MCP-Bridge

Created By
SecretiveShella year ago
A middleware to provide an openAI compatible endpoint that can call MCP tools
Overview

What is MCP-Bridge?

MCP-Bridge is a middleware that provides an OpenAI compatible endpoint to call MCP tools, enabling developers to integrate MCP tools seamlessly with the OpenAI API.

How to use MCP-Bridge?

To use MCP-Bridge, install it via Docker or manually, configure the necessary settings in the config.json file, and run the service. Once running, you can interact with it using the OpenAI API.

Key features of MCP-Bridge?

  • Non-streaming and streaming chat completions with MCP
  • Integration with various MCP tools
  • SSE Bridge for external clients
  • REST API endpoints for interacting with MCP primitives

Use cases of MCP-Bridge?

  1. Integrating MCP tools with OpenAI API for enhanced functionality.
  2. Facilitating communication between different AI models and tools.
  3. Testing configurations and tool availability through the SSE Bridge.

FAQ from MCP-Bridge?

  • What is the recommended installation method?

The recommended way to install MCP-Bridge is using Docker, but manual installation is also possible.

  • How can I test if my configuration is working?

You can use the SSE endpoint to check the availability of MCP tools and test your configuration.

  • Is there documentation available?

Yes, documentation is available at [http://yourserver:8000/docs].

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
SecretiveShell
Star
672
Language
Python
License
MIT license
Tags

Recommend Servers

View All
Payai X402 Tools

an hour ago
Payai X402 Tools

an hour ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago