SIP trunking, SMS, MMS, Call Control and Telephony Data Services.
Full LLM thinking from the 4-phase benchmark pipeline.
MCP server at https://api.telnyx.com/v2/mcp (endpoint source: mcp_manifest)
2/2 tests passed
| Test | Endpoint | Status | Latency |
|---|---|---|---|
| mcp_initialize | POST https://api.telnyx.com/v2/mcp | 200 | 153ms |
| mcp_tools_list | POST https://api.telnyx.com/v2/mcp | 200 | 122ms |
{
"overall": 78,
"dimensions": {
"token_efficiency": 7.5,
"first_try_success": 8.0,
"response_parseability": 9.0,
"error_clarity": 6.5,
"doc_quality": 8.5,
"auth_simplicity": 7.5,
"latency": 9.5,
"consistency": 8.0
},
"pricing_normalized": {},
"issues": [
"Only initialize and tools/list were exercised; tools/call requires an API key we did not supply, so first_try_success, error_clarity, and consistency are inferred from schema quality rather than observed behavior.",
"tools/list response_preview is truncated, so the full tool catalog and meta-tool (get_api_endpoint_schema / invoke_api_endpoint) design could not be fully evaluated.",
"Meta-tool pattern (schema-then-invoke) adds a round trip and extra tokens per real API call, reducing end-to-end token efficiency for agents.",
"Auth requires an API key as Bearer token for tools/call, a soft barrier for agents without provisioned credentials."
],
"recommendations": [
"Return full error bodies with the JSON-RPC error code, a human-readable message, and a remediation hint when tools/call is invoked without a valid Bearer token, so agents can self-correct.",
"Document the invoke_api_endpoint flow and required Authorization header explicitly in tool descriptions so an agent can chain get_api_endpoint_schema -> invoke_api_endpoint on the first try.",
"Consider collapsing the schema-then-invoke pattern into higher-level typed tools for common Telnyx endpoints to cut token cost and round trips.",
"Ensure all tool responses are strict JSON with stable fields across calls to maximize parseability and consistency."
]
}Show your live agent-readiness score on your own site. Free, no auth — it updates as your score changes.
<a href="https://prowl.world/service/telnyx-api">
<img src="https://prowl.world/badge/telnyx-api.svg" height="56" alt="Agent-readiness on Prowl">
</a>
See operational metrics, LLM evaluations, agent readiness, and more.
Open in Dashboard