convez.ai
MCP ServerIntegração & APIsAvançado
Knuckles-Team

GitLab API MCP Server

Knuckles-Team/gitlab-api

MCP server production-grade para automação e integração com GitLab

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP de integração com GitLab que oferece API Python, CLI e agente integrado. Fornece acesso consolidado às operações do GitLab com suporte a segurança empresarial, telemetria nativa e protocolo Agent Control Protocol (ACP).

Instalação

$npx convez-ai Knuckles-Team/gitlab-api

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
10
Forks
1
Acompanhando
2
Saúde
37%
Último commit
há 6 dias
Versão
v27.3.23
Issues abertas
1
Contribuidores
4

Casos de uso

  • Automação de workflows e pipelines GitLab via agentes de IA
  • Gerenciamento programático de repositórios, branches e MRs
  • Integração de GitLab com sistemas de orquestração de agentes

Veredito

Ferramenta madura e bem-documentada para integração profissional com GitLab. Ideal para equipes que precisam orquestrar operações GitLab via agentes de IA com suporte a segurança empresarial e telemetria.

README

A tradução para o português deste README ainda está na fila.

Gitlab Api

CLI or API | MCP | Agent

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 25.44.0

Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, the integrated A2A agent server, and guidance for provisioning the backing GitLab instance are maintained in the official documentation.


Overview

Gitlab Api is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with GitLab API + MCP Server + A2A Server.


Key Features

  • Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
  • Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
  • Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
  • Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the GitLab API + MCP Server + A2A Server API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.


MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool ModuleToggle Env VarEnabled by DefaultDescription & Nested Methods
MiscMISC_TOOLTrueManage gitlab api misc operations.
BranchesBRANCHES_TOOLTrueManage gitlab branches operations. Action-routed methods: create, delete, get.
Protected BranchesPROTECTED_BRANCHES_TOOLTrueManage gitlab protected branches operations. Action-routed methods: get, protect, unprotect.
CommitsCOMMITS_TOOLTrueManage gitlab commits operations. Action-routed methods: create, create_comment, diff, get, get_comments, get_discussions, get_gpg_signature, get_merge_requests, get_statuses, post_status, revert.
Deploy TokensDEPLOY_TOKENS_TOOLTrueManage gitlab deploy tokens operations. Action-routed methods: create_group, create_project, delete_group, delete_project, get, get_group, get_project.
EnvironmentsENVIRONMENTS_TOOLTrueManage gitlab environments operations. Action-routed methods: create, delete, delete_stopped, get, get_protected, protect, stop, stop_stale, unprotect, update, update_protected.
GroupsGROUPS_TOOLTrueManage gitlab groups operations. Action-routed methods: edit, get, get_descendants, get_merge_requests, get_projects, get_subgroups.
JobsJOBS_TOOLTrueManage gitlab jobs operations. Action-routed methods: cancel, erase, get_log, get_pipeline_jobs, get_project_jobs, retry, run.
MembersMEMBERS_TOOLTrueManage gitlab members operations. Action-routed methods: get_group, get_project.
Merge RequestsMERGE_REQUESTS_TOOLTrueManage gitlab merge requests operations. Action-routed methods: create, get, get_project.
Merge RulesMERGE_RULES_TOOLTrueManage gitlab merge rules operations. Action-routed methods: approve_mr, create_project_level, delete_project_level, edit_group_level, edit_project_level, get_group_level, get_mr_approval_state, get_mr_approvals, get_mr_level, get_project_level, unapprove_mr, update_project_level.
PackagesPACKAGES_TOOLTrueManage gitlab packages operations. Action-routed methods: download, get, publish.
PipelinesPIPELINES_TOOLTrueManage gitlab pipelines operations. Action-routed methods: get, run.
Pipeline SchedulesPIPELINE_SCHEDULES_TOOLTrueManage gitlab pipeline schedules operations. Action-routed methods: create, create_variable, delete, delete_variable, edit, get, get_all, get_triggered, run, take_ownership.
ProjectsPROJECTS_TOOLTrueManage gitlab projects operations. Action-routed methods: edit, get, get_contributors, get_nested_by_group, get_statistics, share_with_group, unshare_with_group.
ReleasesRELEASES_TOOLTrueManage gitlab releases operations. Action-routed methods: create, create_evidence, delete, download_asset, get, get_by_tag, get_group_releases, get_latest, get_latest_asset, get_latest_evidence, update.
RunnersRUNNERS_TOOLTrueManage gitlab runners operations. Action-routed methods: delete, delete_project, enable_project, get_all, get_group, get_jobs, get_project, pause, register, reset_gitlab_token, reset_group_token, reset_project_token, reset_token, update_details, verify_auth.
TagsTAGS_TOOLTrueManage gitlab tags operations. Action-routed methods: create, delete, get, get_protected, get_protected_tag, protect, unprotect.
LabelsLABELS_TOOLTrueManage GitLab labels. Action-routed methods: create, delete, get, update.
MilestonesMILESTONES_TOOLTrueManage GitLab milestones. Action-routed methods: create, delete, get, update.
SnippetsSNIPPETS_TOOLTrueManage GitLab snippets. Action-routed methods: create, delete, get, update.
NotesNOTES_TOOLTrueManage GitLab notes/comments on issues, merge requests, commits, and epics. Action-routed methods: create, delete, get, update.
EpicsEPICS_TOOLTrueManage GitLab epics. Action-routed methods: create, delete, get, update.
IssuesISSUES_TOOLTrueManage GitLab issues. Action-routed methods: create, delete, get, update.
Custom ApiCUSTOM_API_TOOLTrueExecute arbitrary GitLab REST API requests directly.
GraphqlGRAPHQL_TOOLTrueExecute raw GraphQL queries and mutations natively on GitLab.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

  • CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
  • Environment Variables: Define standard environment variables:
    • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
    • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
  • HTTP SSE Request Headers: Pass custom headers during transport initialization:
    • x-mcp-enabled-tools / x-mcp-disabled-tools
    • x-mcp-enabled-tags / x-mcp-disabled-tags
  • HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
    • ?tools=tool1,tool2
    • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.


MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "gitlab-api": {
      "command": "uvx",
      "args": [
        "--from",
        "gitlab-api",
        "gitlab-mcp"
      ],
      "env": {
        "GITLAB_URL": "your_gitlab_url_here",
        "GITLAB_TOKEN": "your_gitlab_token_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "gitlab-api": {
      "command": "uvx",
      "args": [
        "--from",
        "gitlab-api",
        "gitlab-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "GITLAB_URL": "your_gitlab_url_here",
        "GITLAB_TOKEN": "your_gitlab_token_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "gitlab-api": {
      "url": "http://localhost:8000/gitlab-api/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name gitlab-api-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e GITLAB_URL="your_value" \
  -e GITLAB_TOKEN="your_value" \
  knucklessg1/gitlab-api:latest

Additional Deployment Options

gitlab-api can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

  • Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
  • Remote URL — connect to a server deployed behind Caddy at http://gitlab-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export GITLAB_URL="your_value"
export GITLAB_TOKEN="your_value"

# Run the agent server
gitlab-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  gitlab-api-mcp:
    image: knucklessg1/gitlab-api:latest
    container_name: gitlab-api-mcp
    hostname: gitlab-api-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  gitlab-api-agent:
    image: knucklessg1/gitlab-api:latest
    container_name: gitlab-api-agent
    hostname: gitlab-api-agent
    restart: always
    depends_on:
      - gitlab-api-mcp
    env_file:
      - ../.env
    command: [ "gitlab-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9017
      - MCP_URL=http://gitlab-api-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9017:9017"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9017/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.


Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

  • Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
  • OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
  • Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

FeatureFunctionalityEnablement
Tool GuardSensitivity inspection with human-in-the-loop validationEnabled by default
Prompt Injection DefenseInput scanning, repetition monitoring, and recursive loop blocksEnabled by default
Context Safety GuardStuck-loop detectors and contextual overflow preemptive alertsEnabled by default

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install gitlab-api[all]

# Using standard pip
python -m pip install gitlab-api[all]

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

PageContents
Installationpip, source, extras, prebuilt Docker image
Deploymentrun the MCP and agent servers, Compose, Caddy + Technitium, env config
Usagethe MCP tools, the Api client, the CLI
Backing Platformdeploy GitLab with Docker
Overviewthe action-routed tool surface and architecture
Conceptsconcept registry (CONCEPT:GL-*)

Repository Owners

GitHub followers GitHub User's stars


Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

  • Format code using ruff format .
  • Lint code using ruff check .
  • Validate type-safety with mypy .
  • Execute test suites using pytest
Ver o original no GitHub

Bom para

Relacionados