CallMCP — Phone Call MCP Server

Send Call Transcripts to a Webhook

request_transcript_webhook

DestructiveIdempotent

Create or update a webhook that receives the business's completed-call events (which can include transcripts) at a URL the business controls. Needs webhook_url and the owner's confirmed approval because call data leaves KaiCalls. A new webhook's signing secret is returned once. Returns needs_user_input, needs_approval, pending_approval, executed, denied or unsupported; only executed means the change was made.

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": {
      "webhook_url": "<webhook_url>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "request_transcript_webhook"
  }
}

Input Schema

Name	Required	Description
`id`	No	Optional: an existing webhook to update.
`actor`	No	Do not set. Kept for older clients; the signed-in connection identifies you.
`events`	No	Events to send. Default ['call.completed'].
`reason`	No	Why the change is being made; kept in the audit log.
`dry_run`	No	Check access, inputs and approval without making the change.
`authority`	No	Do not set. It cannot approve a change: the owner approves through review_url or by being signed in.
`is_active`	No	Optional: false to save it switched off.
`source_ref`	No	Optional reference for the request, such as a ticket or automation run ID.
`business_id`	No	Business ID. Required when the token can reach more than one business.
`description`	No	Optional label for the webhook.
`webhook_url`	Yes	HTTPS URL that receives the events.
`idempotency_key`	Yes	Required to make the change. Repeating a key returns the first outcome instead of running the change again.
`queue_for_approval`	No	When approval is missing, create a pending approval the owner can accept in the dashboard instead of returning needs_approval.

Output Schema

Name	Required	Description
`code`	No
`error`	No	Present when success is false
`intent`	No
`result`	No
`status`	No
`message`	No
`success`	Yes	Whether the tool completed successfully
`summary`	No
`approval`	No
`request_id`	No
`risk_level`	No
`business_id`	No
`missing_fields`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 12, 2026

changedInput schema / properties / actor / description

Previous value: -"Who is asking: { type: agent|human|system|integration, id, display_name }."New value: +"Do not set. Kept for older clients; the signed-in connection identifies you."

changedInput schema / properties / authority / description

Previous value: -"How the owner approved this exact change: { mode: 'human_confirmed', confirmed_by, confirmed_at, confirmation_ref }. Without it the result is needs_approval and nothing changes."New value: +"Do not set. It cannot approve a change: the owner approves through review_url or by being signed in."

First observedNov 12, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Adds real context beyond the annotations: data egress off-platform, mandatory owner confirmation, a one-time signing secret, and the fact that only an 'executed' outcome means the change landed. Annotations already flag destructiveness, so this is a meaningful supplement rather than the full burden.

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?

Three tight sentences, front-loaded with the action and the egress/approval constraint, then the outcome contract. No filler, though the outcome enumeration is dense in a single clause.

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

Completeness4/5

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

A 13-parameter nested mutation with an output schema, and the description still covers the essentials an agent needs: approval gating, the one-time secret, and which status indicates success. Remaining details (business_id scoping, events defaults, dry_run) are adequately handled by the schema.

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

Parameters3/5

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

Schema coverage is 100%, so every parameter including idempotency_key, dry_run and queue_for_approval is already documented in the schema. The description only reinforces webhook_url and the approval requirement, adding little parameter-level meaning beyond the structured fields.

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 pair and resource: create-or-update a webhook that receives completed-call events at a business-controlled URL. The upsert framing plus the transcript mention distinguishes it from get_webhook/delete_webhook, 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 Guidelines3/5

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

Explains the precondition (webhook_url plus owner approval because call data leaves KaiCalls), which implies when to use it, but gives no explicit when-not guidance or named alternative for cases like reading or removing an existing webhook.

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.