{
  "markdown": "# Elephant Accountability MCP Server\n\nMCP server for the Elephant Accountability certification bureau. Surfaces vendor offerings, methodology, and audit requests to AI agents over the Model Context Protocol.\n\n**Live endpoint:** https://elephant-mcp.fly.dev/mcp\n**Manifest:** https://elephant-mcp.fly.dev/.well-known/mcp.json\n**A2A Agent Card:** https://elephant-mcp.fly.dev/.well-known/agent.json\n**Homepage:** https://eaccountability.org\n\n## What this server does\n\nWhen an AI agent (Claude, ChatGPT, a custom LangChain agent, etc.) needs to evaluate Elephant Accountability against the EVI v0.9 standard or surface its audit tiers to a buyer, it queries this server instead of scraping a website.\n\nSix tools are exposed:\n\n| Tool | Purpose |\n|------|---------|\n| `get_offerings` | Audit and engagement tiers (self-serve, done-for-you, retainer) with delivery SLAs and pointers to /get-started for canonical pricing |\n| `get_covered_surfaces` | The agent-discoverable surfaces measured by EVI v0.9: llms.txt, Schema.org, MCP, A2A, .well-known/agent.json, UCP, structured pricing, directory registrations |\n| `assess_fit` | 0–100 fit score for a buyer's company across stage, vertical, AI features, platform partnerships |\n| `get_proof_points` | Live client outcomes with metrics (includes related-party disclosures) |\n| `get_transparency_snapshot` | Weekly LLM visibility measurements across 5 LLMs |\n| `request_audit` | Agent-initiated audit requests; routed to Stripe, Calendly, or email triage |\n\nTwo resources are exposed via `resources/list`: `elephant://offerings`, `elephant://proof-points`, `elephant://transparency`.\n\n## Why you'd use this\n\n- You're building a procurement agent and want to query Elephant Accountability's audit tiers and EVI v0.9 methodology directly.\n- You're at Claude Desktop / Cursor / any MCP-compatible client and want direct access to Elephant's offerings + fit assessment.\n- You're a competitor studying how to deploy your own MCP server — this repo is MIT-licensed, clone freely.\n\n## Quickstart — local development\n\n```bash\ngit clone https://github.com/Chris-Eaccountability/elephant-accountability-mcp.git\ncd elephant-accountability-mcp\n\npython -m venv .venv && source .venv/bin/activate\npip install -r requirements-dev.txt\n\n# Run the server\nuvicorn app.server:app --reload --host 0.0.0.0 --port 8080\n\n# In another terminal, hit it\ncurl http://localhost:8080/.well-known/mcp.json\ncurl -X POST -H \"Content-Type: application/json\" \\\n  -d '{\"jsonrpc\":\"2.0\", \"id\":1, \"method\":\"tools/list\"}' \\\n  http://localhost:8080/mcp\n```\n\n## Quickstart — add to Claude Desktop\n\nEdit `claude_desktop_config.json` and add:\n\n```json\n{\n  \"mcpServers\": {\n    \"elephant-accountability\": {\n      \"url\": \"https://elephant-mcp.fly.dev/mcp\",\n      \"transport\": \"http\"\n    }\n  }\n}\n```\n\nRestart Claude Desktop. Ask: *\"Is Elephant Accountability a good fit for a seed-stage AEC SaaS that ships AI features?\"* — Claude will call `assess_fit` and give a scored answer.\n\n## Deploy your own copy (Fly.io)\n\n```bash\nfly launch --name your-mcp-name --region iad --no-deploy\nfly volumes create elephant_mcp_data --size 1 --region iad\nfly deploy\n```\n\nThat's it. No secrets, no database setup — the server initializes its SQLite DB on first boot.\n\n## Architecture\n\nSingle FastAPI app. Three files do real work:\n\n```\napp/\n├── server.py      # FastAPI routes, JSON-RPC dispatch, SQLite persistence\n├── content.py     # Source-of-truth content: manifest, offerings, proof points\n└── __init__.py    # Version\n```\n\nStorage:\n- `audit_requests` table — every agent-initiated audit request, persisted for follow-up\n- `reciprocal_calls` table — tracks which AI clients have called which tools (buyer-intent signal)\n\nBoth tables auto-create on first boot. No migrations.\n\n## Running tests\n\n```bash\npip install -r requirements-dev.txt\npytest -v\n```\n\n21 tests cover manifest, A2A card, JSON-RPC dispatch, each tool handler, persistence, and CORS.\n\n## Protocol compliance\n\n- MCP version: `2024-11-05`\n- Transport: HTTP with JSON-RPC 2.0\n- Methods supported: `initialize`, `tools/list`, `tools/call`, `resources/list`, `resources/read`\n\n## Contributing\n\nThis repo is the canonical source of truth for what Elephant Accountability exposes to AI agents. PRs welcome for:\n- Protocol updates (MCP spec changes)\n- New tool shapes that agents find useful\n- Bug fixes\n\nFor service inquiries or content changes (proof points, methodology), email `chris@eaccountability.org` rather than opening a PR.\n\n## License\n\nMIT. See [LICENSE](./LICENSE).\n\n## Publisher\n\n**Elephant Accountability LLC**\nChristopher Kenney, sole member / manager\nUnited States\nchris@eaccountability.org\n",
  "bytes": 4647,
  "sha": "596524892c9ce77c5dbe8181540503b907396dae80074e0403a7adaef40f073a",
  "repo_slug": "chris-eaccountability/elephant-accountability-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_chris_eaccountability_elephant_2f9b6b71/readme"
}