Testing

Write, place and run tests for a server in this repo. Use when choosing between driving the server through an MCP client and calling its functions directly; when writing a protocol-level test for a TypeScript or Python server; when choosing the command that runs one suite or a coverage report; or when a test is skipped or passes against a stale build.

92,088 stars 11,978 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add modelcontextprotocol/servers --skill testing
Manual install
git clone --depth 1 https://github.com/modelcontextprotocol/servers.git /tmp/servers
mkdir -p ~/.claude/skills
cp -r /tmp/servers/.claude/skills/testing ~/.claude/skills/testing

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Testing

The **rules** are in [`AGENTS.md`](../../../AGENTS.md) under **Always test new
or modified code**: new behavior comes with tests, every TypeScript file clears
the per-file coverage gate, test at the protocol level where you can, and keep
expected error output off the console. This skill explains the harness each
server has, how to write a test with it, which command runs what, and how to
clear the per-file coverage gate.

Driving a running server by hand, with the Inspector or an LLM client, is
`/client-smoke`. It is evidence for a PR, not a substitute for a test.

**Every server is tested in-process, and every file is gated.** The four
TypeScript servers link a real `Client` to the server over an in-memory
transport (#4854); the three Python servers link a `ClientSession` to the real
`serve()` over in-memory streams (#4855). Both languages hold each file to a
per-file coverage floor, in CI and in `npm run local:gate`.

## Where a test goes

| Server | Directory | File name | Runner |
| --- | --- | --- | --- |
| `everything`, `filesystem`, `memory`, `sequentialthinking` | `src/<server>/__tests__/` | `<subject>.test.ts` | vitest, `globals: true` |
| `fetch`, `git`, `time` | `src/<server>/tests/` | `test_<subject>.py` | pytest, with `pytest-asyncio` (`asyncio_mode = "auto"`) |
| Root tooling | `scripts/`, beside the script | `<name>.test.mjs` | `node --test` |

Each vitest config includes only `**/__tests__/**/*.test.ts`, so a test file
Read the full skill on GitHub

Details

Skill name
testing
Path
.claude/skills/testing/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Testing skill do?

Write, place and run tests for a server in this repo. Use when choosing between driving the server through an MCP client and calling its functions directly; when writing a protocol-level test for a TypeScript or Python server; when choosing the command that runs one suite or a coverage report; or when a test is skipped or passes against a stale build.

How do I install the Testing skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add modelcontextprotocol/servers --skill testing. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Testing popular?

It lives in modelcontextprotocol/servers, which has 92,088 GitHub stars and 11,978 forks, and is included in 1 curated skill list.

Related skills

Board Ops

92k

modelcontextprotocol/servers

gh recipes for the Servers V2 project board (#43): add an issue's card, move its Status, set or change its Priority, delete a card, and recover from a deleted single-select option. Use when moving a card between columns; when setting Status or Priority; when an option ID is rejected; before editing a board field's options; or when cards lost their Status or Priority.

OtherIn 1 list12k

Client Smoke

92k

modelcontextprotocol/servers

Drive a locally built server with a real client: the Inspector CLI (scripted), the Inspector web UI (through Playwright) and an LLM client. Use when smoke-testing a server change; when calling a tool, reading a resource or getting a prompt from the command line; when choosing a protocol era; or when the Inspector CLI will not connect to, or misreads, a server command.

Testing & QAIn 1 list12k

Issue Create

92k

modelcontextprotocol/servers

Create a tracked issue in this repo end to end — duplicate check, v2 label, type label, server-scope label, milestone, board card, Status and Priority. Use when asked to file, create, open or raise an issue; when picking its labels or its milestone; when checking whether one already exists; or when work discovered mid-task needs an issue of its own.

Skill & Plugin AuthoringIn 1 list12k

Character Animation QA

82k

OpenMontageInc/OpenMontage

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

Testing & QA11k

Pre Push Gate

92k

modelcontextprotocol/servers

Run this repo's pre-push gate and fix it when it goes red. Use when npm run local:gate fails or a stage of it does (verify:install-fresh, a root guard, lint, typecheck, ruff, pyright, pytest, verify:skills:cli, the boot smoke); when the gate says it is waiting on the gate lease; or when checking whether a gate run really passed.

Testing & QAIn 1 list12k

Playwright Recording

82k

OpenMontageInc/OpenMontage

Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.

Testing & QA11k

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.