// SCAN REPORT

Retellai

24 tools. 13 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 27 Jun 2026

13 can modify or destroy data

11 read-only

24 tools total

Community server · catalogue entry verified 27/06/2026

How to control Retellai ↓

TOOL MAP

What Retellai exposes to your agents

Read (11) Write / Execute (9) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Retellai tools

Destructive · High delete_agent This tool permanently removes an agent resource with no stated undo capability. Destructive · High delete_call Deletion of call records is an irreversible operation that cannot be undone. Destructive · High delete_phone_number Deleting a phone number is an irreversible action that cannot be undone. Destructive · High delete_retell_llm This tool permanently removes a Retell LLM resource.

13 of Retellai's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Retellai

PolicyLayer is an MCP gateway — it sits between your AI agents and Retellai, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_agent": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_agent": {
    "limits": [
      {
        "counter": "create_agent_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_agent": {
    "limits": [
      {
        "counter": "get_agent_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Retellai — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RETELLAI →

Instant setup, no code required.

FULL CATALOGUE

All 24 Retellai tools

DESTRUCTIVE 4 tools

Destructive delete_agent Deletes a Retell agent Destructive delete_call Deletes a call Destructive delete_phone_number Deletes a phone number Destructive delete_retell_llm Deletes a Retell LLM

EXECUTE 2 tools

Execute create_phone_call Creates a new phone call Execute create_web_call Creates a new web call

WRITE 7 tools

Write create_agent Creates a new Retell agent Write create_phone_number Creates a new phone number Write create_retell_llm Creates a new Retell LLM Write update_agent Updates an existing Retell agent Write update_call Updates an existing call Write update_phone_number Updates a phone number Write update_retell_llm Updates an existing Retell LLM

READ 11 tools

Read get_agent Gets a Retell agent by ID Read get_agent_versions Gets all versions of a Retell agent Read get_call Gets a call by ID Read get_phone_number Gets details of a specific phone number Read get_retell_llm Gets a Retell LLM by ID Read get_voice Gets details of a specific voice Read list_agents Lists all Retell agents Read list_calls Lists all calls Read list_phone_numbers Lists all Retell phone numbers Read list_retell_llms Lists all Retell LLMs Read list_voices Lists all available Retell voices

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Retellai

Can an AI agent delete data through the Retellai MCP server? +

Yes. The Retellai server exposes 4 destructive tools including delete_agent, delete_call, delete_phone_number. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Retellai? +

The Retellai server has 7 write tools including create_agent, create_phone_number, create_retell_llm. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Retellai.

How many tools does the Retellai MCP server expose? +

24 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Retellai? +

Register the Retellai MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Retellai tool call.

Deterministic rules across all 24 Retellai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RETELLAI →

Instant setup, no code required.

24 Retellai tools catalogued and risk-classified — across an index of 43,000+ MCP servers.