filesystem-rag-mcp
Related Servers
Alternatives to filesystem-rag-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceEnables fast local hybrid search over a folder of markdown files via MCP, combining BM25 and vector similarity with explicit relevance verdicts and no LLM or network calls at query time.1-
- AlicenseBqualityAmaintenanceEnables local hybrid search over Obsidian and Markdown vaults via MCP, combining vector retrieval, full-text search, reranking, graph navigation, and safe CRUD while keeping data local.431MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP-compatible hosts to search, ask, and retrieve section-level citations from scattered local notes, docs, PDFs, Word files, web pages, org files, and chat logs using hybrid vector and BM25 retrieval.-
- FlicenseNot gradedqualityBmaintenanceEnables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.4-
- AlicenseAqualityCmaintenanceMCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.94,591 npmMIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to search and query a local hybrid vector/BM25 index of scattered notes, docs, PDFs, Office files, web pages, org files, and chat exports. It returns section-level citations so agents can ground answers in the user's own files.-
TDQS
Scored across 23 tools
Most tools have clearly distinct purposes (search=hybrid semantic, grep_search=regex, search_symbols=declarations, find_symbol_references=usages, deep_search=multi-hop). There is mild overlap in the read family (read_file, read_file_markdown, download_file_raw, read_files_batch) and between refresh_index/refresh_file, but descriptions differentiate scope and format well.
Predominantly consistent snake_case with a verb_noun pattern (get_chunk, read_file, add_workspace, list_workspaces, refresh_index). A few deviations break the pattern: 'ping' is a bare verb, and git_search/grep_search use noun_verb ordering, but overall the convention is predictable.
23 tools sits in the heavy band for a single server. The domain is genuinely broad (search, indexing, git, multi-format reads, workspaces, graph analysis), so most tools earn their place, but several closely related read/search variants push it toward over-scoped.
Coverage of the RAG/filesystem lifecycle is strong: indexing, refresh (full and incremental), hybrid/regex/symbol search, chunk navigation, multi-format reads, git inspection, and workspace management are all present. The notable gap is write operations—only patch_file exists, with no create/delete file, limiting mutation workflows.