Skip to main content
Glama
roilanrodriguez55

mcp-local-rag

by roilanrodriguez55
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Related Servers

Alternatives to mcp-local-rag

No user-submitted related servers found.

    Related Servers

    • mcp-local-rag

      xiuxiansk
      A
      license
      A
      quality
      C
      maintenance
      MCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.
      9
      8,055 npm
      MIT

    • Local RAG

      shinpr
      A
      license
      A
      quality
      A
      maintenance
      Privacy-first local document search using semantic search. Runs entirely on your machine with no cloud services, supporting PDF, DOCX, TXT, and Markdown files.
      22
      9
      8,055 npm
      403
      MIT

    • local-Rag

      zongzi-zongzhi
      A
      license
      A
      quality
      D
      maintenance
      A local-first document retrieval MCP server that enables AI coding tools like Codex to search private local documents via semantic search and keyword boost, supporting ingestion of PDF, DOCX, TXT, Markdown, and HTML files.
      7
      MIT

    • local-notes-search-mcp

      Furkiozknn
      A
      license
      A
      quality
      B
      maintenance
      Enables natural-language semantic search over your own local files through an MCP server, fully offline without API keys or a server daemon, with optional LLM-grounded answers and exact file:line sources.
      5
      MIT

    • doc-index

      mike-anderson
      A
      license
      Not graded
      quality
      B
      maintenance
      A local-first semantic search server for documents, supporting PDFs, Office files, and text/markdown, enabling natural language search via the Model Context Protocol (MCP).
      1
      MIT

    • docs-mcp

      kislevlevy
      F
      license
      Not graded
      quality
      B
      maintenance
      Local documentation search server for AI models using hybrid retrieval (phrase, keyword, vector). Provides MCP tools to search and fetch documentation from bundled or custom doc sets without any external API keys.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.2/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool has a distinct purpose: ingest_file vs ingest_data are cleanly split by path vs in-memory string, delete_file consolidates deletion for both, query_documents is search, read_chunk_neighbors is follow-up context, and sync_start/sync_status form a clear job/poll pair. list_files and status both give overviews but their descriptions clearly separate file scanning from index metrics.

    Naming Consistency4/5

    Most tools follow a consistent verb_noun pattern (query_documents, ingest_file, ingest_data, delete_file, list_files, read_chunk_neighbors, sync_start, sync_status). The lone 'status' noun breaks the pattern, and sync_ prefix is a minor variant, but overall it reads predictably.

    Tool Count5/5

    Nine tools is well-scoped for a local RAG server, with each tool earning its place across search, ingest, delete, listing, status, context retrieval, and sync operations. No redundancy or bloat.

    Completeness4/5

    The surface covers the RAG lifecycle well: create/update via ingest and re-ingest, read via query and chunk neighbors, delete, list, status, and disk reconciliation via sync. Minor gaps exist (no explicit whole-index reset or single-document metadata fetch), but agents can work around them via delete_file and query_documents.

    Maintenance

    ActivityActive
    ResponsivenessNo issues

    Resources