FastMCP Documentation Search Server
Enables intelligent search through FastMCP documentation using TF-IDF indexing, along with utility tools for arithmetic operations, text hashing, and web page content extraction via Jina Reader.
README
FastMCP Search Server 🚀
Português
Servidor baseado no protocolo MCP (Model Context Protocol) projetado para fornecer uma infraestrutura de Arquitetura de Acesso + Contexto. Este sistema permite que Agentes de IA estendam suas capacidades através de ferramentas locais e recuperação de dados especializados sem a necessidade de processamento de LLM no lado do servidor.
🏗️ Arquitetura e Funcionamento
O sistema opera como uma camada intermediária de inteligência local, automatizando a busca e o processamento de dados para injetar apenas o necessário na janela de contexto do cliente.
graph TD
User((Usuário)) --> Client[MCP Client / Interface]
subgraph "Camada de Comunicação"
Client <==> Protocol(MCP Protocol)
end
subgraph "FastMCP Server (Infraestrutura Local)"
Protocol <==> Tools{Motor de Ferramentas}
Tools --> Index[minsearch / TF-IDF]
Tools --> Scraping[Jina Reader]
Tools --> Logic[Lógica Local]
end
Index --- Docs[(Documentação Local)]
Scraping --- Web((Web))
🛠️ Ferramentas, Inputs e Outputs
| Ferramenta | Descrição | Input | Output |
|---|---|---|---|
search_docs |
Busca semântica inteligente usando TF-IDF. | query (string) |
Lista dos 5 documentos mais relevantes com preview. |
scrape_page |
Web scraping otimizado para IA. | url (string) |
Conteúdo da página em Markdown limpo. |
hash_text |
Geração de hash para integridade. | text (string) |
String SHA-256 hexadecimal. |
add |
Operação aritmética precisa. | a (int), b (int) |
Soma literal dos números. |
💻 Stack Tecnológica
- FastMCP: Framework principal para orquestração do protocolo.
- minsearch: Motor de busca minimalista para indexação in-memory.
- Scikit-learn & Pandas: Vetorização e manipulação de dados estruturados.
- Jina Reader API: Conversão de HTML para Markdown legível por IA.
🚀 Instalação
# Clone o repositório e instale as dependências
uv sync
# Execute o servidor
uv run python main.py
English
A server based on the Model Context Protocol (MCP) designed to provide an Architecture of Access + Context. This system allows AI Agents to extend their capabilities through local tools and specialized data retrieval without the need for LLM processing on the server side.
🏗️ Architecture and Workflow
The system operates as an intermediate layer of local intelligence, automating data search and processing to inject only what is necessary into the client's context window.
graph TD
User((User)) --> Client[MCP Client / Interface]
subgraph "Communication Layer"
Client <==> Protocol(MCP Protocol)
end
subgraph "FastMCP Server (Local Infrastructure)"
Protocol <==> Tools{Tools Engine}
Tools --> Index[minsearch / TF-IDF]
Tools --> Scraping[Jina Reader]
Tools --> Logic[Local Logic]
end
Index --- Docs[(Local Docs)]
Scraping --- Web((Web))
🛠️ Tools, Inputs, and Outputs
| Tool | Description | Input | Output |
|---|---|---|---|
search_docs |
Intelligent semantic search using TF-IDF. | query (string) |
List of the 5 most relevant docs with content preview. |
scrape_page |
AI-optimized web scraping. | url (string) |
Page content in clean Markdown. |
hash_text |
Hash generation for data integrity. | text (string) |
SHA-256 hexadecimal string. |
add |
Precise arithmetic operation. | a (int), b (int) |
Literal sum of the numbers. |
💻 Technical Stack
- FastMCP: Core framework for protocol orchestration.
- minsearch: Minimalist search engine for in-memory indexing.
- Scikit-learn & Pandas: Vectorization and structured data handling.
- Jina Reader API: HTML to AI-readable Markdown conversion.
🚀 Getting Started
# Clone the repository and install dependencies
uv sync
# Run the server
uv run python main.py
📝 Conclusão / Conclusion
Este projeto demonstra a viabilidade de construir camadas de suporte para agentes de IA que priorizam a eficiência e a soberania dos dados. Ao utilizar o protocolo MCP, removemos a fricção entre bases de dados locais e modelos globais, garantindo que o contexto injetado seja preciso, relevante e processado de forma otimizada.
This project demonstrates the feasibility of building support layers for AI agents that prioritize efficiency and data sovereignty. By using the MCP protocol, we remove the friction between local databases and global models, ensuring that the injected context is accurate, relevant, and optimally processed.
Developed as part of the AI Dev Bootcamp.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.