Skip to main content
Glama
norandom

RAGFlow Claude MCP Server

by norandom

ragflow_retrieval

Retrieve relevant document chunks from RAGFlow datasets using semantic search with similarity scoring and optional query refinement.

Instructions

Retrieve document chunks directly from RAGFlow datasets using the retrieval API. Returns raw chunks with similarity scores.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataset_idsYesList of IDs of the datasets/knowledge bases to search
queryYesSearch query or question
document_nameNoOptional document name to filter results to specific document
top_kNoNumber of chunks for vector cosine computation. Defaults to 1024.
similarity_thresholdNoMinimum similarity score for chunks (0.0 to 1.0). Defaults to 0.2.
pageNoPage number for pagination. Defaults to 1.
page_sizeNoNumber of chunks per page. Defaults to 10.
use_rerankNoWhether to enable reranking for better result quality. Default: false (uses vector similarity only).
deepening_levelNoLevel of DSPy query refinement (0-3). 0=none, 1=basic refinement, 2=gap analysis, 3=full optimization. Default: 0

Latest Blog Posts

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/norandom/ragflow-claude-desktop-local-mcp'

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