# Agent Bom Enforce

> Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".

- Skill: `leoyeai-openclaw-master-skills/agent-bom-enforce` (Agent Skill)
- Install (CLI): `npx skillmds@latest add leoyeai-openclaw-master-skills/agent-bom-enforce`
- Raw SKILL.md: https://api.skillmd.com/api/skills/leoyeai-openclaw-master-skills/agent-bom-enforce/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- License: Apache-2.0
- Author: LeoYeAI (https://skillmd.com/u/leoyeai-openclaw-master-skills)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/leoyeai-openclaw-master-skills/agent-bom-enforce

---


# agent-bom-enforce — Runtime Policy Enforcement

Enforces security policies on MCP tool calls and blocks dangerous operations
at runtime. Runs a local proxy that intercepts MCP calls and evaluates them
against policy-as-code rules.

## Install

```bash
pipx install agent-bom
agent-bom proxy              # start enforcement proxy
agent-bom policy apply policy.yaml  # apply a policy file
agent-bom policy check       # check current policy status
```

## When to Use

- "block risky calls" / "block dangerous MCP calls"
- "apply policy" / "enforce policy"
- "proxy" / "MCP proxy"
- "runtime protection"
- "policy enforcement"
- "intercept MCP calls"

## Commands

```bash
# Start the enforcement proxy
agent-bom proxy

# Apply a policy file
agent-bom policy apply policy.yaml

# Check current policy status
agent-bom policy check
```

## Example Policy File

```yaml
# policy.yaml
rules:
  - id: block-shell-exec
    description: Block shell execution tool calls
    match:
      tool: "bash|shell|exec|run_command"
    action: block
    severity: critical

  - id: require-path-allowlist
    description: Restrict filesystem access to allowed paths
    match:
      tool: "read_file|write_file|list_directory"
      args.path:
        not_starts_with: ["/home/", "/tmp/"]
    action: block
    severity: high
```

## Guardrails

- IMPORTANT: Do not start the proxy or apply policies without explicit user confirmation — enforcement changes how MCP calls are processed.
- Confirm the policy file contents with the user before applying.
- Do not enable proxy mode autonomously — always ask the user first.
- Audit logs are written locally only; no data is transmitted externally.
- This skill has `disable-model-invocation: true` — do not auto-run enforcement actions.