{
  "markdown": "# mcp-rubygems\n\nRubyGems MCP — wraps the RubyGems.org public API (free, no auth)\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_gem` | Get full metadata for a published Ruby gem by name. Returns latest version, authors, license, descriptions, download counts, and project/source URLs. Use for \"what is gem X?\", \"tell me about Ruby gem Y\", or before calling get_versions/get_dependencies. |\n| `search_gems` | Search RubyGems by keyword in name/description. Returns matching gems sorted by relevance with name, version, downloads, and info text. |\n| `get_versions` | Get full version history for a Ruby gem. Returns every published version with release date, download count, Ruby version compatibility, and licenses. Use for \"what versions of X exist?\" or \"when did Y release version Z?\". |\n| `get_dependencies` | Get the runtime and development dependencies for a specific version of a Ruby gem. Returns each dependency with its version requirement string. Omit version to get the latest. |\n| `get_reverse_dependencies` | List gems that depend on this gem. Useful for understanding ecosystem impact (\"what depends on Rack?\") or risk surface (\"how many gems would break if this one had a vulnerability?\"). API caps at 50 names per request. |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"rubygems\": {\n      \"url\": \"https://gateway.pipeworx.io/rubygems/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/rubygems/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Rubygems data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 3397,
  "sha": "a490ce35f5f7e9d616004aa9a908077a2b909d5bb9a46f05915d9f1d07bb64d3",
  "repo_slug": "pipeworx-io/mcp-rubygems",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_rubygems_14e22a4e/readme"
}