# GitLab MCP MCP Server > **GitLab MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to GitLab MCP. > > MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows, > token refresh, and production-grade auto-scaling — so your AI agents can connect to > third-party services and run freely without you managing any MCP server yourself. > > Server page: https://mewcp.com/mcp/gitlab-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About GitLab connects AI agents to software development workflows, enabling them to manage projects, issues, merge requests, pipelines, repositories, and code reviews. Search code, inspect CI/CD jobs, review security findings, and automate development tasks across GitLab projects. --- ## Details - Server ID: `gitlab-mcp` - Version: 1.0.0 - Tools: 36 - Authentication: OAuth, managed by MewCP - Transport: http --- ## Access The gateway URL below serves your **entire MewCP toolset**, not this server on its own. Pasting a config snippet is not enough — GitLab MCP has to be in the toolset first. In order: 1. Add GitLab MCP to your toolset at https://mewcp.com/mcp/gitlab-mcp 2. Connect your GitLab MCP account (OAuth); MewCP stores the credential and attaches it to each call 3. Copy your MewCP API key from the dashboard (Developer) 4. Configure your client with the snippet for it below Once connected, an agent does **not** see this server's tools as top-level tools. It sees four meta-tools and reaches everything through them: - `search(query)` — find tools by keyword across the toolset - `get_schema(tools)` — full description and arguments for the tools you picked - `list_accounts(provider)` — only when one app has several connected accounts - `call_tool(server_maskedId, tool_name, args)` — execute So the list below is what `search` can return for this server, not a set of callable tool names on their own. --- ## Tools (36) Descriptions are truncated to 160 characters; call `get_schema` for the full text and the argument schema. Where a tool is annotated, its type is shown — treat `destructive` as irreversible. - `get_artifact_file` _(read)_ — Read a file from inside the artifacts archive of a CI/CD job as text. To discover what a job or pipeline produced, use get_job or get_pipeline with include:… - `get_job` _(read)_ — Get a CI/CD job in a GitLab project. Add include: log to also get the job's trace/log, which you can page through with byte_offset and byte_limit. Add include:… - `get_mcp_server_version` _(read)_ — Get the current version of MCP server. - `list_releases` _(read)_ — List releases in a GitLab project, most recently released first. Identify the project with exactly one of url or project_id. Returns release metadata and asset… - `list_tags` _(read)_ — List tags in a GitLab project, most recently updated first. Identify the project with exactly one of url or project_id. When search is given, a tag whose name… - `accept_merge_request` _(destructive)_ — Merge a merge request, or schedule it to merge automatically. Without strategy the merge starts immediately and completes asynchronously; with strategy,… - `add_branch` _(write)_ — Add a branch to a GitLab project from a source ref. Examples: - Use branch and ref to create a new branch from an existing branch or commit SHA - `add_commit` _(destructive)_ — Add a commit with one or more file actions to a project branch. - `get_commit` _(read)_ — Get a single commit's metadata, optionally including its diff or notes. Identify the commit with either url, or project_id and commit_sha. - `get_merge_request` _(read)_ — Get a merge request and optionally its diffs, commits, notes, pipelines, discussions, approvals, or conflicts. By default only the base merge request metadata… - `get_repository_file` _(read)_ — Read a file from a GitLab repository at a given ref. Reads from GitLab, not the local filesystem: use it for a project you have not checked out, or a specific… - `get_pipeline` _(read)_ — Get a CI/CD pipeline in a GitLab project, and optionally its jobs, downstream pipelines, bridge (trigger) jobs, or the artifacts its jobs produced. A bridge… - `get_project` _(read)_ — Get metadata for a single GitLab project: numeric ID, full path, default branch, visibility, and web URL. Identify the project with exactly one of url or… - `get_saved_view_work_items` _(read)_ — Fetch a saved view and its work items list from a namespace - `get_user` _(read)_ — Get a single GitLab user. Use me: true to look up the authenticated user, for example to find your own user id before setting assignee_ids or reviewer_ids.