CallMCP — Phone Call MCP Server

Answer A Number From Your Own Twilio Account

attach_own_twilio_number

Have a voice agent answer calls on ONE number from the business's own connected Twilio account, calls only. Reads only that number. dry_run defaults to true and changes nothing: it returns would_change (the number's VoiceUrl and VoiceMethod) and the fields left unchanged. With dry_run false, only that number's VoiceUrl and VoiceMethod change; its text settings (SmsUrl, SmsMethod, SmsApplicationSid, StatusCallback) are read back afterwards and must be unchanged, so a texting setup another service runs on the account keeps working. Refuses a number a Twilio app answers, and a number another service answers unless replace_existing_voice is true. Uses one plan line. Requires admin role.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "phone_number": "<phone_number>",
      "agent_id": "<agent_id>"
    },
    "name": "attach_own_twilio_number"
  }
}

Input Schema

Name	Required	Description
`dry_run`	No	Default true: report what would change and write nothing.
`agent_id`	Yes	Agent that should answer the calls.
`business_id`	No	Business ID (optional only when the token can access exactly one business).
`phone_number`	Yes	E.164 number on the business's own connected Twilio account.
`replace_existing_voice`	No	Allow replacing another service that answers calls on this number today.

Output Schema

Name	Required	Description
`after`	No
`error`	No	Present when success is false
`before`	No
`dry_run`	No
`success`	Yes	Whether the tool completed successfully
`unchanged`	No
`business_id`	No
`would_change`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite annotations only flagging readOnlyHint=false and destructiveHint=false, the description discloses the exact write surface (only VoiceUrl and VoiceMethod), that text settings are read back and must be unchanged, dry_run defaulting to true with a would_change preview, and refusal conditions. This is behavior an agent could not infer from annotations and materially affects safe invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and scope, then dry_run semantics before write semantics — a sensible order. The sentences are dense and clause-heavy (the read-back guarantee clause especially), so it is efficient but slightly taxing to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with an output schema, the description covers the preview shape (would_change with VoiceUrl/VoiceMethod), the failure modes, permission and billing side effects. Nothing an agent needs to call it safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds real meaning beyond the schema: dry_run defaults to true and writes nothing, and replace_existing_voice gates overriding another service that answers calls today. business_id is not discussed, but it is optional and documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Have a voice agent answer calls on ONE number from the business's own connected Twilio account, calls only.' The 'own connected Twilio account' framing implicitly distinguishes it from platform-number siblings like attach_number/buy_number, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete use conditions and guardrails: requires admin role, consumes one plan line, refuses numbers answered by a Twilio app, and refuses numbers owned by another service unless replace_existing_voice is true. It does not explicitly route the agent to an alternative tool (e.g., attach_number for platform numbers), which keeps it short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CallMCP — Phone Call MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.