Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Map who must approve a PR: CODEOWNERS rules plus who actually reviews these files.
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": {
"approvepath": {
"command": "npx",
"args": [
"-y",
"@reneturcios/approvepath",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add approvepath -- npx -y @reneturcios/approvepath mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"approvepath": {
"command": "npx",
"args": [
"-y",
"@reneturcios/approvepath",
"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": {
"approvepath": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/approvepath",
"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, debuff
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.
Let coding agents play, test and tune your 2D web game: live state, explained errors, replays, fuzz.
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.
A CODEOWNERS file says who is *supposed* to approve a change. Review history says who *actually* shows up. approvepath puts the two side by side for one pull request: you hand it the CODEOWNERS rules, the files the PR touches, and whatever past review activity you have, and it hands back, per file, the owners the rules assign and the people who have reviewed that exact file before.
Pattern matching follows a pinned subset of CODEOWNERS semantics, so the answer never depends on which CODEOWNERS dialect you had in mind. Any leading / is stripped from both the pattern and the file path before comparing. A pattern ending in / is a directory prefix: it matches every file under that directory. A pattern containing * is a glob that must match the whole path — ** matches any run of characters including /, while a single * matches any run except /. Any other pattern matches a file that equals it exactly, or a file underneath it (the pattern plus / as a prefix), so a bare directory name owns its whole subtree.
When several rules match the same file, the last matching rule in file order wins — the same override rule CODEOWNERS itself uses, and the reason a broad early rule can hand a subtree to a team while a later, narrower rule hands one corner of it back. A file no rule matches is unowned: its owners list is empty and its pattern is null, and it also appears in unowned_files, in input order.
Review history is counted plainly. For each changed file, frequent_reviewers counts, per reviewer, how many supplied review entries by that reviewer list the file exactly — no prefix credit, no directory credit. Reviewers are ranked by count descending, then by name ascending, and only the top three are reported. required_reviewers collects every owner from every winning rule across the PR, deduplicated and sorted, which is the shortest honest answer to "whose approval does this PR actually need?".
Everything is computed locally from the arguments alone: no repository is read, no hosting API is called, and nothing is guessed. Malformed input — a rule with an empty pattern, a changed file that is not a non-empty string, a review entry missing its reviewer — is a validation error naming the offending path, with no partial result.
npx @reneturcios/approvepath map --input args.json
npx @reneturcios/approvepath --version
args.json contains the full arguments object:
{
"codeowners": [ { "pattern": "src/", "owners": ["@core"] }, { "pattern": "src/api/", "owners": ["@api-team", "sam"] } ], "changed_files": ["src/api/handler.ts", "README.md"], "reviews": [ { "reviewer": "sam", "files": ["src/api/handler.ts"] }, { "reviewer": "lee", "files": ["src/api/handler.ts"] } ] }
reviews is optional and defaults to []. The result is printed as JSON:
{
"files": [ { "file": "src/api/handler.ts", "owners": ["@api-team", "sam"], "pattern": "src/api/", "frequent_reviewers": [ { "reviewer": "lee", "reviews": 1 }, { "reviewer": "sam", "reviews": 1 } ] }, { "file": "README.md", "owners": [], "pattern": null, "frequent_reviewers": [] } ], "unowned_files": ["README.md"], "required_reviewers": ["@api-team", "sam"] }
Exit codes: 0 on success, 1 on a runtime error (including an unreadable or invalid input file, or invalid input), 2 on a usage error.
npx -y @reneturcios/approvepath mcp
MCP client config:
{
"mcpServers": { "approvepath": { "command": "npx", "args": ["-y", "@reneturcios/approvepath", "mcp"] } } }
map_approvals — Map the approval path for a pull request.codeowners (array, required, may be empty) — CODEOWNERS rules in file order; each entry is {pattern, owners}, where pattern is a non-empty string and owners is an array of non-empty strings (may be empty)changed_files (array of strings, required, non-empty) — paths of the files the PR changesreviews (array, optional, default []) — past review activity; each entry is {reviewer, files}, where reviewer is a non-empty string and files is an array of strings (may be empty)Returns {files, unowned_files, required_reviewers}, where files holds one {file, owners, pattern, frequent_reviewers} entry per changed file, in input order.
docker run -i ghcr.io/cloudcorprecords/approvepath
docker run --rm -v "$PWD:/w" ghcr.io/cloudcorprecords/approvepath map --input /w/args.json
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (pure local, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios