Huldoser/test-inventory-mcp

An MCP server for test-inventory: AI agents ask which tests a project
has, which are skipped and why, and which tests a change can affect, without running them.
It reads Playwright and Vitest test files with test-inventory and answers from their source code. Nothing runs,
nothing is written, and nothing leaves your machine.
## Setup
Node.js 22.12 or newer. The client starts the server with npx and talks to it over standard input and output. Give
it the framework, and the server scans the test files your playwright.config or vitest.config runs. Globs after
it pick the files instead, as on test-inventory's command line.
Claude Code, in the project folder. --scope project writes .mcp.json, for everyone who works on the project:
sh
claude mcp add --scope project test-inventory -- npx -y test-inventory-mcp@0.5 --framework playwright
Cursor, in .cursor/mcp.json:
json
"mcpServers": {
"test-inventory": {
"command": "npx",
"args": ["-y", "test-inventory-mcp@0.5", "--framework", "playwright"]
VS Code, in .vscode/mcp.json:
json
"servers": {
"test-inventory": {
"type": "stdio",
"command": "npx",
"args": ["-y", "test-inventory-mcp@0.5", "--framework", "playwright"]
Without --framework, as in a configuration shared by every project, the agent passes framework in each call, and
patterns when it wants other files than the configs run; the tools say so when the framework is missing.
The project is the folder given with --root, otherwise the one Claude Code names in CLAUDEPROJECTDIR, otherwise
the folder the client starts the server in.
## Command line
text
test-inventory-mcp [--framework [ ]] [--root ]
| Option | Meaning |
| --framework | playwright or vitest. A tool call can pass the other. |
| | The test files, relative to the project, in place of those the configs run. A tool call can pass others. |
| --root | The project. Tool calls can scan folders inside it, never outside. |
| --help, --version | Print the help or the version. |
## Tools
| Tool | Answers |
| testsummary | Counts by state, tag and annotation, and the configs with their projects; with groupBy, the counts of each file, tag or project. |
| findtests | The tests that match states, tags, grep, related, projects, only or withoutReason, with the fields you pick. |
| gettests | Every key of up to 20 tests by id, with the scan's diagnostics about them. |
| scandiagnostics | The problems the scan found, such as a file that failed to parse, by level, code or path. |
related takes the files a change touches, from the project root as git diff --name-only writes them, and keeps
the tests whose dependencies include one of them, and those that reach code the scan can't follow, as
test-inventory's --related does.
dependencies can list hundreds of files, so it isn't among the default fields, and gettests returns as many
tests as fit in one answer, with the other ids in remaining.
Every tool also takes directory, a folder inside the project to scan, and framework and patterns to override