# get_retell_llm

Get details of a Retell LLM response engine (prompt, model, tools). WHEN TO USE: - Inspect current prompt/model before update_retell_llm - Confirm which prompt an agent will use before a call - Debug why an agent said the wrong thing COMMON MISTAKES: - Looking at the agent only; the actual call instructions live in the Retell LLM - Editing a different LLM than the one returned by get_agent.response_engine.llm_id ERROR RECOVERY: - 401: API key is missing or invalid → configure_retell_api_key - 404: llm_id not found → get_agent/list_retell_llms and retry RELATED TOOLS: - get_agent: Find response_engine.llm_id for an agent - update_retell_llm: Change the prompt/model - list_retell_llms: Browse available LLM configs RETURNS: llm_id, general_prompt, begin_message, model, model_temperature, general_tools, timestamps.

Agent View of the PolicyLayer registry record for `get_retell_llm`. HTML page: https://policylayer.com/tools/freshdesk/get-retell-llm

## Facts

- Tool: `get_retell_llm`
- Server: Freshdesk (`@mindstone-engineering/mcp-server-freshdesk`) — https://policylayer.com/tools/freshdesk.md
- Install: `npx -y @mindstone-engineering/mcp-server-freshdesk`
- Homepage: git+https://github.com/nspr-io/mcp-servers.git
- 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": "get_retell_llm",
    "arguments": {}
  }
}
```

## Why get_retell_llm is rated Low

This tool retrieves and inspects details about an existing Retell LLM configuration (prompt, model, tools). It has no side effects and performs only data retrieval. The documented use cases confirm it is diagnostic/informational in nature. Severity is low because inspection of configuration data poses minimal risk compared to tools that execute, modify, or delete resources.

From the tool's own definition: "The tool name is 'get_retell_llm' and the description explicitly states it is used to 'Get details of a Retell LLM response engine' with use cases such as 'Inspect current prompt/model', 'Confirm which prompt', and 'Debug'."

## Use case

AI agents call get_retell_llm to retrieve information from Freshdesk 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 Freshdesk:

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

## Other tools on Freshdesk (421)

- `cancel_runway_task` — Destructive — https://policylayer.com/tools/freshdesk/cancel-runway-task.md
- `delete_custom_voice` — Destructive — https://policylayer.com/tools/freshdesk/delete-custom-voice.md
- `delete_email` — Destructive — https://policylayer.com/tools/freshdesk/delete-email.md
- `delete_event` — Destructive — https://policylayer.com/tools/freshdesk/delete-event.md
- `delete_file` — Destructive — https://policylayer.com/tools/freshdesk/delete-file.md
- `delete_library_item` — Destructive — https://policylayer.com/tools/freshdesk/delete-library-item.md
- `delete_list_item` — Destructive — https://policylayer.com/tools/freshdesk/delete-list-item.md
- `opus_cancel_scheduled_post` — Destructive — https://policylayer.com/tools/freshdesk/opus-cancel-scheduled-post.md
- `opus_delete_collection` — Destructive — https://policylayer.com/tools/freshdesk/opus-delete-collection.md
- `opus_remove_clip_from_collection` — Destructive — https://policylayer.com/tools/freshdesk/opus-remove-clip-from-collection.md
- `outreach_disconnect_account` — Destructive — https://policylayer.com/tools/freshdesk/outreach-disconnect-account.md
- `remove_freshdesk_account` — Destructive — https://policylayer.com/tools/freshdesk/remove-freshdesk-account.md
- `remove_zendesk_account` — Destructive — https://policylayer.com/tools/freshdesk/remove-zendesk-account.md
- `unenrol_talentlms_user` — Destructive — https://policylayer.com/tools/freshdesk/unenrol-talentlms-user.md
- `apple_shortcuts_run` — Execute — https://policylayer.com/tools/freshdesk/apple-shortcuts-run.md
- `browser_authenticate` — Execute — https://policylayer.com/tools/freshdesk/browser-authenticate.md
- `browser_back` — Execute — https://policylayer.com/tools/freshdesk/browser-back.md
- `browser_click` — Execute — https://policylayer.com/tools/freshdesk/browser-click.md
- `browser_close` — Execute — https://policylayer.com/tools/freshdesk/browser-close.md
- `browser_fill` — Execute — https://policylayer.com/tools/freshdesk/browser-fill.md
- `browser_forward` — Execute — https://policylayer.com/tools/freshdesk/browser-forward.md
- `browser_hover` — Execute — https://policylayer.com/tools/freshdesk/browser-hover.md
- `browser_navigate` — Execute — https://policylayer.com/tools/freshdesk/browser-navigate.md
- `browser_press_key` — Execute — https://policylayer.com/tools/freshdesk/browser-press-key.md
- `browser_scroll` — Execute — https://policylayer.com/tools/freshdesk/browser-scroll.md
- `browser_select` — Execute — https://policylayer.com/tools/freshdesk/browser-select.md
- `browser_type` — Execute — https://policylayer.com/tools/freshdesk/browser-type.md
- `browser_wait` — Execute — https://policylayer.com/tools/freshdesk/browser-wait.md
- `character_performance` — Execute — https://policylayer.com/tools/freshdesk/character-performance.md
- `create_phone_call` — Execute — https://policylayer.com/tools/freshdesk/create-phone-call.md
- …and 391 more: https://policylayer.com/tools/freshdesk.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=freshdesk · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/freshdesk