Skip to main content
Glama
sfrangulov

minirag-mcp

by sfrangulov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to minirag-mcp

No user-submitted related servers found.

    Related Servers

    • ragi

      SusuTawar
      A
      license
      A
      quality
      D
      maintenance
      Local-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.
      3
      10 npm
      MIT

    • corpus-rag

      monahand1023
      A
      license
      Not graded
      quality
      A
      maintenance
      MCP server for local RAG over personal notes, PDFs, and documents, enabling plain-English querying and hybrid search with multi-hop context expansion.
      MIT

    • 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
      4,565 npm
      MIT
    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

    A4.3/5.0

    Scored across 11 tools

    Disambiguation5/5

    Each tool targets a distinct operation: ingestion is split cleanly by source type (ingest_file, ingest_data, ingest_url), sync is split into start/status, and reads are split by scope (read_file vs read_chunk_neighbors). The only adjacency is between list_files and status (both report index/disk state) and sync_start vs ingest_file, but the descriptions make the bulk-vs-single distinction explicit.

    Naming Consistency4/5

    All names are snake_case and readable, with a mostly verb_noun pattern (list_files, read_file, ingest_url, delete_file, query_documents). Minor deviations: sync_start and sync_status invert to noun_verb, and status is a bare noun, so the pattern is not perfectly uniform.

    Tool Count5/5

    Eleven tools is well within the sweet spot and each one maps to a real workflow step: index management (sync, status), content ingestion across three source types, retrieval (query, read), and housekeeping (list, delete). Nothing appears redundant or padded.

    Completeness4/5

    The lifecycle is well covered: ingest from files/data/URLs, bulk reconcile via sync, poll status, query, read, list, and delete with re-ingest as the update path. Minor gaps exist — no cancel/abort for a running sync, no bulk delete, and no direct way to inspect a data/url source's metadata apart from its content.

    Maintenance

    ActivityMaintained
    ResponsivenessSlow

    Resources