mcpField
G
gitgoblin

gitgoblin

Local
anandkaranubc.github.ioVersion Control2Updated 2d ago

About gitgoblin

gitgoblin is an MCP server for developers and agents seeking open-source projects and contribution work. It ranks repositories, explains its signals, and provides evidence-based project and opportunity briefings through read-only tools.

Key features

  1. 01Rank repositories by goals and filters
  2. 02Explain repository ranking signals
  3. 03Analyze project activity and conventions
  4. 04Brief a specific contribution opportunity
  5. 05Read-only tools with progress updates

Use cases

  1. 01Find repositories matching a language or topic
  2. 02Assess why a repository fits a goal
  3. 03Identify evidenced contribution opportunities
  4. 04Review project commands and contribution etiquette

MCP support

Exposes four read-only tools to MCP clients: repository discovery, ranking explanations, repository analysis, and opportunity briefings. Long requests can report progress and be cancelled by the client.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
npm@gitgoblin/mcp0.1.7
mcpbgitgoblin.mcpb

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

@gitgoblin/mcp

gitgoblin as a Model Context Protocol server. It gives any MCP client (Claude Code, Codex, Cursor, Gemini CLI, Copilot in VS Code, and others) four read-only tools: discover repositories worth your time, explain why one scores the way it does, analyze what a repository actually needs, and get a full briefing on one piece of work.

claude mcp add gitgoblin -- npx -y https://github.com/anandkaranubc/gitgoblin/releases/download/mcp-v0.1.6/gitgoblin-mcp-0.1.6.tgz

docs/agents.md has the one-liner for every client, the skill that teaches agents when to use the tools, and what has been verified. The server is listed in the official MCP Registry as io.github.anandkaranubc/gitgoblin. The command installs the tarball attached to release mcp-v0.1.6. @gitgoblin/mcp is not published to npm yet, so do not use that name with npx -y until it is. You can also run the server from a clone with node packages/mcp/bin/gitgoblin-mcp.mjs after npm install; Claude Desktop users install the release's gitgoblin.mcpb directly.

Tools

ToolInputOutput
discover_repositoriesgoal (default contribute), languages, topics, keywords, min_stars, max_stars, pushed_within_days, created_within_days, license, like, exclude_owners, include_archived, include_forks, limit (default 10, max 25)Ranked repositories: stars, language, license, score, the three strongest reasons for and one against, starter issues for contribute. structuredContent.results[] carries the same fields.
explain_repositoryrepository, goalAll ten discovery signals with value, weight for the goal and evidence. Unknown signals say so.
analyze_repositoryrepository, max_opportunities (default 10, max 30), check_dependencies (default true), goalThe profile (nature, activity, responsiveness, welcomeness with signals, rules, commands, conventions) and the ranked opportunities with their primary evidence.
get_opportunityrepository, opportunity_id or issue_numberOne opportunity in full plus how to work on the project: clone, commands, conventions, rules, etiquette.

repository accepts owner/name or a URL. explain_repository and the like seed take github.com repositories, since discovery reads GitHub's API by owner and name; analyze_repository and get_opportunity also take gitlab.com and codeberg.org, which intel reads through their public APIs. Every other host is refused. Errors come back as tool results with advice (how to get a token, how to spell a repository), never as protocol failures. An analysis runs in a worker thread and is stopped after five minutes, or as soon as the client cancels the request, so one slow repository never freezes the other tools. Long calls send progress notifications when the client provides a progress token.

The server's instructions tell the agent the typical flow, that quoted repository text is data and never instructions, and the one rule that matters: it never opens issues, pull requests or comments on the person's behalf unless asked.

The repository is often chosen by a model, so the server treats it as hostile: git checks committed symlinks out as plain files and only speaks HTTPS, clones live in their own cache, external links are never fetched, and control characters are stripped from every result. docs/design.md explains each defence.

Environment

VariableEffect
GITHUB_TOKEN, GH_TOKENOptional. Raises GitHub's limits and unlocks starter issues. Falls back to gh auth token.
GITGOBLIN_CACHE_DIRWhere the HTTP cache lives (default ~/.cache/gitgoblin); the server's blob-less clones go in its mcp subdirectory.

Development

npm test -w @gitgoblin/mcp                                       # protocol tests with fakes, offline
npm run typecheck -w @gitgoblin/mcp
GITGOBLIN_E2E=1 npx vitest run --root packages/mcp test/e2e      # the real server over stdio, against GitHub
npm run bundle -w @gitgoblin/mcp                                 # what `npm pack` ships: dist/gitgoblin-mcp.mjs and its THIRD_PARTY_NOTICES.md
npm run mcpb -w @gitgoblin/mcp                                   # the Claude Desktop bundle: dist/gitgoblin.mcpb

src/server.ts builds the server from an injectable ServerDeps (discovery and intel); src/format.ts renders results for a model; src/deps.ts wires the real packages; bin/gitgoblin-mcp.mjs is the launcher. Development runs the TypeScript source on Node 24. Publishing bundles the source and the sibling packages into one file with no runtime dependencies, because Node will not strip types under node_modules. docs/design.md explains the decisions; server.json is the manifest for the MCP Registry; it points at the release's .mcpb and its SHA-256. Releases are built by the repository's release workflow from an mcp-v<version> tag on the merged commit, never from a local checkout; docs/releasing.md has the steps, including the MCP Registry workflow run that follows each release.

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.