….
Is AgentSLA 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
308ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 1 checks · signed record
  • 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
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 10 tools
2 open 8 never probed 2 of 10 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.

  • discover_monitored_apis open 7m ago

    Searches the 21,151 APIs and MCP servers indexed by AgentSLA by keyword and/or category. Use it first to find candidate services; then get_api_details for one listing, or check_endpoint to test a URL live. Free, read-only, served from the index (no live probing). Returns totalIndexed, matchedCount and up to `limit` listings, each with id, service_name, endpoint_url, category, link_type ("api" = callable endpoint, "listing-page" = a directory page about the service, "spec-file" = an API description file) and current_sla_score (share of recent probes that answered, null if never probed). Callable APIs come first. When a category matches nothing, availableCategories lists the valid ones.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 25,
          "maximum": 200,
          "minimum": 1,
          "description": "Maximum listings to return."
        },
        "search": {
          "type": "string",
          "description": "Keywords matched against service name and URL, e.g. \"weather\", \"stripe\", \"solana rpc\". Omit to browse a category."
        },
        "category": {
          "type": "string",
          "description": "Category slug: mcp-connectors, ai-models, data-retrieval, autonomous-agents, cloud, developer_tools, web3-rpc, image-generation, security, financial, marketing, analytics, ecommerce, iot, payment, defi-data. Display names such as \"Web3 RPC\" or \"LLM Inference & AI Models\" also work. Omit for all categories."
        },
        "callableOnly": {
          "type": "boolean",
          "default": false,
          "description": "true returns only callable endpoints (link_type \"api\"), skipping directory pages and spec files."
        }
      },
      "additionalProperties": false
    }
    arguments 26 lines
  • get_usdc_escrow_contract open 7m ago

    Returns the reference data for AgentSLA's escrow contract on Base Mainnet: contract and USDC token addresses, chain id, the pass price and period, the 2% escrow fee, the 7-day reclaim timeout, the human-readable ABI of the functions agents call, and a Basescan link. Use it to verify the addresses that buy_pass and create_escrow_job put in their transactions. Free, read-only, static.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • check_endpoint unknown never probed

    Probes any HTTP(S) URL once, right now, from Cloudflare's edge and reports httpStatus, edgeLatencyMs and meetsSla (true when the status is 2xx/3xx within maxLatencyMs; an endpoint that answers GET with 405 is retried as a JSON-RPC POST). Use it before calling or paying an unfamiliar endpoint. Free, unsigned, no wallet needed, sends one request to the target. For a result a third party can verify, use verify_endpoint_sla instead. The result includes a SHA-256 probeHash (a content hash, not a signature).

    mcp-tool

    {
      "type": "object",
      "required": [
        "endpointUrl"
      ],
      "properties": {
        "endpointUrl": {
          "type": "string",
          "format": "uri",
          "description": "Full http(s) URL to probe, e.g. \"https://api.example.com/health\"."
        },
        "maxLatencyMs": {
          "type": "integer",
          "default": 1000,
          "maximum": 30000,
          "minimum": 50,
          "description": "Latency limit in milliseconds for meetsSla."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
  • buy_pass unknown never probed

    Builds the unsigned Base Mainnet transactions that buy a 7-day pass (5 USDC) for a wallet: a USDC approve, only if its allowance is below 5 USDC, then paySubscription() on the escrow contract. Use it when check_pass shows no active pass. Calling it is free and changes nothing: the wallet signs and sends the returned transactions itself (gas in ETH on Base); AgentSLA holds no keys and moves no funds. Buying while a pass is active extends it by 7 days from its current expiry. Returns the ordered transactions (to, data, value, chainId) and warnings such as an insufficient USDC balance.

    mcp-tool

    {
      "type": "object",
      "required": [
        "walletAddress"
      ],
      "properties": {
        "walletAddress": {
          "type": "string",
          "pattern": "^0x[0-9a-fA-F]{40}$",
          "description": "Base Mainnet wallet that will sign, pay for and own the pass, e.g. \"0x1234...abcd\"."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • register_escrow_terms unknown never probed

    Records the latency limit for an escrow job after its createJob transaction confirms, so the oracle knows the SLA to judge. Use it once per job, right after the create_escrow_job transactions. The job is read from the transaction on Base; only its creator's transaction is accepted, and the first registration is kept (calling again does not change it). Writes the terms to AgentSLA's database; moves no funds. Returns jobId and the registered maxLatencyMs. The oracle then settles the job automatically within about 20 minutes (see get_escrow_job).

    mcp-tool

    {
      "type": "object",
      "required": [
        "txHash",
        "maxLatencyMs"
      ],
      "properties": {
        "txHash": {
          "type": "string",
          "pattern": "^0x[0-9a-fA-F]{64}$",
          "description": "Hash of the confirmed createJob transaction, 0x + 64 hex characters."
        },
        "maxLatencyMs": {
          "type": "integer",
          "maximum": 30000,
          "minimum": 50,
          "description": "The SLA: the endpoint must answer 2xx/3xx within this many milliseconds, e.g. 1000."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
  • verify_endpoint_sla unknown never probed

    Probes an endpoint (best of up to 3 tries) and returns an EIP-712 SLAAttestation signed by the AgentSLA oracle: httpStatus, latencyMs, slaMet, eip712Signature and oracleSigner, verifiable with ethers.verifyTypedData (domain and types: GET https://agentsla.io/v1/attestations). Use it when another party must be able to verify the result; for a quick free look use check_endpoint. Requires walletAddress to hold an active 7-day pass (5 USDC): check_pass shows it, buy_pass sells it. Without a pass it returns an error result explaining how to pay; nothing is charged. A listed endpoint's result is also added to its public check history.

    mcp-tool

    {
      "type": "object",
      "required": [
        "endpointUrl",
        "walletAddress"
      ],
      "properties": {
        "endpointUrl": {
          "type": "string",
          "format": "uri",
          "description": "Full http(s) URL to probe, e.g. \"https://api.example.com/health\"."
        },
        "maxLatencyMs": {
          "type": "integer",
          "default": 1000,
          "maximum": 30000,
          "minimum": 50,
          "description": "Latency limit in milliseconds for slaMet."
        },
        "walletAddress": {
          "type": "string",
          "pattern": "^0x[0-9a-fA-F]{40}$",
          "description": "Base Mainnet wallet holding an active pass, e.g. \"0x1234...abcd\" (40 hex characters after 0x)."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • check_pass unknown never probed

    Reads from Base Mainnet whether a wallet holds an active 7-day pass (needed by verify_endpoint_sla), its expiry (validUntil, secondsLeft), the price (5 USDC), and the wallet's USDC balance and existing allowance to the escrow contract. Use it before verify_endpoint_sla, and after buy_pass's transactions confirm. Free and read-only.

    mcp-tool

    {
      "type": "object",
      "required": [
        "walletAddress"
      ],
      "properties": {
        "walletAddress": {
          "type": "string",
          "pattern": "^0x[0-9a-fA-F]{40}$",
          "description": "Base Mainnet wallet to check, e.g. \"0x1234...abcd\"."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • create_escrow_job unknown never probed

    Builds the unsigned Base Mainnet transactions that lock USDC in escrow for one directory listing: the provider gets the price if the oracle finds the endpoint meets your latency limit; otherwise you get the price plus the 2% fee back. Use it to pay a provider conditionally; to check without paying, use check_endpoint. Payouts go only to a wallet the endpoint vouches for (x402 payTo, /.well-known/agentsla.json or a _agentsla TXT record); for an unverified wallet (providerVerified false) the payout waits at the job's claim link and is refunded to you after 6 days. Calling it changes nothing: your wallet signs a USDC approve (if needed) and createJob, then you call register_escrow_terms with the createJob hash. Returns the transactions, the total to approve and the listing.

    mcp-tool

    {
      "type": "object",
      "required": [
        "walletAddress",
        "apiId",
        "providerAddress",
        "priceUsdc"
      ],
      "properties": {
        "apiId": {
          "type": "integer",
          "minimum": 1,
          "description": "Listing id of the endpoint being paid for (from discover_monitored_apis or get_api_details), e.g. 29002."
        },
        "priceUsdc": {
          "type": "number",
          "maximum": 100000,
          "description": "Price in USDC, e.g. 1.5. The payer approves price + 2%.",
          "exclusiveMinimum": 0
        },
        "walletAddress": {
          "type": "string",
          "pattern": "^0x[0-9a-fA-F]{40}$",
          "description": "Payer wallet on Base Mainnet that signs and funds the job."
        },
        "providerAddress": {
          "type": "string",
          "pattern": "^0x[0-9a-fA-F]{40}$",
          "description": "Wallet that receives the price if the SLA is met. Paid at once if the endpoint vouches for it (x402 payTo, /.well-known/agentsla.json {\"payoutAddresses\":[\"0x...\"]} or a TXT record at _agentsla.<domain>: agentsla-payout=0x...); otherwise held until it does."
        }
      },
      "additionalProperties": false
    }
    arguments 33 lines
  • get_escrow_job unknown never probed

    Reads one escrow job from Base Mainnet and AgentSLA's records: status (active, settled or reclaimed), creator, provider, listing and endpoint, price, fee, registered latency limit, created time, and when the creator may reclaim it if the oracle has not settled it. Use it after register_escrow_terms to follow a job to completion. Free and read-only.

    mcp-tool

    {
      "type": "object",
      "required": [
        "jobId"
      ],
      "properties": {
        "jobId": {
          "type": "integer",
          "minimum": 1,
          "description": "Escrow job id, returned by register_escrow_terms, e.g. 2."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • get_api_details unknown 7m ago

    Returns one directory listing in full: its id, name, endpoint_url, category, link_type, current_sla_score, any verified USDC rank stake, and a summary of its signed check history (number of checks, pass rate, latest check with latency). Use it after discover_monitored_apis to judge a candidate, or to find the listing id that create_escrow_job needs. Free and read-only; it does not probe the endpoint (use check_endpoint for a live check). Give either id or endpointUrl.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "id": {
          "type": "integer",
          "minimum": 1,
          "description": "Listing id from discover_monitored_apis, e.g. 29002."
        },
        "endpointUrl": {
          "type": "string",
          "format": "uri",
          "description": "The listing's exact endpoint_url, e.g. \"https://api.openai.com\". Used when id is omitted."
        }
      },
      "additionalProperties": false
    }
    arguments 16 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.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. 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.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 3333f8d9166438c1.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/3333f8d9166438c1/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/3333f8d9166438c1/badge.svg)](https://brick.blue/agent/3333f8d9166438c1?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
0

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.