regintel-mcp@0.1.0
CAUTION· not startedPublisher claims: "Enables retrieval and structural analysis of FDA regulations.gov dockets: searching dockets, pulling comments and attachments into a local cache, extracting sectioned guidance text, and computing section-aligned draft-versus-final guidance diffs. All results are deterministic and cache-first, with no model calls in the server." 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: Caution 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
TYPESAFE_API_KEYConfiguration, not credentials: DEMO_PASS, DEMO_USER, REGINTEL_HOME- Where it talks to
- no vendor host named in the codeAlso regulations.gov, gsa.gov — 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 regulations.gov, gsa.gov as well as its own vendor. The guard injects TYPESAFE_API_KEY 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 2026-11-13 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive file system command detected; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
"Format \u2014 Standardized"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.… FDA. The guidance for industry, Providing Regulatory Submissions In Electronic Format \u2014 Standardized Study Data (Study Data Guidance), and the technical specifica…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- Write `output/$ARGUMENTS/analysis.json` following the schema in `docs/analysis-schema.json`, and validate it with `python scripts/validate_analysis.py output/$ARGUMENTS/analysis.json`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.f"{ROOT / '.env'} or the environment (get one at https://open.gsa.gov/api/regulationsgov/)."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."notes": "Rule 4: named individual, no affiliation, technical content."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."notes": "Rule 4: named individual, no affiliation, technical content."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.env = ROOT / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.The key is read from the environment or a `.env` file and held only in memory.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.… FDA. The guidance for industry, Providing Regulatory Submissions In Electronic Format \u2014 Standardized Study Data (Study Data Guidance), and the technical specifica…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."notes": "Rule 4: named individual, no affiliation, technical content."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.echo "ready: cd site && npx wrangler pages deploy public --project-name docket-lens"Fix: Pin versions and sources; vendor anything fetched at install time.python scripts/validate_analysis.py output/FDA-2020-D-2307/analysis.json [--corpus output/.../corpus.jsonl]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."Format \u2014 Standardized"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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim black-swan-causal-labs: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.