Agent Bom MCP Server

@mcp/server-fs

Open security platform for agentic infrastructure — broad scanning, blast radius, runtime, and trust

24 GitHub npm PyPI

No known CVEs

No license

Actively maintained

Last commit 17d ago

Works with most clients

Transport: stdio, http

0 tools

Grade F

Edit this pageView history

Security DevOps

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

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

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-msaad00-agent-bom)](https://mcppedia.org/s/io-github-msaad00-agent-bom)

Read me

What Agent Bom MCP Server does

agent-bom scans local and fleet AI infrastructure, builds an AI BOM across agents, MCP servers, tools, packages, credential environment names, cloud, runtime, and skills, then turns that inventory into findings, compliance evidence, and graph-backed exposure paths.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y '@mcp/server-fs' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

47/100across 5 weighted dimensions

How we score →

0255075100

−53

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked @mcp/server-fs against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Agent Bom MCP Server safe to use?: Agent Bom MCP Server has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install Agent Bom MCP Server?: Agent Bom MCP Server supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Agent Bom MCP Server?: Agent Bom MCP Server is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is Agent Bom MCP Server actively maintained?: Agent Bom MCP Server is actively maintained — last commit was 17 days ago. It has 24 GitHub stars.

Similar servers

Others in security / devops

View all →

Mcp Gitlab94

MCP server for using the GitLab API

1.7k 12

Ida Pro Mcp90

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

9.8k 3

Mcpki Server90

mcpki-server is the backend infrastructure for https://www.mcpki.org, enabling secure public key management and autonomous certificate handling for large language models (LLMs).

io.github.jasonxkensei/xproof90

Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.

1 1

MCP Security Weekly

Get CVE alerts and security updates for Agent Bom MCP Server and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

What it is

Read-only scanner + self-hosted control plane over local projects, agent fleets, MCP runtimes, and cloud estates (AWS, Azure, GCP, Snowflake) — agentless, in your own boundary, nothing installed on targets.

One correlated evidence model — findings, assets, packages, cloud resources, identities, agents, MCP servers, credentials, and runtime decisions normalize into a single Finding + ContextGraph, so the CLI, API, UI, MCP tools, reports, and gateway all read the same evidence.

Blast radius, not CVE rows — a vulnerable package links to the MCP server that loads it, the tools it exposes, reachable credential references, and the agents that can call it.

Posture lanes in one place — vulnerabilities (SCA + AST reachability), cloud misconfigs (CSPM / CIS), identity and authorization evidence (CIEM), Kubernetes (KSPM), data (DSPM), code (SAST), AI / MCP (AISPM), runtime gateway enforcement, and compliance evidence that reconciles from executive read down to each finding.

Frequently Asked Questions

Is Agent Bom MCP Server safe to use?

Agent Bom MCP Server has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install Agent Bom MCP Server?

Agent Bom MCP Server supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with Agent Bom MCP Server?

Agent Bom MCP Server is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.

Is Agent Bom MCP Server actively maintained?

Agent Bom MCP Server is actively maintained — last commit was 17 days ago. It has 24 GitHub stars.

Open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure.

Headless agent primitives and human cockpit surfaces over one shared evidence model.

Live demo (read-only sandbox) · Docs · First Run · Self-host · GitHub Action · Docker · Changelog

What it is

Read-only scanner + self-hosted control plane over local projects, agent fleets, MCP runtimes, and cloud estates (AWS, Azure, GCP, Snowflake) — agentless, in your own boundary, nothing installed on targets.
One correlated evidence model — findings, assets, packages, cloud resources, identities, agents, MCP servers, credentials, and runtime decisions normalize into a single Finding + ContextGraph, so the CLI, API, UI, MCP tools, reports, and gateway all read the same evidence.
Blast radius, not CVE rows — a vulnerable package links to the MCP server that loads it, the tools it exposes, reachable credential references, and the agents that can call it.
Posture lanes in one place — vulnerabilities (SCA + AST reachability), cloud misconfigs (CSPM / CIS), identity and authorization evidence (CIEM), Kubernetes (KSPM), data (DSPM), code (SAST), AI / MCP (AISPM), runtime gateway enforcement, and compliance evidence that reconciles from executive read down to each finding.

Coverage depth and honest boundaries: AI infrastructure scanning · product boundaries

Who it's

... View full README on GitHub