twilio-call-data-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TWILIO_AUTH_TOKEN | Yes | Your Twilio Auth Token. Required to start the server. | |
| TWILIO_ACCOUNT_SID | Yes | Your Twilio Account SID. Required to start the server. | |
| TWILIO_WORKSPACE_SID | No | Your Twilio TaskRouter Workspace SID. Required for agent tools. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_callsA | Search and filter Twilio call records by date range, phone number, direction, status, minimum duration, or agent. Returns rows plus a pagination cursor. Duration fields are labeled with their source and measurement definition — CDR duration (ring to hangup) and TaskRouter talk time (agent audio open) are never conflated. |
| get_callA | Get full detail for a single call by SID, including child legs. Both CDR duration (ring to hangup) and TaskRouter talk time (agent audio open) are returned with explicit source labels. |
| get_recordingA | Get recording metadata for a call: signed URL with expiry, duration, and transcript if available. Never returns audio bytes. |
| list_agentsC | List the TaskRouter worker roster with each agent's current activity status. |
| get_agent_activityA | Get activity history and reservation history for a single TaskRouter worker over a time window. Includes summary statistics with explicitly labeled duration sources. |
| call_summaryA | Aggregate call data by day, agent, or queue over a date range. Returns counts, talk time, and abandonment rate. Duration fields always carry their source label — CDR and TaskRouter numbers are never mixed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct resource and action: searching calls, getting call detail, retrieving recording metadata, listing agents, getting agent activity, and aggregating summaries. There is no overlap between tools; even the two agent-related tools are clearly separated by current status versus historical activity.
Most tools follow a consistent verb_noun pattern (search_calls, get_call, get_recording, list_agents, get_agent_activity). The one outlier is call_summary, which drops the verb and uses a noun phrase instead of something like summarize_calls. This is a minor deviation that does not impede readability.
Six tools is within the ideal 3-15 range and each tool serves a clear purpose in the call data exploration and analytics domain. The count feels well-scoped without being bloated or too thin.
The tool set covers the full read-only lifecycle for Twilio call data: search, retrieve details, retrieve recordings, list agents, retrieve agent activity, and generate summaries. There are no obvious gaps for the stated purpose of analyzing call data; the domain is fully represented.