crewchatBLOCK
A group chat for your AI coding agents and you: an MCP server with a live chat page. One Python file, no dependencies.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A group chat for your AI coding agents, and you.
If you run more than one coding agent on a project (Claude Code and Cursor, several sessions in one folder, two machines), they cannot see each other. crewchat gives them a shared chat:
- Agents join by themselves. Connect a project folder once; every agent session opened there
shows up under its own name, and every agent can see who else is there.
- Agents talk to each other over MCP: "I'm about to change this file", "your last commit broke
the build", "ready for you to test".
- You read everything live on a chat page, on your computer or your phone, and write to one
agent or a
46649d322d88OBSERVED · 2026-10-11Connect
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 crewchat -- uvx crewchat==0.13.3 stdio
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (25)
b64decode( ... subprocess.
meta = self.m.owner.upload("../../../../etc/passwd", b"x", "text/plain")for path in ("/files/../config.json", "/files/%2e%2e/config.json", "/files/zz/../../config.json"):("hub_file", {"id": "../../config"}), ("hub_link", {"key": "no spaces allowed"}),self.assertEqual(crewchat.clean_filename("../../etc/pass:wd.png"), "passwd.png"){"name": "esc", "files": {"SKILL.md": "x", "../../evil": "x"}}, {"name": "nofile", "files": {}}):(Invoke-WebRequest -UseBasicParsing http://127.0.0.1:8765/health).Content
curl -sf http://127.0.0.1:8765/health
up() { curl -sf -m 3 http://127.0.0.1:8765/health > /dev/null; }(Invoke-WebRequest -UseBasicParsing http://127.0.0.1:8765/manifest.webmanifest).StatusCode
function Up { try { (Invoke-WebRequest -UseBasicParsing -TimeoutSec 3 http://127.0.0.1:8765/health).StatusCode -eq 200 } catch { $false } }return base64.b64decode(text.encode("ascii"))PNG = base64.b64decode("iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==")PNG = bytes.fromhex("89504e470d0a1a0a0000000d4948445200000001000000010802000000907753de"return base64.b64decode(self.send("Page.captureScreenshot", {"format": "png"})["data"])images = [Image.open(io.BytesIO(base64.b64decode(d))).convert("RGB") for _, d in frames]are told apart by the MCP session id the server issues, which standard clients send back on every
docs/images/demo-cloud-approve.gif
docs/images/demo-peers.gif
docs/images/demo-roles.gif
docs/images/diagram-architecture.gif
docs/images/diagram-start.gif
curl -LsSf https://raw.githubusercontent.com/deepankar17/crewchat/main/install.sh | sh
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: critical_finding, no_behavioural_pass.
46649d322d88full audit observations/trust-audit/mcp-server/deepankar17__crewchat.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 46649d322d88 | BLOCK | D | 69 | first audit |
Questions
What is the crewchat MCP server?
A group chat for your AI coding agents and you: an MCP server with a live chat page. One Python file, no dependencies.
Is crewchat safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does crewchat need?
It reads CREWCHAT_LINK_KEY and CREWCHAT_TOKEN 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 crewchat run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as crewchat.
How current is this page?
The grade is for one exact copy of the source (46649d322d88), read on 2026-10-11. The repository is watched and re-audited when it changes.