{
  "markdown": "# APIbase.pro — The API Hub for AI Agents\n\nProduction MCP server: one endpoint gives AI agents access to 1342 tools from 382 providers, pay-per-call via x402 (USDC on Base) or MPP (USDC on Tempo).\n\n[![Security Audit](https://github.com/whiteknightonhorse/APIbase/actions/workflows/security.yml/badge.svg)](https://github.com/whiteknightonhorse/APIbase/actions/workflows/security.yml)\n[![Deploy](https://github.com/whiteknightonhorse/APIbase/actions/workflows/deploy.yml/badge.svg)](https://github.com/whiteknightonhorse/APIbase/actions/workflows/deploy.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n[![MCP Registry](https://img.shields.io/badge/MCP_Registry-Listed-blue)](https://registry.modelcontextprotocol.io)\n[![Smithery](https://img.shields.io/badge/Smithery-Live-brightgreen)](https://smithery.ai/servers/apibase-pro/api-hub)\n[![MPPScan](https://img.shields.io/badge/MPPScan-Listed-purple)](https://www.mppscan.com/server/2ce70c5f97be51cfcabe13aad9b5f4beae6dc77be586357e04db17644729303d)\n\n---\n\n## Quick Start\n\n```json\n{\n  \"mcpServers\": {\n    \"apibase\": { \"url\": \"https://apibase.pro/mcp\" }\n  }\n}\n```\n\nThat's the Claude Desktop config. Cursor, Windsurf, OpenAI Agents SDK, LangChain, Google ADK, CrewAI, Microsoft Copilot Studio, and plain REST: **[apibase.pro/connect](https://apibase.pro/connect)**.\n\n---\n\n## For AI Agents\n\n- **[llms.txt](https://apibase.pro/llms.txt)** — concise LLM context\n- **[ai.txt](https://apibase.pro/ai.txt)** — plain-text agent discovery\n- **[mcp.json](https://apibase.pro/.well-known/mcp.json)** — MCP server metadata\n- **[openapi.json](https://apibase.pro/.well-known/openapi.json)** — OpenAPI 3.1 spec\n- **[api-catalog](https://apibase.pro/.well-known/api-catalog)** — RFC 9727 discovery linkset\n\n---\n\n## Integrations & Registries\n\n**[Full framework guides →](https://apibase.pro/frameworks)**\n\nRegistry listings: [Smithery](https://smithery.ai/servers/apibase-pro/api-hub) · [Glama](https://glama.ai/mcp/servers/whiteknightonhorse/APIbase) · [MCP Registry](https://registry.modelcontextprotocol.io) (`io.github.whiteknightonhorse/apibase`) · [PulseMCP](https://pulsemcp.com) · [MPPScan](https://www.mppscan.com)\n\n---\n\n## Self-Hosting\n\n```bash\ngit clone https://github.com/whiteknightonhorse/APIbase.git && cd APIbase\ncp .env.example .env   # set POSTGRES_PASSWORD, X402_PAYMENT_ADDRESS, provider keys\ndocker compose -f docker-compose.yml -f docker-compose.prod.yml up -d\n```\n\nFull prerequisites, verification steps, and config reference: [`docs/self-hosting.md`](docs/self-hosting.md).\n\n---\n\n## Architecture\n\nSingle Node.js/TypeScript API server, PostgreSQL as the append-only financial source of truth, Redis for cache/rate-limiting only, multi-container Docker stack on one Hetzner server. Every tool call runs the same multi-stage pipeline (escrow-first, idempotent, fail-closed, content-moderated) — dual-rail payments (self-hosted x402 facilitator + MPP), error-code contract, and full container/pipeline detail (exact counts, live): [`docs/architecture.md`](docs/architecture.md).\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 3120,
  "sha": "68ce830a11de3c5cfacedefd793c27cd0040e8825712dc6e082bdb288747f8dc",
  "repo_slug": "whiteknightonhorse/apibase",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_whiteknightonhorse_apibase_5981efda/readme"
}