Skip to main content
Glama
QkartBismuth

Bismut Vector MCP

by QkartBismuth
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Bismut Vector MCP

No user-submitted related servers found.

    Related Servers

    • Sunstone Weave: Local Semantic

      space-bacon
      F
      license
      A
      quality
      A
      maintenance
      Semantic code search for any MCP client: indexes local folders of code and docs and answers plain-language or code queries with matching passages, file paths, line ranges and scores. Embedding runs on the local CPU with the Motherlode code-search encoder, so no file content leaves the machine; the encoder downloads once from Hugging Face. Install: npx -y blackwindow-weave-mcp.
      6
      4
      -

    • lore-mcp

      romainsc
      A
      license
      A
      quality
      B
      maintenance
      Indexes local Markdown/text files into a SQLite database with vector embeddings and provides MCP tools for semantic search without cloud dependencies.
      3
      AGPL 3.0

    • mycelium

      Transmitt0r
      A
      license
      Not graded
      quality
      A
      maintenance
      Provides MCP tools for semantic search over personal knowledge sources using pluggable embeddings and local vector indexing.
      1
      MIT

    • 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
      5 npm
      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
    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

    A4.1/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have clearly distinct roles (index_paths vs index_text differ by source type, and list_sources vs list_collections differ by resource). The only mild overlap is between get_context and get_chunk, which both retrieve fuller content, though their descriptions distinguish fragment-level vs surrounding-context use.

    Naming Consistency4/5

    Nearly all names follow a verb_noun pattern (list_collections, index_paths, delete_sources, drop_collection, get_chunk). Minor deviations are the bare single-word tools `search` and `stats`, but the overall convention is readable and predictable.

    Tool Count5/5

    Ten tools is well within the ideal range and each one maps to a distinct stage of the index/search/retrieve lifecycle. No tool feels redundant or superfluous.

    Completeness4/5

    The surface covers the full lifecycle: indexing (paths/text), discovery (collections/sources), search, context retrieval (get_context/get_chunk), and deletion (delete_sources/drop_collection) plus health via stats. The main gap is an explicit create_collection or metadata-update operation, but these are likely handled implicitly by indexing.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources