trw-mcp@9.5.1
VERIFIED· not startedPublisher claims: "Engineering memory MCP server for Claude Code — patterns, gotchas, and project knowledge that persist across sessions" 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- 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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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 2026-11-20 and scored it 81/100 (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
operator's global egress kill switch, re-checked immediately before theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| Unwanted-behavior | `If <trigger>, then the <system> shall <response>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.``TRW_JEV_ENABLED`` in its ``.env``); or the operator's own ``~/.trw/config.yaml`` machine switchFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Where ``kill -USR1`` dumps go: ``<project>/.trw/logs/thread-dump-<pid>.txt``.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# harness that escalates to SIGKILL after a short grace would kill a clean watch.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# review got `C:/repo/a.py`, `C:\repo\a.py` and `file:///etc/passwd` past it,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# fn is an observe-mode stub, capability_scope not wired, kill switches defaultFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.dotenv_path=project_root / ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| Event-driven | `When <trigger>, the <system> shall <response>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| Ubiquitous | `The <system> shall <response>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.key comes from the env, the project ``.env``, else the owner-only ``~/.trw/jev.env`` machine storeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| Optional-feature | `Where <feature is included>, the <system> shall <response>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| State-driven | `While <precondition>, the <system> shall <response>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.out = subprocess.run( # noqa: S603 - fixed argv, integer pidFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.2. **Run `trw-mcp update-project`** in each project. It writes `AGENTS.md` for Claude Code, removes a TRW-only `CLAUDE.md`, and refreshes every client's instructions.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."""Make ``kill -USR1 <server pid>`` append an all-thread stack dump; called on the serve path only.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.timeout / OOM / sandbox kill is INCONCLUSIVE (FR-03 A2) so planFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# P1-C follow-up: platform_contact_enabled is the global egress killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Only the global ``platform_contact_enabled()`` kill switch gates aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = 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 trw-mcp@9.5.1 as of 21 min ago. This is the package itself, not its dependencies.