# delimit_vault_search

A read tool on the Delimit MCP server.

Agent View of the PolicyLayer registry record for `delimit_vault_search`. HTML page: https://policylayer.com/tools/delimit/delimit-vault-search

## Facts

- Tool: `delimit_vault_search`
- 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_vault_search",
    "arguments": {}
  }
}
```

## Why delimit_vault_search is rated Low

The 'search' suffix strongly indicates this is a Read operation that queries or retrieves data. However, confidence is moderate (0.7) rather than high because the description is empty and 'vault' could imply access to sensitive authentication or secrets data, elevating the severity from low to medium despite the read-only nature.

From the tool's own definition: "Tool name includes 'search' which typically indicates data retrieval without modification. The 'vault' prefix suggests access to stored data or secrets management."

## Use case

AI agents call delimit_vault_search 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_vault_search": {}
  }
}
```

## 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