teadata-mcp GEMINI.md

teadata-mcp GEMINI.md is an instructions file for Gemini CLI from adpena/teadata-mcp. It costs 943 tokens per session, scanned C, original, Apache-2.0.

Project instructions for teadata-mcp, a server that lets AI assistants access Texas Education Agency school data, plus its Python backend and React frontend.

In plain words
What is it for?
Use it when developing, debugging, or extending teadata-mcp and its interface for querying and displaying Texas school information.
Why use it?
It gives a coding agent the project context needed to understand the technology choices, data service, and folder layout.

Instructions file for Gemini CLI

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/adpena/teadata-mcp/gemini-md
Clone the repo
git clone --depth 1 https://github.com/adpena/teadata-mcp

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for teadata-mcp GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adpena/teadata-mcp/gemini-md.svg)](https://agentmods.dev/instructions/adpena/teadata-mcp/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/adpena/teadata-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/adpena/teadata-mcp/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 943 This file is loaded in full into every session.
When invoked 943 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00943 $0.00943
Opus 5 $0.00472 $0.00472
Sonnet 5 $0.00189 $0.00189
Haiku 4.5 $0.00094 $0.00094

Measured 3d ago against content hash 22289234b366, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

teadata-mcp GEMINI.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

* `uv` package manager (`curl -LsSf https://astral.sh/uv/install.sh | sh`)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

* `uv` package manager (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
GEMINI.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context: teadata-mcp

Overview

teadata-mcp is a Model Context Protocol (MCP) server that provides access to Texas Education Agency (TEA) data. It is designed primarily as a backend for ChatGPT applications, featuring a React-based frontend that integrates with OpenAI's apps-sdk-ui.

The application exposes a rich dataset of Texas school districts, campuses, and performance metrics through an SSE (Server-Sent Events) endpoint, allowing AI models to query and visualize this data.

Technology Stack

Backend

  • Language: Python 3.11+
  • Framework: Starlette (ASGI), sse-starlette for SSE.
  • Protocol: Model Context Protocol (MCP) via modelcontextprotocol package.
  • Dependency Management: uv
  • Key Library: teadata (Git dependency) for data access.

Frontend

  • Framework: React 18
  • Build Tool: Vite
  • Styling: Tailwind CSS, shadcn/ui components (Radix UI + Tailwind).
  • Integration: @openai/apps-sdk-ui for ChatGPT native look and feel.
  • Language: TypeScript

Directory Structure

  • src/teadata_mcp/: Python source code.
    • sse_server.py: Main ASGI application entry point. Handles SSE (/sse) and serves static files.
    • server.py: MCP server initialization and logic.
    • router.py: Tool definitions and request routing.
    • logic.py: Core business logic and data processing.
    • config.py: Configuration settings.
  • frontend/: React frontend source code.
    • src/: Components and views (App.tsx, CampusView.tsx, etc.).
    • vite.config.ts: Configured to output builds to ../static_dist.
  • static_dist/: (Generated) Compiled frontend assets served by the Python backend.
  • tests/: Pytest suite.
  • Dockerfile: Multi-stage build for production deployment.
  • run_dev.sh: Helper script for local development.

Development Workflow

Prerequisites

  • Python 3.11 or higher
  • Node.js 20+ (for frontend)
  • uv package manager (curl -LsSf https://astral.sh/uv/install.sh | sh)

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 93 lines · 943 tokens per session scan C 22289234b366

Subscribe to this mod's changes

teadata-mcp GEMINI.md is an instructions file published in the GitHub repository adpena/teadata-mcp (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 943 tokens to every session, about $0.0047 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.