mcp-personal-assistant@0.2.2
VERIFIED· not startedPublisher claims: "Personal Assistant MCP Server with SQLite/TinyDB support for status tracking, project management, todos, calendar functionality, and document storage" 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_KEYSAUTH_ENABLEDAUTH_PROVIDERAUTH0_AUDIENCEAUTH0_DOMAINDATABASE_URLGITHUB_TOKENGOOGLE_CLIENT_SECRETJWT_SECRETMCP_HTTP_API_KEYMCP_HTTP_API_KEYSMCP_HTTP_AUTH0_AUDIENCEMCP_HTTP_AUTH0_DOMAINMCP_HTTP_DATABASE_CONNECTION_STRINGMCP_HTTP_GOOGLE_CLIENT_SECRETOAUTH_CLIENT_IDOAUTH_CLIENT_SECRETOAUTH_ISSUEROPENAI_API_KEYPGVECTOR_CONNECTION_STRINGor--with-tokenConfiguration, not credentials: CACHE_BACKEND, CACHE_ENABLED, CACHE_MAX_SIZE, CACHE_TTL, CORS_ORIGINS, DB_ENCRYPTION_KEY, DB_PATH, DB_POOL_SIZE, DB_TYPE, EMBEDDING_DIMENSION, EMBEDDING_MODEL, EMBEDDING_PROVIDER, ENVIRONMENT, FEATURE_DOCUMENT_INDEXING, FEATURE_INTELLIGENT_DASHBOARD, FEATURE_MULTI_TENANCY, FEATURE_RATE_LIMITING, FEATURE_SEMANTIC_SEARCH, GOOGLE_CLIENT_ID, HEALTH_CHECK_PATH- Where it talks to
- no vendor host named in the codeAlso your-mcp-api.com, google.com, myapp.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 your-mcp-api.com, google.com, myapp.com as well as its own vendor. The guard injects API_KEYS, AUTH_ENABLED, AUTH_PROVIDER, AUTH0_AUDIENCE, AUTH0_DOMAIN, DATABASE_URL, GITHUB_TOKEN, GOOGLE_CLIENT_SECRET, JWT_SECRET, MCP_HTTP_API_KEY, MCP_HTTP_API_KEYS, MCP_HTTP_AUTH0_AUDIENCE, MCP_HTTP_AUTH0_DOMAIN, MCP_HTTP_DATABASE_CONNECTION_STRING, MCP_HTTP_GOOGLE_CLIENT_SECRET, OAUTH_CLIENT_ID, OAUTH_CLIENT_SECRET, OAUTH_ISSUER, OPENAI_API_KEY, PGVECTOR_CONNECTION_STRING 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 2026-11-08 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
for suspicious in ["../", ".env", "passwd", "admin", "config"]):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo "Then set them in your shell profile or .env file"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.sudo \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.&& apt-get clean && rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.RUN chmod +x run_http_server.pyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.&& chmod go+r /usr/share/keyrings/githubcli-archive-keyring.gpg \Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.result = subprocess.run(command, shell=True, check=True, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.chown -R node:node /workspace && \Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.&& chown -R $USERNAME /commandhistoryFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.sudo dpkg -i "git-delta_${GIT_DELTA_VERSION}_${ARCH}.deb" && \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chown -R node:node /home/node/.claudeFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.chown -R node:node /usr/local/shareFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.&& apt-get clean && rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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 mcp-personal-assistant@0.2.2 as of 6d ago. This is the package itself, not its dependencies.