{
  "markdown": "# Mnemom — Trust Ratings for AI Agents (MCP server)\n\nCanonical home for the **Mnemom** Model Context Protocol (MCP) server — trust\ninfrastructure for the agent internet. Look up a verifiable **Trust Rating** for\nan AI agent, **scan a website's** AI-trust-readiness, **verify** signed\nscorecards in‑band, claim an agent identity, and publish an alignment card.\n\nThis repo is the public, canonical source of truth for the server's connection\ndetails and manifest. The server implementation runs on Mnemom's platform; this\nrepo is its metadata + documentation home.\n\n- **Website:** https://www.mnemom.ai · for agents: https://www.mnemom.ai/for-agents\n- **Docs:** https://docs.mnemom.ai\n- **Rubric (isittrustready):** https://www.isittrustready.ai/rubric\n- **Official MCP registry:** `io.github.mnemom/mnemom`\n- **Maintainer:** support@mnemom.ai\n\n## Connect\n\nStreamable‑HTTP MCP endpoint (curated directory profile, 16 tools):\n\n```\nhttps://api.mnemom.ai/mcp?profile=directory\n```\n\nThe full manifest is in [`server.json`](./server.json).\n\n### In Claude / ChatGPT / any MCP client\n\nAdd a custom connector pointing at the URL above. **Reads are anonymous** — you\ncan list tools and call the reputation, search, scan, verify, and get‑started\ntools with no account. **Writes** (claiming an agent, publishing an alignment\ncard) require authentication.\n\n## Authentication\n\n- **Reads:** zero‑auth. No key, no login.\n- **Writes:** OAuth 2.0 with **Dynamic Client Registration (RFC 7591)** + **PKCE**.\n  Discovery follows **RFC 9728** — an unauthenticated write returns `401` with a\n  `WWW‑Authenticate` header pointing at the Protected Resource Metadata, so a\n  compliant client can self‑configure:\n  - Protected Resource Metadata: `https://api.mnemom.ai/.well-known/oauth-protected-resource/mcp`\n  - Authorization Server Metadata: `https://api.mnemom.ai/.well-known/oauth-authorization-server`\n- An `X-Mnemom-Api-Key` header is accepted as an alternative to OAuth.\n\n## What's in the directory profile\n\nA curated 16‑tool surface, grouped:\n\n- **Reputation** — `get_reputation`, `get_reputation_badge`,\n  `search_reputation_directory`, `verify_reputation`, `list_agents`, `get_agent`\n  (agent risk history is authenticated — see `get_risk_history` on the full surface)\n- **Website trust scanning** — `scan_trust`, `verify_scan`\n- **Identity & protection** — `claim_agent`, `verify_agent_binding`,\n  `preview_compose_alignment_by_agent`, `put_alignment_by_agent`,\n  `preview_compose_protection_by_agent`, `put_protection_by_agent`,\n  `report_recipe_fn_fp`\n- **Orientation** — `get_started`\n\nThe default endpoint (`/mcp`, no profile) exposes the full power‑user tool\nsurface; `?profile=directory` is the curated face used for directory listings.\n\n## Verify, don't trust\n\nScan scorecards are **Ed25519‑signed**. Verify any scorecard in‑band with the\n`verify_scan` tool, or check the signature yourself against the published key:\n\n- Scanner JWKS: `mnemom://iitr/jwks` (also at the isittrustready surface)\n- The scorecard carries a self‑describing `verification` block (algorithm, key\n  id, canonicalization rule) so a holder can reconstruct and check the signature.\n\n## Links\n\n| | |\n|---|---|\n| Website | https://www.mnemom.ai |\n| For agents | https://www.mnemom.ai/for-agents |\n| Documentation | https://docs.mnemom.ai |\n| Trust‑readiness rubric | https://www.isittrustready.ai/rubric |\n| Contact | support@mnemom.ai |\n\n---\n\n© Mnemom. The server implementation is operated by Mnemom; this repository is its\npublic manifest and documentation home.\n",
  "bytes": 3529,
  "sha": "ba35ec3790a39866af080bf1ae70351313c32a57527e0fb2cd5878ca10f9f36f",
  "repo_slug": "mnemom/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_mnemom_isittrustready_ecb6ef2c/readme"
}