# ContextGuard SQL Agent MCP Server

> ContextGuard SQL Agent MCP Server — ivan0912-contextguard-datahub-mcp. Use this tool when you need to perform safe and analytical SQL queries on DataHub data without modifying it. It solves problems related to data analysis and querying by providing a read-only interface with a strict SQL safety layer, ensuring zero write or mutation operations. The ContextGuard SQL Agent MCP Server takes DataHub schema, lineage, ownership, and tags as inputs and outputs secure, deterministic query results.

Canonical page: https://skillsregistry.net/skills/ivan0912-contextguard-datahub-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ivan0912-contextguard-datahub-mcp

## Description

A metadata-guided, read-only SQL analysis MCP server for DataHub that helps agents perform safe analytical queries using DataHub schema, lineage, ownership, and tags, with a deterministic planner and strict SQL safety layer against local synthetic SQLite, guaranteeing zero write or mutation operations.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pxf45rn0k1)
- **Repository:** <https://github.com/ivan0912/contextguard-datahub-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": "ivan0912-contextguard-datahub-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ivan0912-contextguard-datahub-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ivan0912-contextguard-datahub-mcp/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