# Latent Defense MCP Server

> Use this tool when you need to visualize and analyze potential attack paths in your infrastructure. It connects code repositories to a security graph, using the JEPA energy model to identify vulnerabilities and provide actionable findings through a terminal interface. Ideal for security teams seeking to proactively defend against threats and prioritize remediation efforts.

Canonical page: https://skillsregistry.net/skills/latent-defense-mcp-server-public  
JSON: https://api.skillsregistry.net/v1/skills/latent-defense-mcp-server-public

## Description

Connects Claude Code to a Latent Defense deployment to map GitHub repositories into an infrastructure graph, discover attack paths using the JEPA energy model, and triage findings from the terminal.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xi69gy0owx)
- **Repository:** <https://github.com/latent-defense/mcp-server-public>

## 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": "latent-defense-mcp-server-public"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/latent-defense-mcp-server-public` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/latent-defense-mcp-server-public/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