thought-mcp@0.5.1
VERIFIED· not startedPublisher claims: "THOUGHT — Temporal Hierarchical Object Union & Graph Hybrid Toolkit. A local MCP memory server with bi-temporal graph + vector + temporal layers, a query router, and a consolidation engine." 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_KEYOPENAI_API_KEYor--budget-tokensConfiguration, not credentials: THOUGHT_DB_PATH, THOUGHT_EMBEDDER- Where it talks to
- no vendor host named in the codeAlso claude.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 claude.com as well as its own vendor. The guard injects ANTHROPIC_API_KEY, OPENAI_API_KEY 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 86/100 (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
&& rm -rf /wheelsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.head_sha = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.if importlib.util.find_spec("sentence_transformers") is not None:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# write config + db + CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.RUN mkdir -p /data && chown -R thought:thought /data /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.diff = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# write config + db + CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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 thought-mcp@0.5.1 as of 6 h ago. This is the package itself, not its dependencies.