CallMCP — Phone Call MCP Server

List Recent Calls

list_recent_calls

Read-onlyIdempotent

List and search the business's calls, newest first, each with who called (when known) and a short summary of what they wanted. Search by caller phone, by words in the call summary ("water heater", "quote"), and by date window; filters combine. Use get_transcript for the full call.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_recent_calls"
  }
}

Input Schema

Name	Required	Description
`after`	No	Only items at or after this ISO-8601 date or time (optional).
`limit`	No	Max results to return (default 20, max 100)
`phone`	No	Only this caller: any phone format; matches on the last 10 digits (optional).
`query`	No	Words to find in the call summary, e.g. "water heater" (optional).
`before`	No	Only items before this ISO-8601 date or time (optional).
`offset`	No	Zero-based pagination offset (default 0)
`status`	No	Filter by status (optional)
`agent_id`	No	Filter by agent ID (optional)

Output Schema

Name	Required	Description
`calls`	No
`count`	No
`error`	No	Present when success is false
`limit`	No
`offset`	No
`filters`	No
`success`	Yes	Whether the tool completed successfully
`has_more`	No
`next_offset`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds useful behavior beyond that: results are newest-first, each carries caller identity when known, and multiple filters combine rather than override. It omits pagination behavior, but the offset/limit defaults are documented in the 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?

Two sentences, no filler, with the scope and ordering front-loaded and the alternative-tool routing placed at the end where it belongs. Every clause carries information an agent needs.

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?

With an output schema present and rich annotations, the description needs only to frame intent and its gaps are small. It does not mention the status and agent_id filters or pagination, relying on the schema for those, which is reasonable given full coverage but leaves a slight incompleteness for an 8-parameter tool.

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 description coverage is 100%, so baseline is 3. The description adds a genuinely new semantic — that the filters combine — and frames the phone and query parameters in terms of user intent (find calls about a topic), which the schema alone does not convey.

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 (list and search calls) plus the ordering (newest first) and the returned content (caller identity and a short summary). It explicitly contrasts itself with get_transcript, so an agent can distinguish it from the main sibling without opening either 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 clear context for when this is the right tool — searching calls by caller, summary words, or date window — and routes to get_transcript when the full call content is needed. It does not state exclusions against other list_* siblings (e.g. list_leads), but the search-over-calls framing is unambiguous.

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.