# cgm-get-agent

> cgm-get-agent — johnmartinez-cgm-get-agent. Use this tool when you need to connect your Dexcom G7 CGM to AI agents like Claude and ChatGPT, enabling natural language queries about your glucose levels. It solves the problem of accessing CGM data through a secure and encrypted interface, using OAuth2 and AES-256 encryption. The tool takes natural language inputs and outputs glucose level information, ideal for use cases requiring seamless and secure CGM data retrieval.

Canonical page: https://skillsregistry.net/skills/johnmartinez-cgm-get-agent  
JSON: https://api.skillsregistry.net/v1/skills/johnmartinez-cgm-get-agent

## Description

MCP server connecting Claude and ChatGPT to your Dexcom G7 CGM. Ask about your glucose in natural language. Go, Docker, 11 tools, OAuth2, AES-256 encrypted tokens.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** BSD-3-Clause
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/johnmartinez/cgm-get-agent)

## 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": "johnmartinez-cgm-get-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/johnmartinez-cgm-get-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/johnmartinez-cgm-get-agent/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