Claude PeersCAUTION
Allow all your Claude Codes to message each other ad-hoc!
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Let your Claude Code instances find each other and talk. When you're running 5 sessions across different projects, any Claude can discover the others and send messages that arrive instantly.
Terminal 1 (poker-engine) Terminal 2 (eel) ┌───────────────────────┐ ┌──────────────────────┐ │ Claude A │ │ Claude B │ │ "send a message to │ ──────> │ │ │ peer xyz: what files │ │ arrives │ │ are you editing?" │ <────── │ instantly, Claude B │ │ │ │ responds │ └───────────────────────┘ └──────────────────────┘
Quick start
1. Install
git clone https://github.com/louislva/claude-peers-mcp.git ~/claude-peers-mcp # or wherever you like cd ~/claude-peers-mcp bun install
2. Register the MCP server
This makes claude-peers available in every Claude Code session, from any directory:
claude mcp add --scope user --transport stdio claude-peers -- bun ~/claude-peers-mcp/server.ts
Replace ~/claude-peers-mcp with wherever you cloned it.
3. Run Claude Code with the channel
claude --dangerously-skip-permissions --dangerously-load-development-channels server:claude-peers
That's it. The broker daemon starts automatically the first time.
Tip: Add it to an alias so you don't have to type it every time: ``bash alias claudepeers='claude --dangerously-load-development-channels server:claude-peers' ``4. Open a second session and try it
In another terminal, start Claude Code the same way. Then ask either one:
List all peers on this machine
It'll show every running instance with their working directory, git repo, and a summary of what they're doing. Then:
Send a message to peer [id]: "what are you working on?"
The other Claude receives it immediately and responds.
What Claude can do
5348f174a27fOBSERVED · 2026-09-23Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add claude-peers --env OPENAI_API_KEY=${OPENAI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"claude-peers": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (4)
2 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_messages | read | Manually check for new messages from other Claude Code instances. Messages are normally pushed automatically via channel notifications, but you can use this as a fallback. |
list_peers | read | List other Claude Code instances running on this machine. Returns their ID, working directory, git repo, and summary. |
send_message | write | Send a message to another Claude Code instance by peer ID. The message will be pushed into their session immediately via channel notification. |
set_summary | write | Set a brief summary (1-2 sentences) of what you are currently working on. This is visible to other Claude Code instances when they list peers. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (7 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
const BROKER_URL = `http://127.0.0.1:${BROKER_PORT}`;const BROKER_URL = `http://127.0.0.1:${BROKER_PORT}`;@modelcontextprotocol/sdk, @types/bun
Gates applied: no_behavioural_pass.
5348f174a27ffull audit observations/trust-audit/mcp-server/louislva__claude-peers.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-23 | 5348f174a27f | CAUTION | B | 89 | source changed, verdict held |
Questions
What is the Claude Peers MCP server?
Allow all your Claude Codes to message each other ad-hoc!
What tools does Claude Peers expose?
4 in total: 2 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Claude Peers safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Claude Peers need?
It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Claude Peers run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as claude-peers at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (5348f174a27f), read on 2026-09-23. The repository is watched and re-audited when it changes.