gknowledge — Claude Code MCP server: a cited wiki from your documents
Gives your agent a wiki of linked Markdown pages: feed it documents, the model keeps pages current and answers with citations.
claude mcp add gknowledge -- uvx gknowledge-mcpWhat gknowledge does
The server exposes a knowledge base shaped like a wiki. Dropped-in documents become linked Markdown pages with YAML frontmatter, and a plain SQLite index sits alongside. You can open the folder in Obsidian or any editor; the files stay on disk.
Lookups combine lexical search with graph expansion across page links, and each answer points back to the pages it used. A generated page keeps track of where its material came from. Whatever the model changes lands in a review queue first, so edits do not stick on their own.
It starts as uvx gknowledge-mcp, so uv has to be on the machine. With no model attached, a built-in heuristic engine handles ingestion and answers offline; adding a model is worth it when you want tighter synthesis.
What it helps with
- turn a folder of documents into a wiki that stays current
- answer questions from your own notes with page citations
- review model edits before they reach the knowledge base
- read accumulated knowledge in Obsidian with no export step
- search the base when an outside API is unavailable
Example prompts for the agent
- Ingest the files in
papersinto the wiki and list which pages changed - Find everything about incremental indexing and answer with citations
- Show the review queue and the pages the model touched last
How to install gknowledge
Platform CLI
claude mcp add gknowledge -- uvx gknowledge-mcpuvx runs the command named after the package; if the README names another one, use uvx --from gknowledge-mcp <command>
Platform CLI
codex mcp add gknowledge -- uvx gknowledge-mcpuvx runs the command named after the package; if the README names another one, use uvx --from gknowledge-mcp <command>
Config file
{
"mcpServers": {
"gknowledge": {
"command": "uvx",
"args": [
"gknowledge-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from gknowledge-mcp <command>
Config file
{
"servers": {
"gknowledge": {
"type": "stdio",
"command": "uvx",
"args": [
"gknowledge-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from gknowledge-mcp <command>
Platform CLI
gemini mcp add gknowledge uvx gknowledge-mcpuvx runs the command named after the package; if the README names another one, use uvx --from gknowledge-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about gknowledge
How do I install gknowledge in Claude Code?
Run claude mcp add gknowledge -- uvx gknowledge-mcp. That registers the server, which starts through uvx.
What does gknowledge do?
It maintains a wiki of linked Markdown pages built from your documents and answers questions against it with citations. Model edits wait in a review queue.
Do I need an API key?
No: the built-in heuristic engine ingests and answers offline. Attach a model when you want better synthesis.
