Skip to main content
Glama
NavinAnik

mcp-knowledge-server

by NavinAnik
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
API_KEYNoAPI key for authentication
CHUNK_SIZENoChunk size (default: 1000)
QDRANT_URLNoQdrant server URL (default: http://localhost:6333)
ENABLE_AUTHNoEnable authentication (true/false)
DATABASE_URLNoDatabase URL (default: sqlite:///./knowledge.db)
GROQ_API_KEYNoGroq API key
LLM_PROVIDERNoLLM provider (ollama, openai, anthropic, gemini, groq, together, openrouter, lmstudio, llamacpp, openai_compatible)
OLLAMA_MODELNoOllama model (default: qwen3:8b)
OPENAI_MODELNoOpenAI model (default: gpt-4.1)
CHUNK_OVERLAPNoChunk overlap (default: 200)
CHUNK_STRATEGYNoChunking strategy (recursive, token, markdown, semantic)
GEMINI_API_KEYNoGemini API key
OPENAI_API_KEYNoOpenAI API key
QDRANT_API_KEYNoQdrant API key
EMBEDDING_MODELNoEmbedding model (default: all-MiniLM-L6-v2)
OLLAMA_BASE_URLNoOllama base URL (default: http://localhost:11434)
TOGETHER_API_KEYNoTogether AI API key
ANTHROPIC_API_KEYNoAnthropic API key
EMBEDDING_PROVIDERNoEmbedding provider (sentence_transformers, openai, ollama, voyage, cohere)
OPENROUTER_API_KEYNoOpenRouter API key

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
health_checkA

Check the health status of the knowledge server.

search_documentsA

Search documents by semantic similarity.

    Args:
        query: The search query text.
        collection: Optional collection name to search in.
        top_k: Number of results to return (default 10).
rag_answerA

Generate a RAG answer with citations from the knowledge base.

    Args:
        query: The question to answer.
        collection: Optional collection to search in.
        top_k: Number of context chunks to retrieve.
add_documentA

Add a document to the knowledge base.

    Args:
        file_path: Absolute path to the document file.
        collection: Target collection name.
        author: Optional document author.
        tags: Comma-separated tags.
update_documentA

Update an existing document by re-ingesting it.

    Args:
        document_id: UUID of the document to update.
        file_path: Absolute path to the new document file.
delete_documentA

Delete a document from the knowledge base.

    Args:
        document_id: UUID of the document to delete.
list_documentsC

List documents in the knowledge base.

    Args:
        collection: Optional collection filter.
        limit: Maximum number of documents to return.
get_documentA

Get a document by ID.

    Args:
        document_id: UUID of the document.
similar_documentsA

Find documents similar to a given chunk.

    Args:
        chunk_id: The chunk ID to find similar documents for.
        collection: Optional collection to search in.
        top_k: Number of similar results to return.
create_collectionA

Create a new document collection.

    Args:
        name: Collection name (alphanumeric, hyphens, underscores).
        description: Optional collection description.
delete_collectionA

Delete a collection and all its vectors.

    Args:
        name: Collection name to delete.
list_collectionsA

List all document collections.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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

A3.7/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct action on either documents or collections. search_documents and similar_documents are differentiated by input (query text vs. chunk ID), and rag_answer is clearly for answer generation, so there is no ambiguity.

Naming Consistency4/5

Most tools follow a verb_noun pattern with snake_case (add_document, delete_document, list_collections). However, 'add' and 'create' are used interchangeably for creation, and 'similar_documents' uses an adjective instead of a verb, creating minor inconsistencies.

Tool Count5/5

With 12 tools, the server covers document CRUD, collection management, search/retrieval, and health monitoring. This is well-scoped for a knowledge server and each tool earns its place without redundancy.

Completeness4/5

The tool surface provides full document lifecycle (add, get, update, delete, list), collection management (create, delete, list), semantic search, similar-document lookup, and RAG. Minor gaps such as missing get_collection or update_collection exist, but core workflows are fully covered.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources