Skip to main content
Glama
Sign In
deenesjakoptruzh
MCP - Model Context Protocol

MCP - Model Context Protocol

by eversonpereira
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

🧠 MCP - Model Context Protocol

Complete project for a conversational application with:

  • ✅ FastAPI + JWT

  • ✅ Local LLM via Ollama (ex: Mistral)

  • ✅ Context with vector memory (ChromaDB)

  • ✅ Support for multiple users and sessions

  • ✅ Automatic summary of long history

  • ✅ Plugin system to perform real actions

🚀 How to rotate

1. Clone the project and create the environment

git clone <repo>
cd mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

2. Configure .env

MODEL_NAME=mistral
VECTOR_DB_PATH=./chroma
DB_PATH=./mcp.db
CONTEXT_LIMIT=5
SUMMARY_TRIGGER=20

3. Launch Ollama

ollama run mistral

4. Upload the server

chmod +x start.sh
./start.sh

Related MCP server: RAG Context MCP Server

🛡️ Authentication

  • POST /auth/register: Create new user

  • POST /auth/login: Returns JWT token

Use the JWT token in requests to /mcp/chat.

🤖 Plugins

To call a plugin:

{
  "session_id": "sessao01",
  "prompt": "plugin: {\"name\": \"list_files\", \"args\": {\"path\": \"/etc\"}}"
}

📁 Structure

app/
├── routes/         # Rotas da API
├── services/       # Lógica de negócio (MCP, plugins, memória)
├── db/             # Persistência (SQLite e vetorial)
├── models/         # Schemas Pydantic
├── plugins/        # Plugins executáveis pelo MCP
├── auth/           # Login, JWT, usuários

📬 Contact

Developed by [Everson 🧠].

This server cannot be deployed

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

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • RAG Context MCP Server

    notbnull
    A
    license
    Not graded
    quality
    D
    maintenance
    A lightweight server that provides persistent memory and context management for AI assistants using local vector storage and database, enabling efficient storage and retrieval of contextual information through semantic search and indexed retrieval.
    2
    MIT

  • @contextable/mcp

    Contextable-me
    A
    license
    Not graded
    quality
    D
    maintenance
    A persistent AI memory server that enables storage and retrieval of context and project artifacts across conversations. It features full-text search, version history, and automatic content chunking using local SQLite or hosted cloud storage.
    5 npm
    Apache 2.0

  • Memory MCP

    dsins
    F
    license
    Not graded
    quality
    D
    maintenance
    A production-grade memory server for LibreChat that stores conversation turns and distills durable memories like decisions, constraints, and assumptions. It provides hybrid retrieval and consistency auditing to ensure AI plans remain aligned with established context and previous decisions.
    -

Appeared in Searches