MCP server for retrieving relevant documentation from a knowledge base
MCP server for retrieving relevant documentation from a knowledge base. That is what the gemini docs mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
This project implements an MCP server that enables access to documentation for various technologies using the Gemini API with its gigantic context window of 2M tokens. It should work for any client, but is targeted especially to the Roo/Cline environment.
The server publishes 2 tools. What each one is for:
Input — ** docs, prompt, x, technologyOutput — ** success, dataInstallation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: GEMINI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Gemini Docs's toolset — Input, Output — is a fair guide to whether it matches your workflow. It is maintained by M-Gonzalo; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Input | ** docs, prompt, x, technology |
| Output | ** success, data |
{
"mcpServers": {
"cosa-sai": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"GEMINI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.