mcp-server@2.6.53
VERIFIED· startup onlyPublisher claims: "Model Context Protocol server for Intangle - AI context that persists across conversations" Observed in sandbox: calls registry.npmjs.org, renvoi.co only, touches nothing outside the project, writes no memory.
Coverage
Started with a decoy MCP_API_KEY and answered initialize; the tool list did not come back (tools/list error: MCP remote tools/list failed: 401 Unauthorized). Authenticated tool behavior not tested.- Tested
- server startup with a tagged decoy in MCP_API_KEY · MCP initialize · every file read, file written and host contacted by what ran
- Not tested
- the tool list · what the tools do when called with a real credential
- Needs
- MCP_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
MCP_API_KEYConfiguration, not credentials: INTANGLE_CLAUDE_CHANNEL_CONVERSATION_ID, INTANGLE_CLAUDE_CHANNEL_ORGANIZATION_ID, INTANGLE_CLAUDE_CHANNEL_PARTICIPANT_ID, INTANGLE_CLAUDE_CHANNEL_PARTICIPANT_LABEL, INTANGLE_CLAUDE_CHANNEL_PARTICIPANT_TYPE, INTANGLE_CLAUDE_CHANNEL_SPACE_ID, NEXT_APP_URL, XDG_STATE_HOME- Where it talks to
- renvoi.co, intangle.tools (its own)
- What the honeypot saw
- no credential files read · reached only registry.npmjs.org, renvoi.co (its own)
- What we could not test
- the tool list · what the tools do when called with a real credential
Connect it with a scoped credential, under the guard. It asks for MCP_API_KEY and talks to renvoi.co, intangle.tools. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; started with a decoy MCP_API_KEY and answered initialize; the tool list did not come back (tools/list error: MCP remote tools/list failed: 401 Unauthorized). Authenticated tool behavior not tested) on 2026-11-13 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed (it asks for MCP_API_KEY); the static findings and the publisher carry the rest of the score. Summary: calls registry.npmjs.org, renvoi.co only, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 40 s · 2 scenarios · 0 deviationsStatic findings
console.error("Update with: npx @intangle/mcp-server@latest\n");Fix: Pin versions and sources; vendor anything fetched at install time.UPDATE AVAILABLE: MCP Server v${latestVersion} is available (you're on v${CURRENT_VERSION}). Update with: npx @intangle/mcp-server@latest`;Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for @intangle/mcp-server@2.6.53 as of 14 h ago. This is the package itself, not its dependencies.