Docket Lens

com.blackswancausallabsPublished by blackswancausallabs.comv0.1.0Updated Oct 29, 2026

Retrieve FDA docket comments, attachments and draft/final guidance for reviewable analysis.

The publisher's own server: docket

VerifiedSTDIODesktop onlyWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Retrieves FDA regulations.gov docket comments, attachments and guidance documents, and diffs draft against final guidance, for local analysis.

What you can do
  • Search dockets and read docket metadata and comment counts
  • List documents (notices, draft and final guidance, meeting material) with file URLs
  • List and read comments, including submitter fields, attachments and extracted attachment text
  • Build a resumable local corpus of comments and attachments, and export it as JSONL
  • Split guidance into numbered sections and diff draft against final with moved-paragraph detection
When to use it
Useful when you need to review an FDA rulemaking docket: who commented, what they asked for, and how draft guidance text changed in the final version. Suited to regulatory research and analysis workflows rather than general web search.
Requirements
Runs as a local Python process (Python 3.11 or later; the MCP bundle also needs uv) with a writable working folder. Requires a free regulations.gov API key supplied as REGULATIONS_GOV_API_KEY; DEMO_KEY works for single lookups but is heavily rate-limited. Network access is needed on cache misses or with refresh=true.
Before you install
The API key is a credential: keep it in .env, which is gitignored, and note it is sent as the X-Api-Key header. Tools write to a local SQLite cache and to output files. Results measure concordance between draft and final text, not the impact of any comment, and the server performs no interpretation.

Installation

In SourceWeft

  1. Open Docket Lens in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

regintel-mcp

Regulatory intelligence from FDA regulations.gov dockets: who commented, what they asked for, and what changed between the draft and final guidance.

Black Swan Causal Labs · blackswancausallabs.com

Retrieval lives in the MCP server. Judgment lives in skills. Humans sit at the checkpoints.

LayerComponentStatus
Dataregintel-mcp server (this repo, MIT)Phase 1 built. Fetch, cache, extract, diff. No interpretation.
Methodskills: submitter-taxonomy, comment-theming, draft-final-concordanceBuilt
Orchestration/docket-analysis <docketId> with 4 human checkpointsBuilt; first run on FDA-2020-D-2307
OutputDocket Lens explorer (reads one analysis.json; PolyForm Noncommercial)Built for FDA-2020-D-2307

Install

Python 3.11 or later.

bash
git clone https://github.com/Black-Swan-Causal-Labs/regintel-mcp.gitcd regintel-mcppython3 -m venv .venv && .venv/bin/pip install -e .cp .env.example .env    # then paste your key into .env

API key: get a free key at https://open.gsa.gov/api/regulationsgov/ and put it in .env as REGULATIONS_GOV_API_KEY=.... .env is gitignored. The key is sent only as the X-Api-Key header and never appears in logs, the cache or any output. DEMO_KEY is fine for single lookups but too rate-limited for a full corpus pull. Personal keys allow 1,000 requests/hour.

Register with an MCP client. MCP is an open standard, so the server works with any compatible assistant (Claude, OpenAI Codex, others). For Claude Code, from the repo directory:

bash
claude mcp add regintel-mcp -- "$(pwd)/.venv/bin/python" -m regintel_mcp

When installed as a Claude plugin, .mcp.json starts the server from the plugin root.

Tools

Every tool reads the local SQLite cache (data/cache.sqlite) first. It only touches the network on a cache miss or when called with refresh=true.

ToolDoes
search_dockets(query, agency="FDA", docket_type?, limit=25)Keyword search over dockets
get_docket(docket_id)Docket metadata and total comment count
list_documents(docket_id)Notices, draft and final guidance, meeting material, with every file URL
list_comments(docket_id, include_withdrawn=false)All comments, paginated internally. Flags is_stub, duplicate_of and agency_duplicate_count (flags only; nothing is dropped)
get_comment(comment_id)Body, submitter fields, attachments and extracted attachment text
build_corpus(docket_id, with_attachments=true)Pulls every comment and attachment into the cache. Resumable. Reports stubs, duplicates, OCR needs and failures
get_guidance_text(ref)A guidance document (doc ID or URL) split into numbered sections
diff_guidance(draft_ref, final_ref)Section-aligned draft-vs-final diff with paragraph changes and moved-paragraph detection
export_corpus(docket_id)Writes output/<docket>/corpus.jsonl for skills and subagents

For long pulls outside a chat: .venv/bin/python -m regintel_mcp build-corpus FDA-2020-D-2307.

