MCP Server: Secure, Lightning-Fast Local Hosting for CPS DataOps

Maximize CPS data ops with MCP Server—secure, lightning-fast local hosting built for Chicago’s schools, no cloud middlemen needed!

Visit Repository

✨ Research And Data

4.4(145 reviews)

217 saves

101 comments

Ranked in the top 1% of all AI tools in its category

About MCP Server

What is MCP Server: Secure, Lightning-Fast Local Hosting for CPS DataOps?

MCP Server provides a secure and high-performance local hosting solution for managing Chicago Public Schools (CPS) data through a combination of SQLite and LanceDB vector databases. Designed for DataOps workflows, this server exposes structured school data and semantic search capabilities for contextual queries, enabling efficient access to CPS datasets without compromising security or speed.

How to use MCP Server: Secure, Lightning-Fast Local Hosting for CPS DataOps?

Begin by obtaining the required databases from the cps-childcare project. Configure the server in Claude Desktop by specifying paths to your SQLite and LanceDB files. For debugging, utilize the MCP Inspector tool, which provides browser-based diagnostics. Here’s a simplified workflow:

Set up configuration parameters in your claude_desktop_config.json.
Launch the server with the specified command-line arguments.
Use the query_schools_and_neighborhoods or query_school_websites endpoints to interact with the databases.

MCP Server Features

Key Features of MCP Server: Secure, Lightning-Fast Local Hosting for CPS DataOps?

Core features include:

Secure local hosting with strict data isolation
Instant query performance via optimized SQLite and vectorized LanceDB storage
Context-aware search capabilities for school websites
Integrated debugging support via the MCP Inspector
Flexible parameterization for adaptive querying

Use cases of MCP Server: Secure, Lightning-Fast Local Hosting for CPS DataOps?

Common applications include:

Data analysts querying neighborhood-school correlations
Educators retrieving policy-relevant website content
Researchers benchmarking educational resource distribution
Automated workflows requiring real-time CPS data access

MCP Server FAQ

FAQ from MCP Server: Secure, Lightning-Fast Local Hosting for CPS DataOps?

Q: How do I troubleshoot connection issues?
Use the MCP Inspector’s diagnostic interface to inspect server logs and API responses. Ensure database paths are correctly configured.

Q: Can this run on Windows/macOS?
Yes, provided system dependencies are met. The server is OS-agnostic but requires compatible database drivers.

Q: What query formats are supported?
Structured queries for SQLite and semantic search terms for LanceDB. Refer to the official docs for syntax details.

Content

mcp-cps-data MCP server

A MCP server project for exposing a local SQLite database and a local LanceDB vector database with information on Chicago Public Schools

Components

Tools

The server implements two tools:

query_schools_and_neighborhoods: Excecute a SELECT query on a table of Chicago public schools and their neighborhoods called "schooltoneighborhood" with the following schema: (id INTEGER NOT NULL, created_at DATETIME NOT NULL, school_id INTEGER NOT NULL, school_name VARCHAR NOT NULL, neighborhood VARCHAR NOT NULL, PRIMARY KEY (id)).
- Takes required parameter query
query_school_websites: Query a database of Chicago public school websites for context relevant to answering a given question.
- Takes required parameter question and optional parameter school_name.

Configuration

Get the SQlite database and the LanceDB vector database from the [cps-childcare] project(https://github.com/mdagost/cps-childcare).

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration:

  "mcpServers": {
    "mcp-cps-data": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-cps-data",
        "run",
        "mcp-cps-data",
        "--sqlite-path",
        "/path/to/cps_crawler.db",
        "--lancedb-path",
        "/path/to/embeddings.lancedb"
      ]
    }
  }

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-cps-data run mcp-cps-data --sqlite-path /path/to/cps_crawler.db --lancedb-path /path/to/embeddings.lancedb

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.