Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Find the tests relevant to a source file from an import map, ranked, with the run command.
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": {
"testfinder": {
"command": "npx",
"args": [
"-y",
"@reneturcios/testfinder",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add testfinder -- npx -y @reneturcios/testfinder mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"testfinder": {
"command": "npx",
"args": [
"-y",
"@reneturcios/testfinder",
"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": {
"testfinder": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/testfinder",
"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 4 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, Safe Fetch
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.
MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.
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.
Running the whole test suite after every small edit is a slow loop. testfinder narrows it: give it one source file plus the project's file/import map — every file's path and the paths it imports — and it works out which tests are actually relevant to that file, why each one is relevant, and the exact command that runs just those tests:
.test or .spec inserted before the final extension, either beside the source (src/foo.ts → src/foo.test.ts) or in the __tests__ form (src/__tests__/foo.test.ts). A source whose name has no extension gets the suffix appended instead (src/foo → src/foo.test).Every relevant test carries exactly one reason, decided by precedence: self (the source file is itself a test) over direct over convention over transitive. Results are ranked by that reason order, then by distance, then by path, and run_command is the npx tsx --test line that runs them in ranked order — or null when nothing is relevant. The result also reports total_files and test_files_considered, the count of test files in the set whether relevant or not. A file counts as a test when its name carries .test. / .spec. (or ends in .test / .spec), or when it lives under a test, tests, or __tests__ directory.
Imports that name paths outside the supplied set are external: they are ignored, never followed, and never an error. Duplicate import entries are de-duplicated and a file importing itself is ignored for graph purposes, though distances still flow through ordinary non-test files on the way to a test. Malformed input — a missing or unknown source_file, an empty file set, a duplicate file path, a wrongly typed field — is a validation error naming the offending path (for example files[1].imports[0] must be a string), and no partial result is produced. The computation is pure and local, and the tool only finds tests: running them, with the command it returns, is left to your own environment.
npx @reneturcios/testfinder find --input args.json
npx @reneturcios/testfinder --version
args.json contains the full arguments object:
{
"source_file": "src/foo.ts", "files": [ { "path": "src/foo.ts" }, { "path": "src/bar.ts", "imports": ["src/foo.ts"] }, { "path": "src/foo.test.ts" }, { "path": "src/bar.test.ts", "imports": ["src/bar.ts", "react"] } ] }
imports defaults to [] per file; here react is external to the set and ignored. src/foo.test.ts is a naming-convention match with no import of its own, and src/bar.test.ts reaches the source through src/bar.ts at distance 2. The result is printed as JSON:
{
"source_file": "src/foo.ts", "relevant_tests": [ { "path": "src/foo.test.ts", "reason": "convention", "distance": null }, { "path": "src/bar.test.ts", "reason": "transitive", "distance": 2 } ], "total_files": 4, "test_files_considered": 2, "run_command": "npx tsx --test src/foo.test.ts src/bar.test.ts" }
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/testfinder mcp
MCP client config:
{
"mcpServers": { "testfinder": { "command": "npx", "args": ["-y", "@reneturcios/testfinder", "mcp"] } } }
find_relevant_tests — Find the tests relevant to one source file from a file/import map.source_file (string, required) — path of the source file; must be one of the supplied filesfiles (array, required, at least one) — files as {path, imports?} objects; path is unique across the set, and each imports entry either names another supplied file or anything else (external, ignored)Returns {source_file, relevant_tests, total_files, test_files_considered, run_command}, where each entry of relevant_tests is {path, reason, distance}.
docker run -i ghcr.io/cloudcorprecords/testfinder
docker run --rm -v "$PWD:/w" ghcr.io/cloudcorprecords/testfinder find --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