Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gleanwork/mcp-server-testernpx agentmods add skills/gleanwork/mcp-server-tester/write-mcp-testWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gleanwork/mcp-server-tester/write-mcp-test)<a href="https://agentmods.dev/skills/gleanwork/mcp-server-tester/write-mcp-test"><img src="https://agentmods.dev/badge/skills/gleanwork/mcp-server-tester/write-mcp-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gleanwork/mcp-server-tester/write-mcp-test"><img src="https://agentmods.dev/badge/skills/gleanwork/mcp-server-tester/write-mcp-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 164 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 322 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.03458 |
| Opus 5.5 | $0.00040 | $0.01383 |
| Sonnet 5.5 | $0.00020 | $0.00692 |
| Haiku 4.5 | $0.00010 | $0.00346 |
Grade A, and why
write-mcp-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write MCP server tests
A test checks a server directly: it calls a tool with fixed arguments through MST's mcp fixture and asserts on the response with MST's matchers. Tests are fast and deterministic, so run each once, in CI.
A test has no client and no model, so it can't tell you whether a model would pick the tool. That is an eval: use the write-mcp-eval skill.
Before you start
- Check that the project has
@gleanwork/mcp-server-testerand@playwright/test(npm install --save-dev @gleanwork/mcp-server-tester@beta @playwright/test). - Find the tools to test and their input schemas: the server source, or
await mcp.listTools()in a test. - Check
playwright.config.tsfor anmcpConfig(Step 1).
npx mst generate connects to a server, lets you call tools interactively, and writes the calls as a spec (default tests/generated.spec.ts) you can edit. npx @gleanwork/mcp-server-tester@beta init scaffolds a new project.
Step 1: Configure the server
Each Playwright project's use.mcpConfig says how to reach the server:
// playwright.config.ts
import { defineConfig } from '@playwright/test';
export default defineConfig({
testDir: './tests',
reporter: [['list'], ['@gleanwork/mcp-server-tester/reporters/mcpReporter']],
projects: [
{
name: 'local',
use: {
mcpConfig: {
transport: 'stdio',
command: 'node',
args: ['./dist/server.js'],
env: { LOG_LEVEL: 'warn' },
},
},
},
{
name: 'staging',
use: {
mcpConfig: {
transport: 'http',
serverUrl: 'https://staging.example.com/mcp',
auth: { accessToken: process.env.MCP_ACCESS_TOKEN },
},
},
},
],
});
HTTP servers take serverUrl (not url) and optional headers. For auth:
| Need | auth setting |
|---|---|
| A token you already have | { accessToken: process.env.MCP_ACCESS_TOKEN } |
| CI, service account, no browser | { clientCredentials: { tokenEndpoint: 'https://auth.example.com/oauth/token' } } (reads MCP_CLIENT_ID and MCP_CLIENT_SECRET) |
| A user logs in once | Run npx mst login <server-url>; the mcp fixture uses the stored login and refreshes it |
| A browser OAuth flow in global setup | { oauth: { serverUrl, scopes, authStatePath } } (see docs/authentication.md) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed · +18 lines · +47 tokens per session 51bee5fb6a8a
- 23d ago Changed 84c12e0c2322
- 27d ago Changed dc15e2a9d51d
- 2mo ago First seen · 323 lines · 52 tokens per session scan A bc16beb83175
write-mcp-test is a skill published in the GitHub repository gleanwork/mcp-server-tester (19 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 3,458 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.