agent-bom registry

MCP server security registry and trust assessment — look up servers in the 1081-entry server security metadata registry, run pre-install marketplace checks, batch fleet risk scorin…

Agent Bom

@msaad00

What This Skill Does

Security registry and trust assessment tool for MCP servers. Looks up servers in a bundled 1013-entry metadata registry, runs pre-install marketplace checks, batch fleet risk scoring, skill file trust analysis, and SAST code scans via Semgrep. No network calls or API keys required for core functionality.

Replaces manual security vetting of MCP servers by providing a bundled registry with trust scores, marketplace cross-references, and automated code scanning in a single offline tool.

When to Use It

  • Look up an MCP server's security metadata before installing it
  • Run a pre-install trust check on a package from the MCP marketplace
  • Batch scan and risk-score an inventory of MCP servers in your fleet
  • Assess the trust level of a skill file (SKILL.md) for security posture
  • Scan instruction files for package references and security findings
  • Run SAST code scanning with CWE-based compliance mapping on MCP server code

Install

$ openclaw skills install @msaad00/agent-bom-registry

agent-bom-registry — MCP Server Trust & Security Registry

Look up MCP servers in the 1081-entry server security metadata registry, assess skill file trust, and run pre-install marketplace checks.

Install

pipx install agent-bom
agent-bom mcp scan @modelcontextprotocol/server-brave-search --ecosystem npm
agent-bom mcp scan @modelcontextprotocol/server-filesystem --ecosystem npm

Tools (7)

ToolDescription
registry_lookupLook up MCP server in the 1081-entry security metadata registry
marketplace_checkPre-install trust check with registry cross-reference
fleet_scanBatch registry lookup + risk scoring for MCP server inventories
skill_scanScan instruction files for package refs, trust, and findings
skill_verifyVerify Sigstore provenance for instruction files
skill_trustAssess skill file trust level (5-category analysis)
code_scanSAST scanning via Semgrep with CWE-based compliance mapping

Example Workflows

# Look up a server in the registry
registry_lookup(server_name="brave-search")

# Pre-install trust check
marketplace_check(package="@modelcontextprotocol/server-filesystem")

# Scan instruction files and then assess a specific skill file
skill_scan(path=".")
skill_trust(skill_path="./SKILL.md")

# Batch risk scoring
fleet_scan(servers=["brave-search", "github", "slack"])

MCP Resources

ResourceDescription
registry://serversBrowse the 1081-entry MCP server security metadata registry

Privacy & Data Handling

Registry data is bundled in the package — lookups are in-memory string matches with zero network calls. Skill trust analysis parses content passed as a string argument (no file system access needed).

Verification

  • Source: github.com/msaad00/agent-bom (Apache-2.0)
  • 7,100+ tests with CodeQL + OpenSSF Scorecard
  • No telemetry: Zero tracking, zero analytics

Top skills in this category