Skip to main content
Glama

kb-mcp-server

by Geeksfino
technical_docs.yml1.83 kB
# Configuration optimized for technical documentation # Examples: API docs, product manuals, technical guides # Main path configuration path: .txtai/kb-techdocs content: true writable: true # Text extraction configuration textractor: paragraphs: true sections: true # Preserve section structure for technical docs minlength: 30 # Technical docs often have shorter meaningful paragraphs cleantext: true backend: "text" # Embedding configuration embeddings: # Model optimized for technical/scientific content path: sentence-transformers/allenai-specter # Better for technical content content: true normalize: true hybrid: true # Important for technical terminology gpu: true # Storage configuration writable: true backend: faiss storagetype: sqlite # Scoring methods - emphasize keyword matching for technical terms scoring: method: bm25 normalize: true terms: cachelimit: 1000000000 cutoff: 0.0005 # Lower cutoff to catch technical terms # Graph configuration graph: backend: "networkx" batchsize: 256 limit: 15 # More connections for technical docs minscore: 0.25 # Lower threshold to capture more technical relationships approximate: true topics: algorithm: "louvain" terms: 6 # More terms for technical topics centrality: "betweenness" # Better for technical concept relationships directed: true weight: "similarity" # Graph search options search: max_hops: 2 use_centrality: true min_score: 0.25 # Search configuration - emphasize keyword matching for technical queries search: limit: 7 minscore: 0.25 rerank: true weights: bm25: 0.7 # Higher weight for keyword matching similarity: 0.3 # Lower weight for semantic similarity

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/Geeksfino/kb-mcp-server'

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