MCP RAG Serverは、Model Context Protocol (MCP)に準拠したRAG（Retrieval-Augmented Generation）機能を持つPythonサーバーです。マークダウン、テキスト、パワーポイント、PDFなど複数の形式のドキュメントをデータソースとして、
Connect MCP Rag Server to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP RAG Serverは、Model Context Protocol (MCP)に準拠したRAG（Retrieval-Augmented Generation）機能を持つPythonサーバーです。マークダウン、テキスト、パワーポイント、PDFなど複数の形式のドキュメントをデータソースとして、multilingual-e5. The mcp rag server mcp server is what makes that connection.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
command — uv（推奨）またはpythonargs — 実行引数の配列query — 検索クエリ（必須）limit — 返す結果の数（デフォルト: 5）with_context — 前後のチャンクも取得するかどうか（デフォルト: true）context_size — 前後に取得するチャンク数（デフォルト: 1）full_document — ドキュメント全体を取得するかどうか（デフォルト: false）mcp-rag — serverのコードベースsearch — The search tool exposed by this serverget_document_count — The get_document_count tool exposed by this serverConfiguration is passed through the environment: POSTGRES_HOST. 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.
Installation goes through your MCP client rather than a global install: point it at pgvector/pgvector on a container image and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Rag Server's toolset — command, args, query and 7 more — is a fair guide to whether it matches your workflow. It is maintained by karaage0703; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against MCP Rag Server's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| command | uv（推奨）またはpython |
| args | 実行引数の配列 |
| query | 検索クエリ（必須） |
| limit | 返す結果の数（デフォルト: 5） |
| with_context | 前後のチャンクも取得するかどうか（デフォルト: true） |
| context_size | 前後に取得するチャンク数（デフォルト: 1） |
| full_document | ドキュメント全体を取得するかどうか（デフォルト: false） |
| mcp-rag | serverのコードベース |
| search | The search tool exposed by this server. |
| get_document_count | The get_document_count tool exposed by this server. |
{
"mcpServers": {
"mcp-rag-server": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/mcp-rag-server",
"python",
"-m",
"src.main"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| POSTGRES_HOST | Endpoint or connection string the server talks to. | Optional |
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.
Thousands of open models on tap — run image, video and audio generation through Replicate's hosted API.