Retell AI MCP Server

52 tools. 32 can modify or destroy data without limits.

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

Last updated:

32 can modify or destroy data
20 read-only
52 tools total

Community server · catalogue entry verified 04/07/2026

How to control Retell AI MCP Server ↓

What Retell AI MCP Server exposes to your agents

Read (20) Write / Execute (24) Destructive / Financial (8)
Critical Risk

The most dangerous Retell AI MCP Server tools

32 of Retell AI MCP Server's 52 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Retell AI MCP Server

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

Deny destructive operations
{
  "retell_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
{
  "retell_add_knowledge_base_sources": {
    "limits": [
      {
        "counter": "retell_add_knowledge_base_sources_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "retell_get_agent": {
    "limits": [
      {
        "counter": "retell_get_agent_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Retell AI MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON RETELL AI →

Instant setup, no code required.

All 52 Retell AI MCP Server tools

READ 20 tools
Read retell_get_agent Retrieve the configuration and details of a specific voice agent. Read retell_get_agent_versions Retrieve the version history of an agent. Read retell_get_call Retrieve details of a specific call including transcript, recording URL, duration, and analysis. Read retell_get_chat Retrieve details of a specific chat session. Read retell_get_chat_agent Retrieve details of a specific chat agent. Read retell_get_concurrency Check the current concurrent call limits and usage for your account. Read retell_get_conversation_flow Retrieve a conversation flow configuration. Read retell_get_knowledge_base Retrieve a knowledge base configuration. Read retell_get_llm Retrieve a Retell LLM configuration. Read retell_get_phone_number Retrieve details of a specific phone number. Read retell_get_voice Retrieve details of a specific voice. Read retell_list_agents List all voice agents in your Retell account. Read retell_list_calls List and filter calls with pagination support. Can filter by agent, status, time range, and more. Read retell_list_chat_agents List all chat agents in your account. Read retell_list_chats List all chat sessions with optional filtering. Read retell_list_conversation_flows List all conversation flows. Read retell_list_knowledge_bases List all knowledge bases. Read retell_list_llms List all Retell LLM configurations. Read retell_list_phone_numbers List all phone numbers registered with your Retell account. Read retell_list_voices List all available voices for use with agents.

Related servers

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

Questions about Retell AI MCP Server

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

Yes. The Retell AI MCP Server server exposes 8 destructive tools including retell_delete_agent, retell_delete_call, retell_delete_chat_agent. 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 Retell AI MCP Server? +

The Retell AI MCP Server server has 15 write tools including retell_add_knowledge_base_sources, retell_create_agent, retell_create_chat. 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 Retell AI MCP Server.

How many tools does the Retell AI MCP Server MCP server expose? +

52 tools across 3 categories: Destructive, Read, Write. 20 are read-only. 32 can modify, create, or delete data.

How do I enforce a policy on Retell AI MCP Server? +

Register the Retell AI MCP Server 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 Retell AI MCP Server tool call.

Deterministic rules across all 52 Retell AI MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

52 Retell AI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.