# TiDB AI

> Use this tool when you need to integrate AI assistance into your database development workflow, enabling you to ask questions and receive responses without leaving your editor. It solves problems of cumbersome AI query processes, providing a lightweight bridge between your editor and TiDB AI. The tool takes in user questions as input and outputs streamed responses from the TiDB AI API, ideal for developers working with TiDB who require AI-driven insights.

Canonical page: https://skillsregistry.net/skills/siddontang-tidb-ai  
JSON: https://api.skillsregistry.net/v1/skills/siddontang-tidb-ai

## Description

TiDB AI MCP Server provides a lightweight bridge between Cursor and TiDB AI, enabling users to ask questions directly to TiDB AI without leaving their editor. Built with Go, it implements the Model Control Protocol with Server-Sent Events (SSE) transport and exposes a single 'ask' tool that forwards questions to the TiDB AI API and streams back responses. The server is configurable via command-line arguments for port selection and requires minimal setup, making it ideal for developers working with TiDB who want AI assistance integrated into their workflow.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/siddontang-tidb-ai)
- **Repository:** <https://github.com/siddontang/tidb-ai-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "siddontang-tidb-ai"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/siddontang-tidb-ai` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/siddontang-tidb-ai/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt