semantic-search-mcp
Related Servers
Alternatives to semantic-search-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceEnables local semantic code search across repositories using natural language, with AST-aware chunking and hybrid vector/FTS5 retrieval.-
- AlicenseNot gradedqualityDmaintenanceProvides local semantic search over files using embeddings, enabling directory indexing and natural language queries without external services.51 PyPIMIT
- AlicenseAqualityFmaintenanceProvides intelligent semantic code search using local AI embeddings, enabling natural language queries to find relevant code by meaning rather than exact keywords. Indexes codebases in the background with smart project detection and privacy-first local processing.635 npm199MIT
- AlicenseAqualityBmaintenanceEnables semantic and keyword search over a local codebase by chunking source files along function and class boundaries, embedding them offline, and fusing vector and BM25 results. Runs entirely on your machine in a single SQLite file, so AI coding agents can find relevant code with no API keys, telemetry, or cloud calls.7368 npmMIT

dfine-semanticofficial
AlicenseAqualityBmaintenanceEnables natural-language semantic search of a project's code through a local vector index, so questions that plain grep cannot match return ranked file:line references. It also indexes or refreshes projects on demand, reports index status, and optionally flags near-identical code across files.418 npmMIT- FlicenseNot gradedqualityDmaintenanceProvides semantic code search capabilities that run 100% locally using EmbeddingGemma embeddings. Enables finding code by meaning across 15 file extensions and 9+ programming languages without API costs or sending code to the cloud.238-
TDQS
Scored across 11 tools
initialize and reindex both appear to trigger full index builds, making their boundaries unclear and causing potential misselection. Other tools like search_code, pause_watcher, and exclude_paths are well-distinguished, but the core indexing pair introduces significant ambiguity.
Most tools follow a consistent verb_noun pattern (e.g., search_code, reindex_file, pause_watcher, get_status). However, initialize and reindex are standalone verbs that break the pattern, creating a minor but noticeable deviation.
11 tools is well within the ideal range for a domain-specific server. Each tool contributes to searching, indexing, or management, and there is no obvious redundancy or bloat.
The server covers the core search and indexing lifecycle, including search, full/partial indexing, and clearing. However, it lacks a way to remove a single file from the index, and exclude_paths does not retroactively affect already-indexed content, leaving notable gaps for handling file deletions.