Skip to main content
Glama
Sign In
lilbee

lilbee

by tobocop2
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to lilbee

  • knowledge-rag

    lyonzin
    A
    license
    A
    quality
    A
    maintenance
    Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.
    13
    528 PyPI
    302
    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

Related Servers

  • rag-mcp

    Kamalesh-Kavin
    F
    license
    A
    quality
    D
    maintenance
    Enables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.
    4
    -

  • bigos

    FPGArtktic
    A
    license
    Not graded
    quality
    F
    maintenance
    Enables fully local, cross-lingual retrieval over documents and source code by indexing files and providing search and ingest tools, with all data staying on the machine.
    GPL 2.0

  • Folio

    Shahrukh19S
    A
    license
    A
    quality
    D
    maintenance
    A privacy-first, zero-cost AI assistant that lets you chat with your documents locally via CLI or web app, supporting search, summarization, and Q&A using your own model.
    7
    MIT

  • Synorive

    arturoaeriform174
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables private, offline semantic search across local files (documents, images, videos) using OCR and vector search, and optionally performs web research with cited sources.
    AGPL 3.0
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

B3.1/5.0

Scored across 29 tools

Disambiguation4/5

Most tools target clearly distinct resources or actions, but there is some overlap among model_list/catalog_browse/model_show and between reset/settings_reset. The detailed descriptions resolve most ambiguity, so an agent can usually select correctly.

Naming Consistency3/5

All names use snake_case, but the patterns vary: bare verbs such as search, sync, add; verb_noun such as get_gpus and list_documents; noun_verb such as settings_list, model_pull, and wiki_status; plus the abbreviation model_rm. It remains readable, but the convention is mixed rather than predictable.

Tool Count2/5

With 29 tools spanning knowledge-base lifecycle, crawling, wiki, settings, model management, and GPU placement, the surface is heavy for one MCP server. Many tools are justified by the broad scope, but the set feels sprawling rather than tightly scoped.

Completeness4/5

Core workflows for document ingestion/search, crawling, settings, model management, and GPU placement are well covered. The main gap is the wiki layer: status and wipe exist, but generation/lint controls are not exposed, though agents can still handle most primary tasks.

Maintenance

ActivityNo data
ResponsivenessOutdated data

Resources