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/specmatic/specmatic-mcp-server/agents-mdgit clone --depth 1 https://github.com/specmatic/specmatic-mcp-serverWrote 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/instructions/specmatic/specmatic-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/specmatic/specmatic-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/specmatic/specmatic-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03587 | $0.03587 |
| Opus 5 | $0.01793 | $0.01793 |
| Sonnet 5 | $0.00717 | $0.00717 |
| Haiku 4.5 | $0.00359 | $0.00359 |
Grade A, and why
specmatic-mcp-server 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 5d 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides shared guidance for coding agents working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) server that exposes Specmatic Contract Test capability, allowing coding agents to use it as a reference while implementing OpenAPI specification.
Current State
This is a fully implemented MCP (Model Context Protocol) server built with TypeScript/Node.js that exposes Specmatic contract testing capabilities. The implementation includes:
- MCP Server: Complete implementation with 3 main tools
- npm Package: Standalone package using
specmaticnpm dependency - Secure Docker: Uses
node:latestbase image for reduced vulnerabilities - Contract Testing: Supports both standard and resiliency testing
- Mock Server: Can start mock servers from OpenAPI specs
- Build System: TypeScript compilation with npm scripts
- Automated Testing: MCP Inspector integration for testing npm package functionality
Development Setup
The project is built with TypeScript and uses Node.js. Always use nvm to use the node stable version.
Prerequisites
- Node.js (use
nvm use stable) - Docker (optional - for running the MCP server in container)
- npm package can be run standalone without Docker
Available Commands
# Build the TypeScript code
npm run build
# Start the MCP server locally
npm start
# Development mode with watch
npm run dev
# Testing commands
npm run test:smoke # Run smoke test loop (recommended)
npm run test:mcp # Run MCP Inspector tests for npm package
npm run inspect # Interactive MCP Inspector
# Docker commands (optional)
npm run docker:build # Build Docker image
npm run docker:run # Run in container
npm run start:host-network # Run with host networking for localhost API testing
# Setup host for development
npm run setup # Runs setup-host.sh script
Dependencies
@modelcontextprotocol/sdk: MCP protocol implementationspecmatic: Contract testing framework (npm package)zod: Input validation and parsing- TypeScript for type safety
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.
- 5d ago First seen · 428 lines · 3,587 tokens per session scan A c4fb8756bda1
specmatic-mcp-server AGENTS.md is an instructions file published in the GitHub repository specmatic/specmatic-mcp-server (12 stars, last pushed 2mo ago), licensed MIT. It adds 3,587 tokens to every session, about $0.0179 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
apifable AGENTS.md
AGENTS.md instructions for ycs77/apifable, covering agents.md, keep this file strict, constraints, commands and rules.
liquidus-005 CLAUDE.md
Claude Code instructions for aygp-dr/liquidus-005, covering liquidus — agent instructions, your role, confirmation gate, failure handler and instrumentation requirement.
apifable CLAUDE.md
Claude Code instructions for ycs77/apifable, a project described as: MCP server that helps AI agents explore OpenAPI specs, search endpoints, and generate TypeScript types.
scalar AGENTS.md
AGENTS.md instructions for scalar/scalar, covering agents.md - ai agent guide for scalar, project overview, prerequisites, first-time setup and commands.
fli CLAUDE.md
Instructions for punitarani/fli, covering claude.md, project overview, development commands, core development tasks and install dependencies.
api-gateway CLAUDE.md
Claude Code instructions for membrane/api-gateway, covering claude.md, git & commit policy, working principles, 1. think before coding and 2. simplicity first.