… - `get_work_item` _(read)_ — Get a single work item (issue, epic, task, incident, objective, key result) with its type, dates, assignees, labels, milestone, and parent. Optionally include… - `get_work_item_types` _(read)_ — List the work item types available in a namespace (group or project), including system-defined types (Issue, Epic, Task, etc.) and custom types. Each returned… - `link_work_items` _(write)_ — Link a work item to other work items with a relationship type (relates_to, blocks, blocked_by) - `list_commits` _(read)_ — List commits in a GitLab project, filtered by ref, author, path, or date. Identify the project with exactly one of url or project_id. Returns compact commit… - `list_groups` _(read)_ — List GitLab groups. Without group_id, lists top-level groups where you are a member. With group_id, lists the direct subgroups of that group, regardless of… - `list_merge_requests` _(read)_ — List or search merge requests in a GitLab project or group by author, assignee, reviewer, state, milestone, labels, or text. Identify the project or group with… - `list_projects` _(read)_ — List GitLab projects. Without group_id, defaults to projects you have at least guest access to; pass min_access_level to raise the threshold. With group_id,… - `list_repository_tree` _(read)_ — List files and directories in a GitLab repository at a given path and ref. Identify the project with exactly one of url or project_id. Returns entry metadata… - `list_project_members` _(read)_ — List the members of a GitLab project with their role and access level. Direct members only, unless include_inherited is true. - `list_work_items` _(read)_ — List or search work items (ISSUE, INCIDENT, TEST_CASE, REQUIREMENT, TASK, TICKET, OBJECTIVE, KEY_RESULT, EPIC) in a group or project. Filter by state, author,… - `save_merge_request_review` _(write)_ — Write merge request review artifacts as the authenticated user. Exactly one method per call: create_note adds a top-level comment; reply_discussion replies… - `save_note` _(write)_ — Add a comment to a GitLab merge request or work item, or reply to an existing discussion thread. Identify the target with url, or with merge_request_iid or… - `save_pipeline` _(destructive)_ — Run, retry, cancel, or rename a CI/CD pipeline in a GitLab project. Omit pipeline_id and pass ref to run a new pipeline, and identify the project with exactly… - `save_work_item` _(write)_ — Create or update a GitLab work item, such as an issue, task, or epic. Omit work_item_iid to create a new work item; provide work_item_iid or a work item URL to… - `search_labels` _(read)_ — Search labels in a GitLab project or group by multiple terms - `fork_repository` _(write)_ — Create a fork of a project - `list_pipelines` _(read)_ — List all project pipelines - `list_branches` _(read)_ — List all repository branches - `semantic_search` _(read)_ — Semantic (meaning-based) search over different types of content. Searches indexed project content using embedding-based similarity rather than keyword… - `search` _(read)_ — Search across GitLab with automatic selection of the best available search method. **Capabilities:** basic (keywords, file filters), advanced (boolean… - `save_merge_request` _(write)_ — Create or update a merge request in a GitLab project. merge_request_iid alone decides the operation. Omitting it always creates a new merge request; provide it… --- ## Connect Gateway URL: https://gateway.mewcp.com/personal/mcp Every request carries one header: Authorization: Bearer Replace `API_KEY` with your own key from the dashboard (Developer). ## Apps ### Claude Desktop Mac & Windows app - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "mewcp": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://gateway.mewcp.com/personal/mcp", "--header", "Authorization:${AUTH_HEADER}" ], "env": { "AUTH_HEADER": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open Claude Desktop → Settings → Developer → "Edit Config" 2. Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one) 3. Save the file, then quit Claude Desktop completely and reopen it 4. Start a new conversation — your tool will be available ### VS Code Copilot / Cline - Command Palette → "MCP: Open User Configuration" (opens mcp.json). For one project only, use .vscode/mcp.json instead. ```json { "mcp.servers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have a "servers" section in your mcp.json? Just add the server entry inside it. 1. Open VS Code → Command Palette (Cmd+Shift+P / Ctrl+Shift+P) 2. Run "MCP: Open User Configuration" to open your mcp.json 3. Paste the snippet and save 4. Start the server when prompted (or from the MCP servers view) and use it in Copilot Chat ### Cursor AI-first editor - macOS: `~/.cursor/mcp.json` - Windows: `%USERPROFILE%\.cursor\mcp.json` ```json { "mcpServers": { "mewcp": { "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your mcp.json? Just add the server entry inside it. 1. Open Cursor → Settings → Cursor Settings → MCP 2. Click "Add new global MCP server" 3. Paste the snippet and save 4. Restart Cursor ### Codex OpenAI's CLI agent - Add the snippet to your Codex MCP config or your standard MCP config file for the CLI tool you use. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Codex generally reads a standard MCP server block, so you can add this alongside your other configured servers. 