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/yoda-digital/mcp-gitlab-server/claude-mdgit clone --depth 1 https://github.com/yoda-digital/mcp-gitlab-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/yoda-digital/mcp-gitlab-server/claude-md)<a href="https://agentmods.dev/instructions/yoda-digital/mcp-gitlab-server/claude-md"><img src="https://agentmods.dev/badge/instructions/yoda-digital/mcp-gitlab-server/claude-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 | $0.00993 | $0.00993 |
| Opus 5 | $0.00496 | $0.00496 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
mcp-gitlab-server CLAUDE.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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
GitLab MCP Server - A Model Context Protocol server enabling AI assistants to interact with GitLab resources. Exposes 30+ tools for repository management, file operations, issues, merge requests, wikis, and member management.
Package: @yoda.digital/gitlab-mcp-server
Build & Development Commands
npm run build # Compile TypeScript to dist/
npm start # Run compiled server
npm run dev # Development with ts-node hot reload
Note: npm test runs vitest (vitest run). Unit specs live alongside source: src/formatters.test.ts, src/schemas.test.ts, src/gitlab-api.test.ts, src/transport.test.ts, src/utils.test.ts. Plus an E2E suite under e2e/ that runs against a real GitLab CE container (81 tests, 86 tools, see CONTRIBUTING.md § "Running the E2E suite locally"). The coverage gate in scripts/check-tool-coverage.sh (wired into build.yml) fails the build if a new tool ships without an E2E test. No dedicated linter is configured; TypeScript strict mode handles type checking.
Security: Vulnerabilities go through GitHub Private Vulnerability Reporting — never via public issues. Threat model and scope are in SECURITY.md.
Architecture
src/
├── index.ts # MCP server setup, tool registration, and request handlers (main switch statement)
├── gitlab-api.ts # GitLabApi class - all GitLab REST API interactions
├── schemas.ts # Zod schemas for input validation and response types
├── formatters.ts # Response formatting functions for MCP-compatible output
├── transport.ts # Stdio and SSE transport setup
└── utils.ts # Utility functions (ISO date validation)
Request Flow
- Tool receives request → Zod schema validates input
GitLabApimethod makes authenticated HTTP call with Bearer token- Response validated with Zod schema
- Formatter creates MCP response with text content blocks
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 · 87 lines · 993 tokens per session scan A acdd1f256d5f
mcp-gitlab-server CLAUDE.md is an instructions file published in the GitHub repository yoda-digital/mcp-gitlab-server (64 stars, last pushed 22d ago), licensed MIT. It adds 993 tokens to every session, about $0.0050 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
gitlab-mcp-server copilot-instructions.md
Copilot instructions for jmrplens/gitlab-mcp-server, covering gitlab-mcp-server — gitlab mcp server in go, project overview, architecture, project structure and development conventions.
gitlab-mcp-server go-mcp-server.instructions.md
Best practices and patterns for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk package (v1.7.0+).
gitlab-mcp-server go.instructions.md
Instructions for writing Go code following idiomatic Go practices and community standards.
gitlab-mcp-server code-review-generic.instructions.md
Generic code review instructions that can be customized for any project using GitHub Copilot.
gitlab-mcp-server AGENTS.md
AGENTS.md instructions for jmrplens/gitlab-mcp-server, covering gitlab-mcp-server — agent quick reference, read first, hard invariants, common commands and build.
gitlab-mcp-server mcp-best-practices.instructions.md
MCP protocol-level best practices for tool design, annotations, response formats, pagination, and security. Applies to all Go MCP server code.