Agent MCP Server

AI supply chain security scanner — CVE scanning, blast radius, policy enforcement, SBOM generation

Remote serverstreamable-httpPython

What is the Agent MCP server?

Most cloud and infrastructure work still happens through a UI a human drives. Agent MCP server moves it into the conversation instead. AI supply chain security scanner — CVE scanning, blast radius, policy enforcement, SBOM generation.

The short version

The tools it exposes

The server publishes 14 tools. What each one is for:

  • Read — only discovery by default; runtime write decisions are separate and explicit
  • Role — Start here
  • Developers — agent-bom scan
  • AppSec — agent-bom scan . -f sarif -o findings.sarif
  • Overview — Findings
  • Investigation — Remediation
  • Target — Start here
  • EKSTerraform module
  • Air-gappedImage bundle guide
  • Need — First action
  • Surface — Get it
  • Container — docker pull agentbom/agent-bom — Docker Hub

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agent's toolset — Read, Role, Developers and 11 more — is a fair guide to whether it matches your workflow. It is maintained by msaad00; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agent's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agent.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Readonly discovery by default; runtime write decisions are separate and explicit.
RoleStart here
Developersagent-bom scan .
AppSecagent-bom scan . -f sarif -o findings.sarif
OverviewFindings
InvestigationRemediation
TargetStart here
EKS[Terraform module](deploy/terraform/platform-eks)
Air-gapped[Image bundle guide](site-docs/deployment/airgapped-image-bundle.md)
NeedFirst action
SurfaceGet it
Containerdocker pull agentbom/agent-bom — [Docker Hub](https://hub.docker.com/r/agentbom/agent-bom)
Kuberneteshelm install agent-bom oci://ghcr.io/msaad00/charts/agent-bom
SDKs[Python](sdks/python) · [TypeScript](sdks/typescript) · [Go](sdks/go)

How to install the Agent MCP server

{
  "mcpServers": {
    "agent-bom": {
      "command": "uvx",
      "args": ["agent-bom"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Agent to Read.
  • Use Agent to Role.
  • Use Agent to Developers.

Frequently asked questions

It connects Agent to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Read, Role, Developers, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agent directly.