Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Track Regulations.gov dockets, documents and public comments; open comment periods, FAR cases.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"docketwatch": {
"command": "npx",
"args": [
"-y",
"@reneturcios/docketwatch",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add docketwatch -- npx -y @reneturcios/docketwatch mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"docketwatch": {
"command": "npx",
"args": [
"-y",
"@reneturcios/docketwatch",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"docketwatch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/docketwatch",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 3 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Follow the federal rulemaking record without living in a browser tab. docketwatch talks to the Regulations.gov API v4 — the public record of dockets, documents and public comments behind rules published by US agencies — and answers with the API's own JSON, so a search result here is the same payload you would get from the API directly.
You will need a free api.data.gov key:
export REGULATIONS_GOV_API_KEY="<your key>"
Get one at https://api.data.gov/signup. The key goes out as the X-Api-Key header on every data call. If the variable is unset the server still starts and lists its tools, but every data tool replies with setup instructions and makes no request at all — handy for checking that a client is wired up before a key exists. get_access_status is the exception: it never calls out and reports only {"configured": true} or {"configured": false}, never the key itself. The base URL defaults to https://api.regulations.gov/v4 and can be overridden with REGULATIONS_GOV_API_BASE.
The nine tools:
search_documents — find documents (proposed rules, rules, notices, supporting material) by keyword, agency, docket and posted/modified date windows.get_document_detail — one document in full; pass include_attachments: true to ask the API to include its attachments.search_comments — search the public comments by keyword, agency, docket, or the document commented on.get_comment_detail — one comment's full text and submitter information.search_dockets — search rulemaking and nonrulemaking dockets by keyword or agency.get_docket_detail — one docket's metadata, abstract and RIN.open_comment_periods — composition (labelled): not a single API call. It pages through documents posted in the last 180 days (the scan window is a local choice), keeps those whose comment period ends today or later, and returns them soonest-closing first alongside complete and truncated flags.far_case_history — composition (labelled): fetches a FAR/DFARS case docket (for example FAR-2023-0008) together with every page of that docket's documents, concatenated, plus a complete flag saying whether all pages were read.get_access_status — the key check described above.Search arguments are flat names that map onto the API's documented filter[...] parameters, with sort, page[number] and page[size] for ordering and paging. Filter values are case-sensitive — the API treats EPA and epa differently — and docketwatch passes them through unchanged.
One honest gap: the API documentation used for this build does not pin a document-type or docket-type filter parameter name, so no type filter argument is exposed. Keyword, agency, docket and date filters cover the documented surface.
Each tool is a subcommand taking one JSON argument string (get_access_status takes none):
npx @reneturcios/docketwatch search_documents '{"agency_id":"EPA","search_term":"emissions"}'
npx @reneturcios/docketwatch get_document_detail '{"document_id":"EPA-HQ-OAR-2020-0001-0001","include_attachments":true}' npx @reneturcios/docketwatch search_comments '{"docket_id":"EPA-HQ-OAR-2020-0001"}' npx @reneturcios/docketwatch open_comment_periods '{"agency_id":"EPA","limit":20}' npx @reneturcios/docketwatch far_case_history '{"case_number":"FAR-2023-0008"}' npx @reneturcios/docketwatch get_access_status npx @reneturcios/docketwatch --version
Output is the tool's result text (JSON for every tool). Exit codes: 0 on success, 1 on a runtime error (including a validation, missing-key or upstream failure), 2 on a usage error.
npx -y @reneturcios/docketwatch mcp
MCP client config:
{
"mcpServers": { "docketwatch": { "command": "npx", "args": ["-y", "@reneturcios/docketwatch", "mcp"], "env": { "REGULATIONS_GOV_API_KEY": " " } } } }
docker run -i -e REGULATIONS_GOV_API_KEY="<your key>" ghcr.io/cloudcorprecords/docketwatch
docker run --rm -e REGULATIONS_GOV_API_KEY=" " ghcr.io/cloudcorprecords/docketwatch get_access_status
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (fake fetch + fake clock, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios