Skip to main content
Glama

Local RAG

server.json2.93 kB
{ "$schema": "https://static.modelcontextprotocol.io/schemas/2025-10-17/server.schema.json", "name": "io.github.shinpr/mcp-local-rag", "description": "Easy-to-setup local RAG server with minimal configuration", "vendor": "Shinsuke Kagawa", "license": "MIT", "repository": { "url": "https://github.com/shinpr/mcp-local-rag", "source": "github" }, "version": "0.1.5", "packages": [ { "registryType": "npm", "registryBaseUrl": "https://registry.npmjs.org", "identifier": "mcp-local-rag", "version": "0.1.5", "transport": { "type": "stdio" }, "environmentVariables": [ { "name": "BASE_DIR", "description": "Base directory for document storage (defaults to current working directory)", "isRequired": false, "format": "string", "isSecret": false }, { "name": "DB_PATH", "description": "Path to LanceDB database directory (defaults to ./lancedb/)", "isRequired": false, "format": "string", "isSecret": false }, { "name": "CACHE_DIR", "description": "Directory where Transformers.js models are cached (defaults to ./models/)", "isRequired": false, "format": "string", "isSecret": false }, { "name": "MODEL_NAME", "description": "Embedding model name (defaults to Xenova/all-MiniLM-L6-v2)", "isRequired": false, "format": "string", "isSecret": false }, { "name": "MAX_FILE_SIZE", "description": "Maximum file size in bytes (defaults to 104857600 / 100MB)", "isRequired": false, "format": "string", "isSecret": false }, { "name": "CHUNK_SIZE", "description": "Text chunk size for splitting documents (defaults to 512)", "isRequired": false, "format": "string", "isSecret": false }, { "name": "CHUNK_OVERLAP", "description": "Overlap between consecutive chunks (defaults to 100)", "isRequired": false, "format": "string", "isSecret": false } ], "features": { "tools": { "supported": true, "list": [ "query_documents", "ingest_file", "list_files", "status" ] }, "prompts": { "supported": false }, "resources": { "supported": false } } } ], "tags": [ "rag", "vector-search", "lancedb", "transformers", "local-ai", "privacy", "document-search", "semantic-search" ], "homepage": "https://github.com/shinpr/mcp-local-rag", "documentation": "https://github.com/shinpr/mcp-local-rag#readme" }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/shinpr/mcp-local-rag'

If you have feedback or need assistance with the MCP directory API, please join our Discord server