Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "directory": {
      "type": "http",
      "url": "https://mcp.agenticterminal.ai/mcp"
    }
  }
}

claude mcp add --transport http directory https://mcp.agenticterminal.ai/mcp

[mcp_servers.directory]
url = "https://mcp.agenticterminal.ai/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "directory": {
      "type": "remote",
      "url": "https://mcp.agenticterminal.ai/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "directory": {
      "type": "http",
      "url": "https://mcp.agenticterminal.ai/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=directory&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmFnZW50aWN0ZXJtaW5hbC5haS9tY3AifQ%3D%3D"
}

{
  "servers": {
    "directory": {
      "type": "http",
      "url": "https://mcp.agenticterminal.ai/mcp"
    }
  }
}

{
  "mcpServers": {
    "directory": {
      "httpUrl": "https://mcp.agenticterminal.ai/mcp"
    }
  }
}

extensions:
  "directory":
    enabled: true
    name: "directory"
    type: streamable_http
    uri: "https://mcp.agenticterminal.ai/mcp"
    timeout: 300

Quality 79 / 100good

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 hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_categories (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_merchants (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); verify_payment_endpoint (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 487 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno 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

6 tools, about 487 tokens to load them all · tool set d93592caa086 · checked 2026-10-20 07:53 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

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 88 / 100

provenance85

liveness98

freshness65

hygiene100

+repository +dns-namespace +website +reachable +uptime-95% ~updated-154d-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://mcp.agenticterminal.ai/mcp` streamable-http	none	yes	95%	289 ms	2025-11-25	2026-10-20

Tools (6)

`get_merchant`	Get the full record for one merchant including all rails, payment endpoints, and OP attestation. Tier 2+ requires an AT credential.
`list_categories`	List the category taxonomy with merchant counts.
`list_rails`	List supported payment rails and their current merchant counts.
`search_merchants`	Search OP-verified merchants by rail, chain, category, agent-callable tier, trust tier, and free text. Ranked by trust tier then verification recency.
`verify_payment_endpoint`	Run a live check against a merchant's declared payment endpoint for a rail. Returns health, detail, and rail-specific evidence.
`whoami`	Report the resolved credential state and rate limits for the calling agent.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.agenticterminal/directory",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "ai.agenticterminal": {
        "pitch": "An agent-callable directory of real merchants you can pay over Lightning, L402, BOLT12 or USDT — each carrying an Observer Protocol trust tier. Discover anonymously with no credential or signup, inspect a merchant's payment surface, and verify a rail is live before you send funds. Built for autonomous agents that bring their own wallet and rails.",
        "tools": [
          {
            "name": "search_merchants",
            "description": "Filter merchants by rail, chain, category, trust tier and accepts_usdc; returns ranked summaries plus your resolved auth state."
          },
          {
            "name": "get_merchant",
            "description": "Full record for one merchant: every rail, payment endpoints, agent_endpoints (MCP/REST/API docs) and any OP attestation."
          },
          {
            "name": "verify_payment_endpoint",
            "description": "Live, rail-specific health check of a merchant's payment surface before you transact — and honest about probe-able vs attestation-only rails."
          },
          {
            "name": "list_categories",
            "description": "Category taxonomy with live merchant counts."
          },
          {
            "name": "list_rails",
            "description": "Supported rails and USDT chains with live merchant counts."
          },
          {
            "name": "whoami",
            "description": "Your resolved credential/auth state and rate-limit tier."
          }
        ],
        "categories": [
          "agent-commerce",
          "payments",
          "bitcoin-lightning",
          "stablecoin-usdt",
          "directory"
        ],
        "credibility": [
          "Counterparty-verified, not self-claimed: Bitrefill's Tier-2 status comes from a real autonomous-agent Lightning purchase, preimage-verified on the record. Proof a transaction settled, not a marketing checkbox.",
          "Not a static list: verify_payment_endpoint live-probes a rail and is explicit when a rail is attestation-only rather than rubber-stamping it. The directory tells you what it actually knows."
        ],
        "example_calls": [
          "search_merchants({ rail: \"lightning\", category: \"gift-cards\" })  ->  Bitrefill (Tier 2) ranked first",
          "get_merchant({ id: \"bitrefill\" })  ->  rails, agent_endpoints, attestation",
          "verify_payment_endpoint({ merchant_id: \"bitrefill\", rail: \"lightning\" })  ->  live status + evidence"
        ],
        "anonymous_access": "Reads (search, get, verify) require no credential. Bring your own wallet/rails and transact directly with the merchant — the directory is never in the payment path."
      }
    }
  },
  "title": "Agentic Terminal Directory",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.agenticterminal.ai/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/observer-protocol/at-directory",
    "source": "github"
  },
  "websiteUrl": "https://agenticterminal.ai",
  "description": "Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay."
}