_ registry / mcp streamable-http · checked 1h ago

Agent Guard

https://agent-guard.annushka1190.workers.dev

Registry code: 82791e49b285591e

api record

Validate an EVM address (format and checksum style) or a Solana base58 address.

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

endpoint
https://agent-guard.annushka1190.workers.dev/mcp
protocol
streamable-http ·2024-11-05
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 Agent Guard live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is Agent Guard free to use?
No — it charges per call, from 0.001 USDC, quoted in its own 402 answers.
What tools does Agent Guard have?
11 tools: json_repair, pii_redact, wallet_risk_score, risk_full_scan, wallet_heuristic_flags, iban_validate, iban_format_check, x402_endpoint_check, ….
Is Agent Guard 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
99.8%

90 days 99.4%· all time 99.4%

latency
106ms

last good check

priced tools
11

of 11 tools

_ answered our checks, 90 days 677 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
security & compliance threat & vulnerability
used for
  • validate a crypto address checksum
  • validate an iban
  • redact pii from text
  • scan text for crypto scam patterns
  • score wallet risk before paying
takes → gives
text → data
tools
11 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. The address also stands behind 1 other origin: the chain figures are the gateway's, not this listing's alone. How it is counted.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

payers on base
9

distinct

settlements
32

last 2026-11-02

received on chain
0.166 USDC

concentrated, shared-payto

_ what it can do 11 tools
11 paid 11 of 11 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.

  • json_repair reads paid never probed

    Repair broken JSON. Parses malformed JSON typically produced by LLM output: strips markdown code fences, removes trailing commas before ]/}, converts single-quoted strings and unquoted object keys to valid double-quoted JSON. Returns the parsed object plus a boolean flag indicating whether a fix was needed. Price: $0.002 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "json"
  ],
  "properties": {
    "json": {
      "type": "string",
      "description": "Malformed JSON string to repair"
    }
  }
}
    arguments 12 lines
  • pii_redact reads paid never probed

    Redact PII from text. Detects and masks 5 PII categories in free text via regex: email addresses, phone numbers (8+ digits), card numbers (13-19 digits, Luhn-length), US SSN format (XXX-XX-XXXX), and 64-hex-char strings that match an EVM private key shape. Returns the redacted text plus a per-category match count. Price: $0.005 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Free text to scan and redact"
    }
  }
}
    arguments 12 lines
  • wallet_risk_score reads paid never probed

    Deep on-chain wallet risk score. Deep risk scoring for a wallet before your agent pays it. Base: contract vs EOA, tx count, ETH balance, USDC balance, vanity patterns, zero/low activity. Solana: recent signatures, SOL balance, USDC token accounts, activity flags. Returns riskScore (0-1), label (low|medium|high|critical), flags[], metrics, and recommendation (safe_to_pay|review|avoid). Designed for agents that need to decide whether to trust a counterparty wallet. Price: $0.025 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "description": "EVM or Solana address"
    },
    "network": {
      "type": "string",
      "description": "base | solana (default: base)"
    }
  }
}
    arguments 16 lines
  • risk_full_scan reads paid never probed

    Combined risk report (bundle). One paid call runs any combination of: text (PII redact + scam scan), address+network (deep on-chain wallet risk score), iban (mod-97 validation), and resourceUrl (x402 endpoint reputation check) — whichever fields you include in the JSON body. Returns each sub-result plus one aggregated overallRiskScore/overallLabel. $0.04 total vs calling the tools separately. Price: $0.04 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "iban": {
      "type": "string",
      "description": "optional — IBAN validation"
    },
    "text": {
      "type": "string",
      "description": "optional — PII redact + scam scan"
    },
    "address": {
      "type": "string",
      "description": "optional — wallet risk score"
    },
    "network": {
      "type": "string",
      "description": "optional (base|solana)"
    },
    "resourceUrl": {
      "type": "string",
      "description": "optional — x402 endpoint reputation check"
    }
  }
}
    arguments 26 lines
  • wallet_heuristic_flags reads paid never probed