How the diff works: the text layer is extracted with pdfplumber. Running headers, draft line numbers, footnotes and the table of contents are removed. Sections are split on the guidance's own Roman, letter and number headings, then matched draft→final by heading (parent-qualified first) and then by heading plus text similarity. Paragraphs are diffed within each matched section, and paragraphs that moved to a different section are labelled. Everything is deterministic: there are no model calls in the server.

API behaviour verified against the live service is recorded in docs/api-notes.md.

Docket Lens (the explorer)

Docket Lens (explorer/template.html) is a single page that reads one analysis.json and shows three linked views: who spoke, what they asked for (a themes × submitter-type heatmap that opens the verbatim requests), and what changed (draft vs final by section, with each request's call). Build a docket's copy with:

bash
.venv/bin/python scripts/build_analysis.py FDA-2020-D-2307.venv/bin/python scripts/build_explorer.py FDA-2020-D-2307

Then open explorer/FDA-2020-D-2307/index.html through any static server, e.g. python3 -m http.server --directory explorer/FDA-2020-D-2307. The explorer is licensed separately under PolyForm Noncommercial 1.0.0 (explorer/LICENSE, explorer/NOTICE).

Hosting a Docket Lens demo (Cloudflare Pages, password-protected)

bash
sh scripts/build_site.sh FDA-2020-D-2307cd site && npx wrangler pages deploy public --project-name docket-lens

site/functions/_middleware.js puts HTTP Basic Auth in front of every request, including analysis.json. Credentials are Pages secrets, never files: npx wrangler pages secret put DEMO_USER --project-name docket-lens, and the same for DEMO_PASS. If either secret is missing, the site serves nothing (it fails closed). It is a demo gate, not access control for sensitive data.

Status (3 Oct 2026)

  • First full run: FDA-2020-D-2307 (60 comments, 1,211 requests, 4 checkpoints, human spot-check agreement 91% on 55 calls). Outputs in output/FDA-2020-D-2307/, decisions in decisions/.
  • Second-docket smoke test: FDA-2021-D-0548. Retrieval and the draft/final comparison passed without changes; see docs/smoke-test-FDA-2021-D-0548.md.

The concordance caveat

This tool measures concordance, not impact. Changes between draft and final guidance also come from FDA's internal review, ICH M14, other guidances and the evolving science. When the final text moves in the direction a commenter asked for, that does not show the comment caused the change. Every output from this project carries that caveat.

License

Server: MIT (see LICENSE). The Explorer template is licensed separately under PolyForm Noncommercial 1.0.0.

© 2026 Black Swan Causal Labs · https://blackswancausallabs.com

Official MCP Registry packaging

The Docket Lens retrieval server has an MCP bundle for Registry distribution. See Registry installation and release instructions. The bundle requires uv, your Regulations.gov API key, and a writable working folder.

Source: README.md at commit b10fd0b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestOct 29, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Docket integrations

docket

rocks.docketOfficial publisher

docket's hosted MCP server, published by docket.rocks; credential required; Streamable HTTP.

Streamable HTTPWeb executableAuth
Credential requiredOct 30, 2026

Docket SEO

Published by GitHub account mattkerr09

Runs local SEO audits of a website and lets an assistant read scores, findings, fixes and audit comparisons.

STDIODesktop only
Web Search & ScrapingNot validated yetNov 7, 2026

Docket Room

Published by GitHub account makinglyai

Hosted MCP server giving assistants searchable US legislative records — bills, votes, hearings, legislators and federal regulations — plus change tracking.

Streamable HTTPWeb executableAuth
Productivity & WorkflowCredential requiredNov 2, 2026

Eclipse Docket MCP

Published by GitHub account CYAN-ECLIPSE-TECHNOLOGIES-LLC

Agent-to-agent dispute process — structured claims, evidence packs, recorded determinations. Not a

STDIODesktop only
Not validated yetOct 26, 2026

Docket Alarm

Published by GitHub account pipeworx-io

Pipeworx gateway pack for searching US state, county and federal court dockets via Docket Alarm, with a router that reaches the wider catalog.

Streamable HTTPWeb executable
Web Search & Scraping47 toolsNov 1, 2026