1. Conduid
  2. AI
  3. Local Analyst
MCP server · AI

Local Analyst

by · github.com/fabiothiroki/mcp-local-analyst

Talk to your data locally 💬📊. A private AI Data Analyst built with the Model Context Protocol (MCP), Ollama, and SQLite. Turn natural language into SQL queries without data leaving your machine. Includes a Dockerized Streamlit UI

Unclaimed MIT last commit 9 months ago model-context-protocolstreamlitmcpollamaailocal-llmsqlitepython
InstallView source
56Fair

Scored 5 months ago · breakdown

About Local Analyst

Local Analyst is an MCP server published by fabiothiroki in the AI category: talk to your data locally 💬📊. A private AI Data Analyst built with the Model Context Protocol (MCP), Ollama, and SQLite. Turn natural language into SQL queries without data leaving your machine. Includes a Dockerized Streamlit UI.

The repository has 9 stars and 8 forks, with the last commit 9 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/fabiothiroki/mcp-local-analyst

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Local Analyst

Powered by Claude · Grounded in docs

I know everything about Local Analyst. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 2 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • !Dependencies pinnedNo lockfile. Installs can pull different code over time.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

MCP Local Analyst

Demo

Talk to your data locally 💬📊. A private AI Data Analyst built with the Model Context Protocol (MCP), Ollama, and SQLite. Turn natural language into SQL queries without data leaving your machine. Includes a Dockerized Streamlit UI

📝 Read the full article on Medium

Getting Started

Prerequisites

Before running the application, make sure you have the following installed:

  1. Docker & Docker Compose - Required for running the application in containers

    • Install Docker Desktop from docker.com
    • Includes Docker Compose by default

  2. Ollama - For running local LLM models

    • Download from ollama.ai
    • After installation, pull a model: ollama pull mistral (or your preferred model)
    • Ollama will run as a service on http://localhost:11434

Installation & Running Locally

  1. Clone the repository

  2. Ensure Ollama is running:

    ollama serve

    (Keep this running in a separate terminal)

  3. Start the application with Docker Compose:

    docker-compose up --build

  4. Open your browser and navigate to:

    http://localhost:8501

Configuration

  • Modify the database by editing src/seed_data.py if needed
  • Configure model selection and parameters in the application UI
  • Data is stored in the data/ directory

README fetched from the repository 2 hours ago. The original is authoritative.

Questions

About Local Analyst

How do I install Local Analyst?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Local Analyst safe to use with an AI agent?

Its trust score is 56 out of 100 (fair). It passes 3 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Local Analyst still maintained?

The last commit was 9 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.