1. Open your Codex MCP config or project-level config file 2. Paste the MewCP server block inside the config JSON/TOML structure your tool expects 3. Save the file and restart Codex 4. Verify the tool is available inside a fresh session ### Claude Code Anthropic's CLI agent - ~/.claude.json (user scope) or .mcp.json in your project root — create it if it doesn't exist. Or skip the file and use the CLI command below. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open ~/.claude.json (or .mcp.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file and start (or restart) Claude Code 4. Or skip the file entirely and run the CLI command below instead ### OpenCode Open-source terminal agent - ~/.config/opencode/opencode.json (global) or opencode.json in your project root — create it if it doesn't exist. ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "mewcp": { "type": "remote", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcp" section in your opencode.json? Just add the server entry inside it. 1. Open ~/.config/opencode/opencode.json (or opencode.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and start (or restart) OpenCode ### OpenClaw Self-hosted agent gateway - ~/.openclaw/openclaw.json — create it if it doesn't exist. ```json { "mcp": { "servers": { "mewcp": { "transport": "streamable-http", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } } ``` Already have an "mcp" section in your openclaw.json? Just add the server entry inside "servers". 1. Open ~/.openclaw/openclaw.json in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and restart OpenClaw ### Antigravity Google's agentic IDE - ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace-local) — create it if it doesn't exist. ```json { "mcpServers": { "mewcp": { "serverUrl": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. Remote servers must use the "serverUrl" field — the legacy "url"/"httpUrl" fields aren't supported. 1. In the editor's agent side panel, click "…" → "MCP Servers" → "Manage MCP Servers" → "View raw config" (Antigravity CLI: type /mcp instead to open the Interactive MCP Manager) 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file — the server connects automatically ### Hermes Nous Research's CLI agent - config.yaml in your Hermes config directory (~/.hermes) — add this under a top-level "mcp_servers:" key. ```yaml mcp_servers: mewcp: url: "https://gateway.mewcp.com/personal/mcp" headers: Authorization: "Bearer API_KEY" ``` Already have an "mcp_servers" section in your config.yaml? Just add the server entry inside it. 1. Open config.yaml in your Hermes config directory 2. Paste the snippet under the top-level "mcp_servers:" key (merge with existing entries if you have any) 3. Save the file, then run /reload-mcp in Hermes (or start a fresh session) 4. Ask Hermes "Tell me which MCP-backed tools are available right now" to confirm it connected ### DeepSeek Harness DeepSeek's agent harness - cordis.yml in your DSH project — or the patch file you mount plugins from. ```yaml - id: mcp-mewcp name: '@deepseek-ai/dsh-mcp-client' config: serverName: mewcp transport: streamable-http url: https://gateway.mewcp.com/personal/mcp headers: Authorization: "Bearer API_KEY" ``` One plugin instance = one MCP server. Add this entry to your plugin list; don't nest it inside another entry. 1. Open cordis.yml (or your patch file) in your DSH project 2. Paste the entry into your plugin list, keeping the leading dash and indentation 3. Restart DSH (or let HMR reload) — tools register as mcp__mewcp__ 4. Verify with: dsh web --dump-config | grep -A3 mcp ## SDKs ### Python fastmcp client ```python import asyncio from fastmcp import Client from fastmcp.client.transports import StreamableHttpTransport SERVER_URL = "https://gateway.mewcp.com/personal/mcp" API_KEY = "API_KEY" transport = StreamableHttpTransport( url=SERVER_URL, headers={ "Authorization": f"Bearer {API_KEY}", } ) async def main(): client = Client(transport) async with client: tools = await client.list_tools() print(tools) asyncio.run(main()) ``` 1. Install fastmcp: pip install fastmcp 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run your script ### TypeScript MCP SDK ```typescript import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const SERVER_URL = "https://gateway.mewcp.com/personal/mcp"; const API_KEY = "API_KEY"; const transport = new StreamableHTTPClientTransport(new URL(SERVER_URL), { requestInit: { headers: { Authorization: `Bearer ${API_KEY}`, }, }, }); const client = new Client({ name: "mewcp-client", version: "1.0.0" }); await client.connect(transport); const tools = await client.listTools(); console.log(tools.tools.map((t) => t.name)); ``` 1. Install: npm install @modelcontextprotocol/sdk 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run with Node 18+ as an ES module (e.g. npx tsx script.ts)