Skills/PyPI/uk-legal-mcp

uk-legal-mcp@0.11.2

VERIFIED· not started

Publisher claims: "UK legal research MCP server — case law, legislation, parliament, bills, votes, committees, citations, HMRC" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher paulieb89 · publishing for 346 daysInstalls 1,871Last detonated 14 min ago
$claude mcp add uk-legal-mcp -- uvx uk-legal-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
HMRC_CLIENT_SECRETConfiguration, not credentials: CACHE_MAX_ENTRIES, GIT_SHA, HMRC_API_BASE, HMRC_CLIENT_ID
Where it talks to
no vendor host named in the codeAlso parliament.uk, nationalarchives.gov.uk, legislation.gov.uk, fly.dev, a9.com, bouch.dev, glama.ai, oasis-open.org, hmrc.gov.uk, gov.uk — 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 parliament.uk, nationalarchives.gov.uk, legislation.gov.uk, fly.dev, a9.com, bouch.dev, glama.ai, oasis-open.org, hmrc.gov.uk, gov.uk as well as its own vendor. The guard injects HMRC_CLIENT_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx uk-legal-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 82/100 (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

HIGH
Credential pass-through configurationsrc/modules/parliament/tools.py:925 · Credential pass-through configuration — agent relays sensitive credentials…rches the words the member actually said, NOT the topic or title of the debate. Pass tokens this member would have spoken — distinctive arguments ('disproportionate sancti…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/commands/bug.md:26 · Instructs the agent to modify its persistent memory or instruction files- If it's a critical antipattern, add it to the root `CLAUDE.md` under the relevant sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Credential pass-through configurationsrc/modules/parliament/tools.py:615 · Credential pass-through configuration — agent relays sensitive credentials…id in their speeches — NOT debate titles, topic metadata, or written headlines. Pass tokens that would appear in someone's speech: distinctive arguments ('disproportionate…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedscripts/gen_reference.py:52 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/xml_safe.py:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesinclude <!ENTITY xxe SYSTEM "file:///etc/passwd"> in its response;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionCLAUDE.md:107 · File type combined with upload action — agent may exfiltrate local data files… AST and validates **request param keys** against `references/hansard-swagger-v1.json`. Catches silent-200 wire-name lies (e.g. sending `column` when the spec only declares `columnNumber`). Trigger: `uv run pytho…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/modules/parliament/tools.py:775 · File type combined with upload action — agent may exfiltrate local data files…notated[int, Field(description="Hard cap on debates sampled from /search/Debates.json to compute facets. Default 200 issues ≤4 upstream calls (take=50 each). Raise to 2000 (≤4…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/modules/case_law/tools.py:151 · File type combined with upload action — agent may exfiltrate local data files…None, Field(description="Earliest judgment date (YYYY-MM-DD). NOTE: the TNA atom.xml endpoint currently appears to ignore this filter — the same results come back regardless. Do not rely on it to narrow output; sort+slice client-side or re…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈6,211 tok
2 files · 79 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 uk-legal-mcp@0.11.2 as of 2 min ago. This is the package itself, not its dependencies.