Lattice

io.namiqv0.2.0Updated Oct 4, 2026

Read-only cyber knowledge graph for AI agents: CVEs, ATT&CK, detections, with each link's source.

VerifiedStreamable HTTPWeb executableSecurity & MonitoringKnowledge & Memory

Overview

AI-generated overview

Gives an assistant read-only access to a cyber knowledge graph covering CVEs, ATT&CK techniques, and detections, with sources for each link.

What it does
Lattice is a remote, read-only knowledge graph for security data. According to its description, it covers CVEs, ATT&CK techniques, and detections, and returns the source behind each link so results can be traced. The manifest does not list individual tools, so the exact query surface is not documented here.
When to use it
Useful when an assistant needs to look up vulnerability, adversary-technique, or detection information and cite where each connection came from. It is aimed at security research and analysis rather than general web search.
Requirements
A remote streamable HTTP endpoint at lattice.namiq.io; nothing runs locally. It requires an X-API-Key header. The manifest describes a trial key that must be requested from the provider and is shown once and emailed.
Before you install
The X-API-Key header is a required secret; treat it as a credential and do not expose it. The server is described as read-only, so it should not change data, but queries are sent to a third-party endpoint and may reveal what you are investigating.

Installation

In SourceWeft

  1. Open Lattice in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "lattice": {
      "type": "http",
      "url": "https://lattice.namiq.io/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.2.0LatestOct 4, 2026