mcpField
G
Gitlab Public

Gitlab Public

Remote
pipeworx.ioVersion Control1Updated 2d ago

About Gitlab Public

Gitlab Public is an MCP server for searching public GitLab projects and issues through REST API v4 endpoints that require no authentication. It also retrieves detailed project information for developers researching public repositories.

Key features

  1. 01Search public projects by keyword
  2. 02Retrieve project details and activity
  3. 03Search issues across public projects

Use cases

  1. 01Discover public GitLab projects by topic
  2. 02Review a project's stars, forks, and activity
  3. 03Find issues matching a keyword

MCP support

Exposes public GitLab project and issue search tools to MCP clients. It can run as a local stdio server or through the Pipeworx gateway.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/gitlab-public/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

44
ParameterTypeRequiredDescription
qstringNoAlias for question.
askstringNoAlias for question.
textstringNoAlias for question.
inputstringNoAlias for question.
packsarrayNoOPTIONAL. Restrict routing to these pack slugs (e.g. ["sec-form-d","sec-13f"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_packs / search_packs / https://pipeworx.io/directory; unlisted or unknown slugs are ignored and named in _meta.pack_scope.ignored, and if none of them resolves the question is routed across the whole catalog with _meta.pack_scope.full_catalog:true (never an empty answer).
querystringNoAlias for question.
promptstringNoAlias for question.
messagestringNoAlias for question.
questionstringYesYour question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.

Details

From the project README

mcp-gitlab-public

GitLab Public MCP — wraps the GitLab REST API v4 (public endpoints, no auth)

Part of Pipeworx — an MCP gateway connecting AI agents to 1879+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
search_projectsSearch public GitLab projects by keyword, sorted by popularity. Returns project ID, name, description, star count, fork count, open issues, and web URL.
get_projectGet full details for a public GitLab project by numeric ID or "namespace/project" path (e.g., "gitlab-org/gitlab"). Pass the path as written, with a plain slash — do not URL-encode it, the tool handles that internally. Returns name, description, stars, forks, default branch, topics, and last activity date.
search_issuesSearch issues across public GitLab projects by keyword. Returns issue title, state, author, labels, project ID, and direct URL.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "gitlab-public": {
      "url": "https://gateway.pipeworx.io/gitlab-public/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/gitlab-public/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1879+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/gitlab_public_search_projects \
  -H 'Content-Type: application/json' \
  -d '{"query":"machine learning"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/gitlab_public_search_projects. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "gitlab-public": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-gitlab-public"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-gitlab-public

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Gitlab Public data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.