tf-mcp-server@0.35.1
VERIFIED· not startedPublisher claims: "MCP server for ToothFairyAI documentation, SDK operations, and cross-workspace agent migration via @toothfairyai/cli" 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
API_TOKENConfiguration, not credentials: API_DOCS_PATH, API_URL, BASE_PATH, DB_URL, DOCS_PATH, MCP_HOST, MCP_PORT, MCP_TRANSPORT, OUT_NAME, TF_ENV, TFCODE_PATH, TFCODE_STABLE_PATH, TFCODE_STABLE_VERSION, TFDESIGN_PATH- Where it talks to
- no vendor host named in the codeAlso toothfairyai.com, toothfairylab.link, microsoft.com, microsoftonline.com, azure.com, weather.com, amazonaws.com — 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 toothfairyai.com, toothfairylab.link, microsoft.com, microsoftonline.com, azure.com, weather.com, amazonaws.com as well as its own vendor. The guard injects API_TOKEN only into requests to the host you bind (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 2026-11-19 and scored it 80/100 (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
"For OAuth authorization_code: do NOT pass token_secret here. It will be set in step 3.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Your code string is executed via exec() in a sandboxed globals "Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.IMPORTANT: Never pass secret values directly in authorisations.create().Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."exec(code, namespace, namespace) # globals == locals"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own." exec()s the combined string (see hook-code-runtime).",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."content is re-dumped to a .txt and the .txt is uploaded; the "Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."Expect .json outputs to stay .json (auto-converted to .txt)",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Any .json file in the output folder is auto-converted: its "Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."package": "tf-mcp-server (this server) / hosted https://mcp.toothfairyai.com/sse",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."Output files must go to /tmp/{ws}/{msg}/output/ to be auto-uploaded to S3 (.json auto-converted to .txt); print() text output",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."cause": "Runtime auto-converts .json in output to .txt (re-dumps content).",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."Output written to .../output/summary.csv is auto-uploaded to S3.",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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 tf-mcp-server@0.35.1 as of 9 min ago. This is the package itself, not its dependencies.