a2a-mcp-bridge
A stdio MCP server that allows MCP-capable agents to call an A2A endpoint, enabling agent-to-agent messaging through the A2A protocol.
README
A2A Agent Bridge
Small A2A bridge experiments for OpenClaw/Home Ops agent-to-agent messaging.
This repository contains two pieces:
a2a-agent-bridge/: an HTTP A2A server exposing an Agent Card, JSON-RPC endpoint, and/healthz.a2a-mcp-bridge/: a stdio MCP server that lets MCP-capable agents call an A2A endpoint.
The A2A server is intentionally minimal and in-memory. It is useful as a real protocol target for the A2A Inspector and for wiring agent clients, but it is not yet a durable multi-agent queue.
A2A Server
Build locally:
docker build -t a2a-agent-bridge .
Run locally:
docker run --rm -p 8080:8080 \
-e A2A_AGENT_NAME="Home Ops Agent Bridge" \
-e A2A_BASE_URL="http://localhost:8080" \
a2a-agent-bridge
Endpoints:
GET /healthzGET /.well-known/agent-card.jsonPOST /for A2A JSON-RPCGET /bridge/inbox/{agent}for ephemeral inbox pollingPOST /bridge/inbox/{agent}/ackfor inbox acknowledgements
Inbox endpoints are in-memory and intentionally non-durable. Set
A2A_BRIDGE_TOKEN to require either Authorization: Bearer <token> or
X-A2A-Bridge-Token: <token> for inbox polling/acknowledgement.
MCP Bridge
The MCP bridge lives in a2a-mcp-bridge/ and can be run with:
cd a2a-mcp-bridge
uv run a2a-mcp-bridge
Set A2A_AGENT_URL to point at the target A2A server.
Set A2A_BRIDGE_TOKEN when polling protected inbox endpoints.
Home Ops
Home Ops should consume this repository via the published GHCR image rather than storing the A2A server source in a ConfigMap.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.