    On-chain wallet heuristic flags (lightweight). Live JSON-RPC call to a public node — eth_getCode + eth_getTransactionCount on Base, or getSignaturesForAddress on Solana. Reports contract-vs-EOA, on-chain transaction count / recent signature count, and repeated-character vanity-address pattern detection. Lightweight pre-filter. For deeper scoring use /v1/wallet/risk-score. Price: $0.015 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "description": "EVM or Solana address"
    },
    "network": {
      "type": "string",
      "description": "base | solana (default: base)"
    }
  }
}
    arguments 16 lines
  • iban_validate reads paid never probed

    Validate IBAN. Full ISO 13616 structural check plus ISO 7064 mod-97-10 check-digit verification (the same algorithm banks use). Returns valid (boolean), country code, and the normalized IBAN string. Price: $0.003 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "iban"
  ],
  "properties": {
    "iban": {
      "type": "string",
      "description": "IBAN string"
    }
  }
}
    arguments 12 lines
  • iban_format_check reads 0.001 USDC paid 19h ago

    Structural check of an IBAN. Regex-only structural check: two-letter ISO 3166 country code, two check digits, 10-30 alphanumeric BBAN characters. Mod-97 check digits are NOT computed here. Use as a cheap pre-filter before the full check at /v1/iban/validate. Price: $0.001 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "iban"
  ],
  "properties": {
    "iban": {
      "type": "string",
      "description": "IBAN string"
    }
  }
}
    arguments 12 lines
  • x402_endpoint_check reads 0.02 USDC paid 19h ago

    x402 counterparty endpoint reputation check. Sends an unauthenticated GET to the given x402 resource URL and checks: does it return HTTP 402, does the accepts[] array include valid payTo/scheme/network/amount fields, is the price under 1.00 USDC, is maxTimeoutSeconds within a normal 5-3600s range, and does /.well-known/x402 exist at the origin. Returns a redFlags array and a 0-1 riskScore — useful before your own agent pays an unfamiliar x402 endpoint. Price: $0.02 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "resourceUrl"
  ],
  "properties": {
    "resourceUrl": {
      "type": "string",
      "description": "Another x402 resource URL to reputation-check"
    }
  }
}
    arguments 12 lines
  • address_format_check reads paid never probed

    Structural check of a crypto address. Regex-only structural check: confirms 0x + 40 hex characters for EVM, or 32-44 char base58 for Solana. No checksum computed, no RPC call made. Use as a cheap pre-filter before the full checksum check at /v1/address/validate. Price: $0.001 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "description": "EVM or Solana address"
    }
  }
}
    arguments 12 lines
  • address_validate reads paid never probed

    Validate crypto address. EIP-55 mixed-case checksum validation for 0x-prefixed 40-hex-character EVM addresses, or base58 charset/length validation for Solana addresses. Returns valid (boolean), chain (evm|solana), and checksumOk fields. Price: $0.003 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string",
      "description": "EVM or Solana address"
    }
  }
}
    arguments 12 lines
  • scam_scan reads paid never probed

    Scam and phishing text scan. Regex-heuristic scan for 7 known crypto-scam patterns: seed-phrase/recovery-phrase requests, gas-fee-in-advance scams, fake wallet-connect airdrop claims, urgency/pressure language, private-key exfiltration requests, unlimited-token-approval drainer patterns, and fake wallet-support impersonation. Returns a 0-1 score, a high/medium/low label, and the list of matched pattern names. Price: $0.005 USDC via x402.

    mcp-tool

    {
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Free text to scan for scam patterns"
    }
  }
}
    arguments 12 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 82791e49b285591e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/82791e49b285591e/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/82791e49b285591e/badge.svg)](https://brick.blue/agent/82791e49b285591e?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.