Skills/PyPI/trw-mcp

trw-mcp@9.5.1

VERIFIED· not started

Publisher 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.

Registry PyPI (MCP server)Publisher wallter · publishing for 239 daysInstalls 288Last detonated 54 min ago
$claude mcp add trw-mcp -- uvx trw-mcp
WatchReport an issue

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.

$vet-skills run --net declared -- uvx trw-mcp

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandsrc/trw_mcp/sync/backup.py:19 · Process kill command — agent can terminate processesoperator's global egress kill switch, re-checked immediately before theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Fake instruction boundary tagsrc/trw_mcp/data/aaref.md:59 · Fake instruction boundary tag · informational: not an instruction file| 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.
AST01
HIGH
Access to sensitive file pathssrc/trw_mcp/tools/assess.py:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files``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.
AST05
MEDIUM
Process kill commandsrc/trw_mcp/server/_cli.py:106 · Process kill command — agent can terminate processes"""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.
AST05
MEDIUM
Process kill commandsrc/trw_mcp/comms/_watch.py:208 · Process kill command — agent can terminate processes# 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.
AST05
HIGH
Access to sensitive file pathssrc/trw_mcp/plan/_schema.py:136 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 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.
AST05
MEDIUM
Process kill commandpyproject.toml:183 · Process kill command — agent can terminate processes# 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.
AST05
HIGH
Access to sensitive file pathssrc/trw_mcp/tools/assess.py:145 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv_path=project_root / ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Fake instruction boundary tagsrc/trw_mcp/data/aaref.md:57 · Fake instruction boundary tag · informational: not an instruction file| 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.
AST01
LOW
Fake instruction boundary tagsrc/trw_mcp/data/aaref.md:55 · Fake instruction boundary tag · informational: not an instruction file| Ubiquitous | `The <system> shall <response>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathssrc/trw_mcp/tools/assess.py:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileskey 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.
AST05
LOW
Fake instruction boundary tagsrc/trw_mcp/data/aaref.md:58 · Fake instruction boundary tag · informational: not an instruction file| 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.
AST01
LOW
Fake instruction boundary tagsrc/trw_mcp/data/aaref.md:56 · Fake instruction boundary tag · informational: not an instruction file| 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.
AST01
MEDIUM
Python subprocess execution detectedsrc/trw_mcp/comms/_hint.py:65 · Python subprocess execution detectedout = subprocess.run( # noqa: S603 - fixed argv, integer pidFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:92 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file2. **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.
AST01
MEDIUM
Process kill commandsrc/trw_mcp/server/_cli.py:125 · Process kill command — agent can terminate processes"""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.
AST05
MEDIUM
Process kill commandsrc/trw_mcp/probe/harness.py:70 · Process kill command — agent can terminate processestimeout / OOM / sandbox kill is INCONCLUSIVE (FR-03 A2) so planFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/trw_mcp/sync/push.py:189 · Process kill command — agent can terminate processes# 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.
AST05
MEDIUM
Process kill commandsrc/trw_mcp/sync/backup.py:314 · Process kill command — agent can terminate processesOnly the global ``platform_contact_enabled()`` kill switch gates aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/trw_mcp/startup.py:35 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈63 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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.