MCP relay so Claude Code agents on different machines can exchange messages via named channels.
If you already use Claude, the claude mcp server is the piece that lets your assistant work with it directly. MCP relay so Claude Code agents on different machines can exchange messages via named channels.
Claude Code's native Agent Teams coordinate multiple instances on the same machine. Claude Bridge fills the gap — it lets Claude Code agents on different machines communicate in real time over a shared MCP relay server.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
bridge_send — Send a message to a named channelbridge_receive — Read messages — pass since_id for incremental pollingbridge_channels — List all active channels and message countsbridge_ping — Health check + server statsbridge_clear — Clear all messages from a channelbridge_status — Cross-channel overview with recent messagesclaude-code-bridge on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Configuration is passed through the environment: CLAUDE_BRIDGE_AUTH_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
mcp, starlette, uvicorn, anyio, sse-starlette (declared in pyproject.toml; installed automatically by pip install claude-bridge) - A reachable network path between machines — localhost, LAN, Tailscale, or any other route (see Networking) ---Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Claude's toolset — bridge_send, bridge_receive, bridge_channels and 3 more — is a fair guide to whether it matches your workflow. It is maintained by constripacity; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| bridge_send | Send a message to a named channel |
| bridge_receive | Read messages — pass since_id for incremental polling |
| bridge_channels | List all active channels and message counts |
| bridge_ping | Health check + server stats |
| bridge_clear | Clear all messages from a channel |
| bridge_status | Cross-channel overview with recent messages |
{
"mcpServers": {
"claude-code-bridge": {
"command": "uvx",
"args": ["claude-code-bridge"],
"env": {
"CLAUDE_BRIDGE_AUTH_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
mcp, starlette, uvicorn, anyio, sse-starlette (declared in pyproject.toml; installed automatically by pip install claude-bridge) - A reachable network path between machines — localhost, LAN, Tailscale, or any other route (see Networking) ---| Variable | Description | Required |
|---|---|---|
| CLAUDE_BRIDGE_AUTH_TOKEN | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.