Personal Knowledge-Base MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Personal Knowledge-Base MCP Serversearch my notes for anything about MCP server setup"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Personal Knowledge-Base MCP Server & Web App
F6-Zeppelin Fellowship ā Project 3
A multi-tenant Model Context Protocol (MCP) server and web application enabling semantic search over personal document corpora backed by Qdrant vector search and FastMCP.
š Overview
Static keyword search fails when notes, research papers, and technical documents use different wording for the same concepts. This project implements a protocol-level FastMCP server paired with a Qdrant Vector Database to enable context-aware semantic search over real-world documents.
The system supports dual modes of interaction:
MCP Client Integration: Native tools callable from MCP-compliant clients like Claude Desktop or Claude Code.
Multi-Tenant Web UI: A web dashboard providing isolated document management, uploading, and search capabilities per user.
Related MCP server: Tea Rags MCP
⨠Key Features
Protocol-Level Integration (
FastMCP): Exposes structured MCP tools (search_notes,get_document,list_sources) for native AI agent invocation.Multi-Tenant Isolation: Payload-level tenant isolation in Qdrant ensures document chunks and search results are strictly scoped per user.
Strict Relevance Cutoff: Rejects low-confidence vector matches below similarity thresholds to prevent low-relevance hallucination propagation.
Automated Ingestion Pipeline: Handles PDF, Markdown, and TXT parsing, dynamic chunking, and embedding generation.
Quantitative Retrieval Benchmarking: Hand-labeled evaluation suite tracking Mean Reciprocal Rank (MRR) and Precision@K across test queries.
š ļø Architecture & Tech Stack
Layer | Technology | Purpose |
Protocol | FastMCP (Python) | Tool registry and JSON-RPC over STDIO / HTTP transport |
Backend API | FastAPI | User authentication (JWT), file upload, REST search endpoints |
Vector DB | Qdrant | HNSW similarity search with payload-based user isolation |
Embeddings | sentence-transformers / OpenAI | Dense vectorization of document chunks |
Frontend | React / Tailwind CSS | Web dashboard for uploading documents and testing queries |
š Evaluation & Metrics
Metric | Target | Result |
Precision@3 | ā„ 80% | TBD |
MRR (Mean Reciprocal Rank) | ā„ 0.85 | TBD |
Relevance Threshold | Cosine ā„ 0.72 | Enforced |
ā” Quick Start
1. Environment Setup
cd backend
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env2. Configure Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"personal-kb": {
"command": "python",
"args": ["-m", "app.mcp_server.server"],
"env": {
"QDRANT_URL": "http://localhost:6333",
"QDRANT_API_KEY": "your-api-key"
}
}
}
}š Repository Structure
KNOWLEDGE_BASE-MCP_SERVER/
āāā backend/
ā āāā app/
ā ā āāā api/ # FastAPI REST endpoints (Auth, Documents, Search)
ā ā āāā core/ # App configuration & JWT security settings
ā ā āāā db/ # Qdrant vector database initialization & schemas
ā ā āāā eval/ # Precision@K and MRR benchmark scripts
ā ā āāā mcp_server/ # FastMCP server definition & tool implementations
ā ā āāā services/ # Ingestion, embedding, & similarity search services
ā āāā tests/ # Backend API and retrieval test suite
ā āāā main.py # Application entry point
ā āāā requirements.txt # Python backend dependencies
ā āāā .env.example # Template for environment variables
āāā data/
ā āāā sample_docs/ # Document corpus for local testing
āāā docs/ # Architecture diagrams & project documentation
āāā frontend/ # React / Tailwind web application for multi-user management
ā āāā src/
ā āāā components/ # UI components (Uploaders, Search bar, Score badges)
ā āāā context/ # Auth & Session state providers
ā āāā pages/ # Document dashboard & Search playground
ā āāā services/ # API client bindings
āāā .gitignore # Ignored files (venvs, keys, vector storage)
āāā docker-compose.yml # Local Qdrant & FastAPI orchestration
āāā README.md # Project documentation This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityFmaintenanceA Model Context Protocol (MCP) server that enables semantic search and retrieval of documentation using a vector database (Qdrant). This server allows you to add documentation from URLs or local files and then search through them using natural language queries.24135Apache 2.0
- Alicense-qualityAmaintenanceA high-performance MCP server for semantic search and codebase indexing using the Qdrant vector database. It features optimized embedding pipelines, AST-aware chunking, and git metadata enrichment for fast, privacy-focused local or remote search.68511MIT
- Alicense-qualityDmaintenanceMCP server for document ingestion and semantic search on Qdrant. Enables ingesting local documents, generating embeddings with OpenAI, and performing vector search with metadata filters.Apache 2.0
- AlicenseAqualityDmaintenanceLocal-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.39MIT
Related MCP Connectors
Agentic search over your Dewey document collections from any MCP-compatible client.
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/F6-ZeppelinFellowship/Knowledge_Base-MCP_SERVER'
If you have feedback or need assistance with the MCP directory API, please join our Discord server