Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/gleanwork/mcp-server-tester/agents-mdgit clone --depth 1 https://github.com/gleanwork/mcp-server-testerWhat 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 | $0.03456 | $0.03456 |
| Opus 5 | $0.01728 | $0.01728 |
| Sonnet 5 | $0.00691 | $0.00691 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade A, and why
mcp-server-tester AGENTS.md 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 3d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
Project Overview
@gleanwork/mcp-server-tester is a Playwright-based testing and evaluation framework for Model Context Protocol (MCP) servers. It provides Playwright fixtures for automated testing and data-driven eval datasets with optional LLM-as-a-judge scoring.
Common Commands
# Build (includes UI reporter build)
npm run build
# Unit tests (Vitest)
npm test # Run all unit tests
npm run test:watch # Watch mode
npm test -- src/mcp/clientFactory.test.ts # Run single test file
npm test -- -t "creates client" # Run tests matching pattern
# Integration tests (Playwright)
npm run test:playwright
# Code quality
npm run typecheck # TypeScript validation
npm run lint # ESLint
npm run lint:fix # Auto-fix lint issues
npm run format # Prettier formatting
npm run format:check # Check formatting
Architecture
Core Modules (src/)
config/-MCPConfigtypes and Zod validation for stdio/HTTP transportsmcp/- Client factory (createMCPClientForConfig), fixtures (MCPFixtureApi), and response normalizationauth/- OAuth 2.1 with PKCE (PlaywrightOAuthClientProvider) and static token utilitiesassertions/- Unified assertion architecture (see below)evals/- Dataset types, loader, and runner (uses validators internally)judge/- LLM-as-a-judge via Claude Agent SDKspec/- MCP protocol conformance checksreporters/- Custom Playwright reporter with React-based UIcli/-mcp-server-tester initandmcp-server-tester generatecommands
Assertions Module (src/assertions/)
The assertion architecture provides a single API for both inline tests and data-driven evals:
validators/- Pure validation functions:validateText,validateSchema,validatePattern,validateError,validateSize,validateResponse,validateToolCalls,validateToolCallCountmatchers/- Playwright custom matchers (see table below)
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.
- 3d ago First seen · 319 lines · 3,456 tokens per session scan A e1db80eca8ec
mcp-server-tester AGENTS.md is an instructions file published in the GitHub repository gleanwork/mcp-server-tester (19 stars, last pushed 15d ago), licensed MIT. It adds 3,456 tokens to every session, about $0.0173 per session on Opus 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 instructions, from other repositories
omnigent copilot-instructions.md
Copilot instructions for omnigent-ai/omnigent, covering copilot code review instructions, e2e test requirement, backend test coverage and frontend test coverage.
Math-To-Manim tests.instructions.md
Guidelines for writing and maintaining tests in Math-To-Manim.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).
web-widgets AGENTS.md
AGENTS.md instructions for mendix/web-widgets, covering mendix web widgets, conventions, e2e test rules (playwright), development setup and constraints.