CallMCP — Phone Call MCP Server

Create Agent

create_agent

Create a new KaiCalls agent — the secretary that answers this business’s calls (the live voice agent plus KaiCalls records) — with a system prompt, greeting, voice, and model. Its starting settings are saved as version 1 and each later change as a new version (list_config_versions); rollback_config restores a version's greeting, voice, prompt, model and summary/scoring. Compliance: KaiCalls automatically applies state-aware AI-disclosure and consent handling to every agent it provisions, and flags high-risk business categories for extra review.

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": {
      "business_id": "<business_id>",
      "name": "<name>"
    },
    "name": "create_agent"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Agent display name.
`model`	No	Language model selection: { provider, model, temperature } (optional).
`voice`	No	Raw voice selection: { provider, voiceId } (optional).
`metadata`	No	Extra KaiCalls metadata to store (optional).
`business_id`	Yes	Business ID to create the agent under.
`first_message`	No	Spoken greeting (optional). Leave it out to use the industry intake greeting, which opens on the caller's need.
`system_prompt`	No	The agent's inbound system prompt (optional). Leave it out to start on the business's industry intake script, the same one a signup gets.
`vertical_pack`	No	Setup pack id (optional; inferred from the business when left out). One of: hvac, plumbing, electrical, general-contractor, garage-door, general-contractors, handyman, landscaping, moving, pest-control, pool-service, cleaning, roofing, personal-injury, family-law, insurance-claims, criminal-defense, eviction-law, legal-family-law, immigration-law, legal-personal-injury, party-rentals, tent-rentals, event-equipment, equipment-rental, restaurant-orders, catering, auto-repair, mobile-mechanic, towing, dive-shop, fitness, wellness-recovery, chiropractic-pt, chiropractic, dental, medical-practice, med-spa, mental-health-therapy, veterinary, photography, salon-barbershop, financial-services, insurance-agency, tax-accounting, property-management, real-estate.
`voice_catalog_id`	No	Preferred: a curated catalog id from list_voices (optional).

Output Schema

Name	Required	Description
`agent`	No
`error`	No	Present when success is false
`script`	No
`success`	Yes	Whether the tool completed successfully
`warnings`	No
`compliance`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 12, 2026

changedInput schema / properties / vertical_pack / description

Previous value: -"Setup pack id, e.g. 'personal-injury' (optional; inferred from the business when left out)."New value: +"Setup pack id (optional; inferred from the business when left out). One of: hvac, plumbing, electrical, general-contractor, garage-door, general-contractors, handyman, landscaping, moving, pest-control, pool-service, cleaning, roofing, personal-injury, family-law, insurance-claims, criminal-defense, eviction-law, legal-family-law, immigration-law, legal-personal-injury, party-rentals, tent-rentals, event-equipment, equipment-rental, restaurant-orders, catering, auto-repair, mobile-mechanic, towing, dive-shop, fitness, wellness-recovery, chiropractic-pt, chiropractic, dental, medical-practice, med-spa, mental-health-therapy, veterinary, photography, salon-barbershop, financial-services, insurance-agency, tax-accounting, property-management, real-estate."

First observedNov 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Adds real behavior beyond the annotations: version-1 creation semantics, the fact that each subsequent edit forks a new version, what rollback_config restores, and that compliance (state-aware AI disclosure and consent) is applied automatically plus high-risk category flagging. Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), and the description does not contradict them. It omits per-call failure modes or limits, and return shape is covered by the output schema.

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

Conciseness5/5

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

Three sentences, each doing distinct work: what gets created, how versioning behaves, and what compliance is automatic. The core action is front-loaded, and the em-dash parenthetical is dense but informative rather than filler.

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?

For a 9-parameter creation tool with nested objects, full schema coverage, annotations, and an output schema, the description supplies the missing conceptual layer — lifecycle/versioning and automatic compliance. What remains uncovered is environmental: permission/ownership requirements on business_id and any duplicate-name behavior. Return values need not be explained given the output 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 description coverage is 100%, so the schema already documents all nine parameters including the optional-omission behavior for first_message, system_prompt, and vertical_pack. The description reinforces the prompt/greeting/voice/model concept but adds no syntax, format, or constraint detail beyond the schema (e.g., no model/voice object shape guidance). Baseline 3 is appropriate.

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

Purpose5/5

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

States a specific verb and resource ('Create a new KaiCalls agent') and disambiguates what an agent is ('the secretary that answers this business's calls — the live voice agent plus KaiCalls records'), including the configurable facets (system prompt, greeting, voice, model). An agent can distinguish this from update_agent_config, get_agent_config, or rollback_config without opening any schema.

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 creation-time context: starting settings become version 1 and later changes become new versions, pointing at list_config_versions and rollback_config for the lifecycle. Also explains defaulting behavior when optional fields are omitted (industry intake greeting/script, vertical_pack inferred from the business). It stops short of explicit when-not-to-use or prerequisites such as business ownership/permission requirements.

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.