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/agentspan-ai/mcp-testkit/agents-mdgit clone --depth 1 https://github.com/agentspan-ai/mcp-testkitWhat 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 | $0.01441 | $0.01441 |
| Opus 5 | $0.00720 | $0.00720 |
| Sonnet 5 | $0.00288 | $0.00288 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
mcp-testkit 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 2d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Contributing Guide
Instructions for AI agents contributing to this project.
Project Overview
This is an MCP test server with 65 deterministic tools across 8 groups, exposed via MCP (stdio/HTTP) and REST API. Every tool returns identical output for identical input — no randomness, no datetime.now(), no external state.
Architecture
mcp_test_server/
server.py → Entry point. Creates FastMCP instance, registers tools, starts transport.
api.py → REST API. Data-driven endpoint registry generates Starlette routes + OpenAPI spec.
tools/*.py → Tool modules. Each exports register(mcp) that decorates tools with @mcp.tool().
tests/*.py → Unit + integration tests using unittest + FastMCP's call_tool().
Key pattern: Tools are registered as closures inside register(mcp) via @mcp.tool() decorators. Helper functions live at module level.
How to Add a New Tool
1. Choose the right module
| Group | File | When to use |
|---|---|---|
| math | mcp_test_server/tools/math_tools.py |
Numeric computation |
| string | mcp_test_server/tools/string_tools.py |
String manipulation |
| collection | mcp_test_server/tools/collection_tools.py |
Array/dict operations |
| encoding | mcp_test_server/tools/encoding_tools.py |
Encode/decode/hash |
| datetime | mcp_test_server/tools/datetime_tools.py |
Date computations (no current time!) |
| validation | mcp_test_server/tools/validation_tools.py |
Input checking (returns {valid, reason}) |
| conversion | mcp_test_server/tools/conversion_tools.py |
Unit/format conversions |
| echo | mcp_test_server/tools/echo_tools.py |
Protocol testing, fixtures, misc |
If a tool doesn't fit any group, add it to mcp_test_server/tools/echo_tools.py (the catch-all for test fixtures).
2. Implement the tool
Add it inside the register(mcp) function in the chosen module:
@mcp.tool()
def my_new_tool(param: str, count: int) -> str:
"""Clear one-line description of what the tool does."""
result = param * count
return json.dumps({"result": result})
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.
- 2d ago First seen · 159 lines · 1,441 tokens per session scan A b8eae44f8351
mcp-testkit AGENTS.md is an instructions file published in the GitHub repository agentspan-ai/mcp-testkit (1 stars, last pushed 16d ago), licensed MIT. It adds 1,441 tokens to every session, about $0.0072 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.