cbruyndoncx

ThirdBrain Skills MCP — Development skill for Claude Code

Development community

Serve Agent Skills (SKILL.md libraries) over MCP: SEP-2640 skills extension, multi-library namespaces, discovery tools, digest-verified pull client.

How to install ThirdBrain Skills MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open cbruyndoncx/ThirdBrain-skills-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What ThirdBrain Skills MCP does

Serve Agent Skills (SKILL.md libraries) over MCP: SEP-2640 skills extension, multi-library namespaces, discovery tools, digest-verified pull client.

Alternatives in Development

Notebook Intelligence — A JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills 331 ★
Ext Skills — Experimental exploration of skills discovery and distribution through MCP primitives 214 ★
Rebuild — Build the TabzChrome extension and MCP server (and sync to Windows/plugin cache) 146 ★

README

ThirdBrain skills-mcp

Library-agnostic MCP server that serves one or many directories of **Agent Skills** (`SKILL.md` folders, flat or nested) over the Model Context Protocol, each library under its own namespace. Part of the ThirdBrain Business Operating Brain (BOB) tooling. Built for the ThirdBrain BOB library (~400 skills) and verified against the GBL library (~400 skills). Includes a `pull` client that syncs skills from any SEP-2640 server to disk with digest verification.

It implements the **MCP Skills extension ([SEP-2640](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2640))** for hosts that understand `skill://` resources, and a small set of **discovery tools** for hosts that do not yet, so skills are loaded on demand instead of being copied into every agent's skills folder.

What it exposes

Surface	Purpose
`capabilities.extensions["io.modelcontextprotocol/skills"]`	Declares the extension (`directoryRead: true`).
`skills/list` (paginated) / `skills/get`	Skill entries: `uri`, verbatim `frontmatter`, `resources[]` with `sha256` digests and sizes.
`resources/list`	One `text/markdown` resource per skill (`skill:///SKILL.md`), extra frontmatter under `_meta` with the `io.modelcontextprotocol.skills/` prefix.
`resources/templates/list`	`skill://{+skillPath}/SKILL.md` and `skill://{+skillPath}/{+path}`.
`resources/read`	Any bundled file (text, or base64 blob for binaries).
`resources/directory/read`	Children of a skill directory (`inode/directory`).
`notifications/resources/list_changed`	Sent after a rescan detects changes.
Tools	`_search_skills`, `_list_skills`, `_list_libraries`, `_list_categories`, `_get_skill`, `_read_skill_file`, `_catalog_status`. All declare `outputSchema` and return `structuredContent`; search/list/categories take a `library` filter.
Prompt	`use-skill(skill, task?)` injects a skill's instructions into the conversation.