Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "agent-output-verifier": {
      "type": "http",
      "url": "https://verify.sarnai.dev/mcp"
    }
  }
}

claude mcp add --transport http agent-output-verifier https://verify.sarnai.dev/mcp

[mcp_servers.agent-output-verifier]
url = "https://verify.sarnai.dev/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agent-output-verifier": {
      "type": "remote",
      "url": "https://verify.sarnai.dev/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "agent-output-verifier": {
      "type": "http",
      "url": "https://verify.sarnai.dev/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=agent-output-verifier&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdmVyaWZ5LnNhcm5haS5kZXYvbWNwIn0%3D"
}

{
  "servers": {
    "agent-output-verifier": {
      "type": "http",
      "url": "https://verify.sarnai.dev/mcp"
    }
  }
}

{
  "mcpServers": {
    "agent-output-verifier": {
      "httpUrl": "https://verify.sarnai.dev/mcp"
    }
  }
}

extensions:
  "agent-output-verifier":
    enabled: true
    name: "agent-output-verifier"
    type: streamable_http
    uri: "https://verify.sarnai.dev/mcp"
    timeout: 300

Quality 91 / 100strong

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations2 of 2 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,311 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes5 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 2,311 tokens to load them all · tool set 638c4dd8316b · tools last changed 2026-10-14 · checked 2026-10-20 09:31 UTC

Tool changes

2026-10-14get_verification_recordchangeddescription
before
Use before relying on another AI agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. Agent Scores: $0.01 per lookup when there is a score; a lookup for an AI agent with no history is answered free, signed.
after · 96% of words in common
Agent reputation and trust score: use before relying on another AI agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. AI Agent Scores: $0.01 per lookup when there is a score; a lookup for an AI agent with no history is answered free, signed.
2026-10-14verify_schemachangeddescription, input schema
before
Independent check before paying for another AI agent's work, or before submitting your own. Checks the output against your requirements: structure, formats, ranges, and cross-field rules such as 'line totals must equal the total.' Returns pass/fail, % of checks passed, fix hints, and an Ed25519-signed attestation and receipt you can show as evidence of why you paid or refused. $0.02 per check, small next to the payment it protects. Free during launch: 1000 checks a day (MCP and REST).
after · 87% of words in common
Independent acceptance check of AI agent output before paying for another AI agent's work, or before submitting your own: validate an invoice, check its total, or run JSON Schema validation. Checks structure, formats, ranges, and cross-field rules such as 'line totals must equal the total.' Returns pass/fail, % of checks passed, fix hints, and an Ed25519-signed attestation and receipt you can show as evidence of why you paid or refused. $0.02 per check, small next to the payment it protects. Free during launch: 1000 checks a day (MCP and REST).
2026-10-14get_verification_recordchangeddescription
before
Use before relying on another AI agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. Agent Scores are paid only: $0.01 per lookup.
after · 79% of words in common
Use before relying on another AI agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. Agent Scores: $0.01 per lookup when there is a score; a lookup for an AI agent with no history is answered free, signed.
2026-10-14get_verification_recordchangeddescription, input schema, annotations
before
Use before relying on another agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. Agent Scores are paid only: $0.01 per lookup.
after · 98% of words in common
Use before relying on another AI agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. Agent Scores are paid only: $0.01 per lookup.
2026-10-14verify_schemachangeddescription, input schema, annotations
before
Independent check before paying for another agent's work, or before submitting your own. Checks the output against your requirements: structure, formats, ranges, and cross-field rules such as 'line totals must equal the total.' Returns pass/fail, % of checks passed, fix hints, and an Ed25519-signed attestation and receipt you can show as evidence of why you paid or refused. $0.02 per check, small next to the payment it protects. Free during launch: 1000 checks a day (MCP and REST).
after · 99% of words in common
Independent check before paying for another AI agent's work, or before submitting your own. Checks the output against your requirements: structure, formats, ranges, and cross-field rules such as 'line totals must equal the total.' Returns pass/fail, % of checks passed, fix hints, and an Ed25519-signed attestation and receipt you can show as evidence of why you paid or refused. $0.02 per check, small next to the payment it protects. Free during launch: 1000 checks a day (MCP and REST).

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 96 / 100

provenance85

liveness100

freshness100

hygiene100

+repository +dns-namespace +website +reachable +uptime-100% +updated-6d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://verify.sarnai.dev/mcp` streamable-http	none	yes	100%	381 ms	2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05	2026-10-20

Tools (2)

get_verification_recordread-only Agent reputation and trust score: use before relying on another AI agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. AI Agent Scores: $0.01 per lookup when there is a score; a lookup for an AI agent with no history is answered free, signed.

verify_schema Independent acceptance check of AI agent output before paying for another AI agent's work, or before submitting your own: validate an invoice, check its total, or run JSON Schema validation. Checks structure, formats, ranges, and cross-field rules such as 'line totals must equal the total.' Returns pass/fail, % of checks passed, fix hints, and an Ed25519-signed attestation and receipt you can show as evidence of why you paid or refused. $0.02 per check, small next to the payment it protects. Free during launch: 1000 checks a day (MCP and REST).

Schemas: list_tools.

Similar MCP servers

More from dev.sarnai

Official server.json

{
  "name": "dev.sarnai/agent-output-verifier",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "payment": "Verification is free during launch within a daily allowance per caller, through MCP and REST (the live allowance is stated in the \"Free allowance\" section of https://verify.sarnai.dev/llms.txt). Agent Scores (get_verification_record) are paid only: $0.01 per lookup. After the allowance, each call requires an x402 payment (USDC on Base and Solana) in the MCP request's _meta under \"x402/payment\". Exact prices, networks and the pay-to address are in the agent-card.",
      "agentCardUrl": "https://verify.sarnai.dev/.well-known/agent-card.json"
    }
  },
  "icons": [
    {
      "src": "https://board.sarnai.dev/static/sarnai-icon-512.png",
      "sizes": [
        "512x512"
      ],
      "mimeType": "image/png"
    },
    {
      "src": "https://board.sarnai.dev/static/sarnai-icon-192.png",
      "sizes": [
        "192x192"
      ],
      "mimeType": "image/png"
    }
  ],
  "title": "Agent Output Verifier by SarnAI",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://verify.sarnai.dev/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.5.7",
  "repository": {
    "url": "https://github.com/sarnai-dev/agent-output-verifier",
    "source": "github"
  },
  "websiteUrl": "https://github.com/sarnai-dev/agent-output-verifier",
  "description": "Independent schema and rule check of AI agent output before you pay. Signed attestation and receipt."
}