Relays messages between two Claude Code sessions running on separate machines, using the Channels API to push an incoming message directly into the other session so one session can ask another about its own checkout. Each message carries an id and is tracked as sent, delivered-to-process, or answered, with a per-message reply budget.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
MuhammadTalhaMT
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
INTERCOM_PORT"": "8788"INTERCOM_SECRET"": "your-shared-secret",INTERCOM_SEND_TIMEOUT_MSNo 10000 How long an outbound POST may hang before giving upMY_ROLE"": "backend",REMOTE_HOST"": "MACHINE_B_IP:8788",Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
2/2 tools missing one or more hints — send_message (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_message (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process/subprocess call in production code — runs shell commands (bin/claude-intercom.mjs:18)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets stay with their owner
1 secret/sensitive value flow into network calls (INTERCOM_SECRET → dynamic)
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/muhammadtalhamt-claude-intercom-17m26e)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check