agentmods.dev

cursorrules

A set of project rules for a tool that lets coding agents work with GitLab, a service for hosting code and tracking software projects. It supports finding projects and issues, browsing repositories, and learning the server's available data structure.

In plain words
What is it for?
Use it when configuring or operating a GitLab connection for agents such as Claude Code or LibreChat, including repository browsing, project and issue searches, and paginated results.
Why use it?
It gives agents consistent guidance for authentication, pagination, transports, and read or write access. This reduces errors when handling large GitLab results or connecting different clients.

Cursor rule for Cursor

10 1mo ago A scan 572 tokens original MIT
View the source file ttpears/gitlab-mcp
Install

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.

agentmods
npx agentmods add rules/ttpears/gitlab-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/ttpears/gitlab-mcp

Made for: Cursor.

Per session 572 This file is loaded in full into every session.
When invoked 572 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00572 $0.00572
Opus 5 $0.00286 $0.00286
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured yesterday against content hash f5ce35f9d635, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 39 lines

What it actually says

Project rules and notes for gitlab-mcp

  • Authentication model

    • Hybrid by default: shared read-only token for read tools; user PAT required for write tools.
    • Env: GITLAB_SHARED_ACCESS_TOKEN, GITLAB_AUTH_MODE=hybrid, optional GITLAB_URL.
    • Tools accept optional userCredentials with accessToken and optional gitlabUrl.

  • Transports

    • Server provides stdio (default) and Streamable HTTP transport at / (and /mcp for container compatibility).
    • LibreChat (HTTP) should use type: streamable-http and url: http://HOST:PORT/.
    • Hosted environments may provide PORT; server also respects GITLAB_MCP_PORT and MCP_TRANSPORT=http.

  • Pagination

    • All list/search tools support cursor-based pagination (first, after) and auto-pagination (fetchAll).
    • fetchAll loops server-side via fetchAllPages() up to maxItems (default 100), returning { nodes, totalFetched, hasMore, pageInfo }.
    • Default page size: 20. Max per request: config.maxPageSize (default 50, env GITLAB_MAX_PAGE_SIZE).
    • Sort defaults to UPDATED_DESC for recency bias on issues, MRs, and projects.
    • search_gitlab paginates projects and issues independently when fetchAll=true.

  • GraphQL / Validation

    • Avoid unsupported fields (e.g., Project.defaultBranch) across self-hosted instances; rely on introspection.
    • Search term inputs are trimmed and empty strings are rejected for tools that require them.
    • Issue/MR state: all maps to undefined; others map to GQL enums via UPPERCASE.

  • New discovery tools

    • resolve_path: Distinguishes group vs project and lists group projects.
    • get_group_projects: Lists projects within a group, supports search and pagination.
    • get_type_fields: Lists fields for a given GraphQL type using introspection.
    • update_issue: Schema-aware updates for issues; falls back to granular mutations when needed.
    • update_merge_request: Schema-aware MR updates; supports assignees, reviewers, labels, title/description.

  • Error handling

    • Read tools fall back to shared token; write tools throw if no user token is provided.
    • Null guards ensure clearer errors when a group path is provided to project-only tools.

  • Maintenance

    • Keep this file updated when adding tools, transports, or auth changes.
    • Reviewers apply to merge requests, not issues (per GitLab GraphQL docs).
Changes

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.

  1. yesterday First seen · 39 lines · 572 tokens per session scan A f5ce35f9d635

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository ttpears/gitlab-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 572 tokens to every session, about $0.0029 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.

Backend and APIsData and AILLMResearchclaudegitlabgraphqlmcpmodel-context-protocol
Related

Other cursor rules, from other repositories

swift-development

Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.

madebyaris/rakitui-ai · 0 tokens

cursorrules

When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.

CSOAI-ORG/social-media-ai-mcp · 80 tokens

cursorrules

This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.

tysoncung/notion-agent-hub · 437 tokens

lighter-safety

Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.

iamgoatedaf/lighter-mcp · 18 tokens

nix-security

Nix Security and Sandboxing.

ghuntley/groundhog · 489 tokens

memory-bank

You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…

alexeyleshchenko/fast-mcp-telegram · 1,623 tokens