# delimit_security_audit

A read tool on the Delimit MCP server.

Agent View of the PolicyLayer registry record for `delimit_security_audit`. HTML page: https://policylayer.com/tools/delimit/delimit-security-audit

## Facts

- Tool: `delimit_security_audit`
- Server: Delimit (`delimit-cli`) — https://policylayer.com/tools/delimit.md
- Install: `npx -y delimit-cli`
- Homepage: https://github.com/delimit-ai/delimit
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "delimit_security_audit",
    "arguments": {}
  }
}
```

## Why delimit_security_audit is rated Low

Audit tools typically retrieve and report on existing state without modifying data. The name indicates passive security review rather than active intervention. However, the empty description prevents higher confidence assessment. Classified as Read with low severity since even if misused, audit queries have minimal blast radius compared to write/execute/destructive actions.

From the tool's own definition: "Tool name 'delimit_security_audit' strongly suggests inspection or review of security logs/status, consistent with audit functions which are typically read-only queries. The description is empty, which lowers confidence."

## Use case

AI agents call delimit_security_audit to retrieve information from Delimit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Delimit:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "delimit_security_audit": {}
  }
}
```

## Other tools on Delimit (206)

- `delimit_intel_dataset_freeze` — Destructive — https://policylayer.com/tools/delimit/delimit-intel-dataset-freeze.md
- `delimit_ledger_auto_cancel_stale` — Destructive — https://policylayer.com/tools/delimit/delimit-ledger-auto-cancel-stale.md
- `delimit_release_rollback` — Destructive — https://policylayer.com/tools/delimit/delimit-release-rollback.md
- `delimit_secret_revoke` — Destructive — https://policylayer.com/tools/delimit/delimit-secret-revoke.md
- `delimit_build_loop` — Execute — https://policylayer.com/tools/delimit/delimit-build-loop.md
- `delimit_build_loop_daemon` — Execute — https://policylayer.com/tools/delimit/delimit-build-loop-daemon.md
- `delimit_daemon_run` — Execute — https://policylayer.com/tools/delimit/delimit-daemon-run.md
- `delimit_deploy_build` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-build.md
- `delimit_deploy_npm` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-npm.md
- `delimit_deploy_plan` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-plan.md
- `delimit_deploy_publish` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-publish.md
- `delimit_deploy_rollback` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-rollback.md
- `delimit_deploy_site` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-site.md
- `delimit_deploy_verify` — Execute — https://policylayer.com/tools/delimit/delimit-deploy-verify.md
- `delimit_executor` — Execute — https://policylayer.com/tools/delimit/delimit-executor.md
- `delimit_gov_run` — Execute — https://policylayer.com/tools/delimit/delimit-gov-run.md
- `delimit_story_build` — Execute — https://policylayer.com/tools/delimit/delimit-story-build.md
- `delimit_content_queue` — Other — https://policylayer.com/tools/delimit/delimit-content-queue.md
- `delimit_control` — Other — https://policylayer.com/tools/delimit/delimit-control.md
- `delimit_cost_alert` — Other — https://policylayer.com/tools/delimit/delimit-cost-alert.md
- `delimit_design_component_library` — Other — https://policylayer.com/tools/delimit/delimit-design-component-library.md
- `delimit_ledger_auto_close_external` — Other — https://policylayer.com/tools/delimit/delimit-ledger-auto-close-external.md
- `delimit_ledger_groom` — Other — https://policylayer.com/tools/delimit/delimit-ledger-groom.md
- `delimit_quickstart` — Other — https://policylayer.com/tools/delimit/delimit-quickstart.md
- `delimit_resource_drivers` — Other — https://policylayer.com/tools/delimit/delimit-resource-drivers.md
- `delimit_semver` — Other — https://policylayer.com/tools/delimit/delimit-semver.md
- `delimit_social_accounts` — Other — https://policylayer.com/tools/delimit/delimit-social-accounts.md
- `delimit_social_daemon` — Other — https://policylayer.com/tools/delimit/delimit-social-daemon.md
- `delimit_social_target` — Other — https://policylayer.com/tools/delimit/delimit-social-target.md
- `delimit_ventures` — Other — https://policylayer.com/tools/delimit/delimit-ventures.md
- …and 176 more: https://policylayer.com/tools/delimit.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=delimit · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/delimit