vaquill-mcp@0.5.0
VERIFIED· not startedPublisher claims: "MCP server for the Vaquill legal research API - search US federal and 50-state statutes, regulations, constitutions, and court rules via AI" 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_APPS_CHALLENGE_TOKENVAQUILL_API_KEYVAQUILL_INTERNAL_SECRETVAQUILL_OAUTH_ALGORITHMVAQUILL_OAUTH_ALLOWED_REDIRECT_URISVAQUILL_OAUTH_AUDIENCEVAQUILL_OAUTH_AUTHORIZE_URLVAQUILL_OAUTH_CLIENT_IDVAQUILL_OAUTH_CLIENT_SECRETVAQUILL_OAUTH_TOKEN_URLVAQUILL_OAUTH_UPSTREAM_ISSUERVAQUILL_OAUTH_UPSTREAM_JWKS_URIConfiguration, not credentials: VAQUILL_BASE_URL, VAQUILL_JURISDICTION, VAQUILL_PUBLIC_URL, VAQUILL_TIMEOUT- Where it talks to
- vaquill.ai (its own)Also claude.ai — 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.ai as well as its own vendor. The guard injects ANTHROPIC_API_KEY, OPENAI_APPS_CHALLENGE_TOKEN, VAQUILL_API_KEY, VAQUILL_INTERNAL_SECRET, VAQUILL_OAUTH_ALGORITHM, VAQUILL_OAUTH_ALLOWED_REDIRECT_URIS, VAQUILL_OAUTH_AUDIENCE, VAQUILL_OAUTH_AUTHORIZE_URL, VAQUILL_OAUTH_CLIENT_ID, VAQUILL_OAUTH_CLIENT_SECRET, VAQUILL_OAUTH_TOKEN_URL, VAQUILL_OAUTH_UPSTREAM_ISSUER, VAQUILL_OAUTH_UPSTREAM_JWKS_URI only into requests to vaquill.ai (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 2026-11-20 and scored it 85/100 (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 /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/.cacheFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert r.json()["n"] == len(httpx.Request("POST", "http://x", json=payload).content)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.mcp_app = mcp_server.http_app(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them._FORUM, "../../etc/passwd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.monkeypatch.setenv("VAQUILL_BASE_URL", "file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# `set -a` exports everything sourced from .env, then `exec` replaces the shellFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.("cat_cis", "../../../etc/passwd"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Dokploy writes the app's saved environment variables to `.env` in the buildFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.RUN mkdir -p /data && chown 65532:65532 /dataFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.return response.json()["input_tokens"]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# The trailing `*` keeps the build working on a machine with no .env (localFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.COPY --chown=65532:65532 .env* ./Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.) or "/" not in _file_name(_FORUM, "../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.mcp_app = mcp_server.http_app(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.mcp_app = mcp_server.http_app(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.# environment variables and no .env behaves identically.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.spec = importlib.util.find_spec(module)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
Not checked against OSV yet; the weekly check has not reached this version.