# Boltz

> Use this tool when you need to predict protein structures, screen molecules, or estimate ligand binding affinities within a conversational interface. Boltz solves problems in computational biology by providing workflows for structure prediction, molecular screening, and binding estimation through natural language inputs and outputs. It integrates seamlessly with Claude Desktop, accepting text-based commands and returning results directly within conversations.

Canonical page: https://skillsregistry.net/skills/boltz  
JSON: https://api.skillsregistry.net/v1/skills/boltz

## Description

This Claude Desktop extension enables protein structure prediction, molecular screening, and ligand binding estimation directly within Claude conversations. Packaged as a .mcpb bundle for seamless Claude Desktop integration, it provides access to Boltz's computational biology workflows through natural language tool calls without requiring separate software beyond Claude Desktop 0.10.0 or later.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/boltz)
- **Repository:** <https://github.com/boltz-bio/boltz-mcpb>

## 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": "boltz"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/boltz` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/boltz/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