openinterp-mcp@0.2.0
VERIFIED· not startedPublisher claims: "MCP server + Colab backend for mechanistic interpretability research. Bring-your-own-agent. Privacy-first." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
ANTHROPIC_API_KEYGITHUB_TOKENHF_TOKENOPENAI_API_KEYZENODO_TOKENConfiguration, not credentials: OPENINTERP_REGISTRY_INDEX, OPENINTERP_REGISTRY_REPO, OPENINTERP_SESSIONS_PATH, SMTP_FROM, SMTP_HOST, SMTP_PASS, SMTP_PORT, SMTP_USER, ZENODO_API- Where it talks to
- openinterp.org (its own)Also ngrok-free.app, doi.org, semanticscholar.org, arxiv.org, githubusercontent.com, huggingface.co, zenodo.org — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names ngrok-free.app, doi.org, semanticscholar.org, arxiv.org, githubusercontent.com, huggingface.co, zenodo.org as well as its own vendor. The guard injects ANTHROPIC_API_KEY, GITHUB_TOKEN, HF_TOKEN, OPENAI_API_KEY, ZENODO_TOKEN only into requests to openinterp.org (and its subdomains) and refuses the rest.
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; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 88/100 (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; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
ΔrelFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.print(url) # → https://xxx.ngrok-free.app — paste in Claude CodeFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."endpoint": {"type": "string", "description": "Public HTTPS URL (e.g. https://abc.ngrok-free.app)"},Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.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 openinterp-mcp@0.2.0 as of 16 h ago. This is the package itself, not its dependencies.