{
  "markdown": "# inbody-api-mcp\n\n<!-- mcp-name: io.github.rwestergren/inbody-api-mcp -->\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![CI](https://github.com/rwestergren/inbody-api-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/rwestergren/inbody-api-mcp/actions/workflows/ci.yml)\n[![Build Docker image](https://github.com/rwestergren/inbody-api-mcp/actions/workflows/docker.yml/badge.svg)](https://github.com/rwestergren/inbody-api-mcp/actions/workflows/docker.yml)\n[![PyPI](https://img.shields.io/pypi/v/inbody-api-mcp.svg)](https://pypi.org/project/inbody-api-mcp/)\n\n> **Hosted version for Claude.ai, ChatGPT, and Grok coming soon.** [**Join the waitlist →**](https://tally.so/r/A7WVge?ref=inbody-api-mcp)\n\nAn [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) server for\n[InBody](https://inbody.com/) body-composition data, built on the\nreverse-engineered mobile REST API used by the InBody Android app.\n\nInBody has no public API and no web UI for personal scan data. This server talks\nto the same JSON REST endpoints the mobile app uses, exposing your body\ncomposition history (body fat, muscle mass, body water, segmental impedance) to\nany MCP client.\n\n## Features\n\n- **Profile** -- identity and baseline metrics (height, weight, age, gender)\n- **Scan history** -- chronological summaries (weight, BMI, % body fat, muscle mass)\n- **Full scan metrics** -- complete body composition (BCA), BMI/%fat/muscle with\n  normal ranges (MFA), and segmental/multi-frequency impedance (IMP)\n- **Automatic region routing** -- resolves the correct regional API host from\n  your country code\n- **Automatic re-authentication** -- caches the 24h JWT and re-logs in on expiry\n\n## Quick Start\n\n### 1. Install [uv](https://docs.astral.sh/uv/)\n\n```bash\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\n\n### 2. Set credentials\n\n```bash\nexport INBODY_LOGIN_ID=\"3026323617\"   # registration phone number, digits only\nexport INBODY_LOGIN_PW=\"your-password\"\nexport INBODY_COUNTRY_CODE=\"US\"       # ISO country code (default US)\n```\n\n> **`INBODY_LOGIN_ID` is the phone number used at registration**, not your email\n> -- digits only, no country code or `+` (e.g. `3026323617`). InBody keys login\n> on the phone number; the email is only returned as profile data. An email\n> value will fail login with `EmptyData`.\n\n### 3. Configure your MCP client\n\n`uvx` downloads and runs the server on demand -- no separate install step.\n\n#### OpenCode (`opencode.json`)\n\n```json\n{\n  \"$schema\": \"https://opencode.ai/config.json\",\n  \"mcp\": {\n    \"inbody\": {\n      \"type\": \"local\",\n      \"command\": [\"uvx\", \"inbody-api-mcp\"],\n      \"environment\": {\n        \"INBODY_LOGIN_ID\": \"{env:INBODY_LOGIN_ID}\",\n        \"INBODY_LOGIN_PW\": \"{env:INBODY_LOGIN_PW}\",\n        \"INBODY_COUNTRY_CODE\": \"US\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\n#### Claude Desktop (`claude_desktop_config.json`)\n\n```json\n{\n  \"mcpServers\": {\n    \"inbody\": {\n      \"command\": \"uvx\",\n      \"args\": [\"inbody-api-mcp\"],\n      \"env\": {\n        \"INBODY_LOGIN_ID\": \"3026323617\",\n        \"INBODY_LOGIN_PW\": \"your-password\",\n        \"INBODY_COUNTRY_CODE\": \"US\"\n      }\n    }\n  }\n}\n```\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_profile` | User identity and baseline metrics (height, weight, age, gender) |\n| `get_scan_count` | Total number of scans on the account |\n| `list_scans` | Chronological scan summaries (weight, BMI, % body fat, muscle mass) |\n| `get_scan` | Full metric set for one scan (BCA / MFA / IMP blocks) |\n\nThis server is read-only: no write or delete endpoints are exposed.\n\n## How It Works\n\nThis server communicates with the regional `*.lookinbody.com` REST API -- the\nsame backend used by the InBody Android app (v2.8.31). The API was\nreverse-engineered by capturing app traffic with mitmproxy and confirming\npayload shapes against the live API.\n\nThe auth flow:\n\n1. `POST /CommonAPI/GetCountryInfoV2` (on `appapicommon.lookinbody.com`) returns\n   a per-country host table. The `Type == \"API\"` row for your ISO country code\n   gives the regional API base (US -> `appapiusav2.lookinbody.com`) and the\n   numeric phone code used in request bodies.\n2. `POST /V2/Main/GetLoginWithSyncDataPartV2` exchanges the login ID + password\n   for a 24-hour JWT, a refresh token, and the account UID.\n3. Subsequent calls send `Authorization: Bearer <JWT>`. The client\n   re-authenticates automatically when the token expires.\n\nEach scan record nests three blocks: **BCA** (body composition analysis -- body\nwater, protein, mineral, fat, segmental water), **MFA** (BMI, % body fat,\nskeletal muscle mass, WHR with normal ranges), and **IMP** (raw impedance per\nfrequency and body segment).\n\n## Python API\n\nYou can use the client directly:\n\n```python\nfrom inbody_api_mcp.client import InBodyClient\n\nclient = InBodyClient()\n\n# Total number of scans\ncount = client.get_scan_count()\n\n# Recent scans (newest first), paginated\nscans = client.get_scans(number=20, index=0)\n\n# User profile\nprofile = client.get_user_info()\n```\n\n## Transport\n\nstdio only. MCP clients (OpenCode, Claude Desktop) spawn the stdio process\ndirectly via `uvx`/`uv`.\n\n## License\n\nMIT\n",
  "bytes": 5191,
  "sha": "ff4385acec340ca8168013094b00db2db2a0fe2df4625df7a25dc171833ba66b",
  "repo_slug": "rwestergren/inbody-api-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_rwestergren_inbody_api_mcp_d8b3c6dc/readme"
}