How is this different from connecting Telnyx MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Telnyx MCP API changes?

We track the Telnyx MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Telnyx tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Telnyx?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Telnyx MCP server myself?

No. TrustGate connects to the Telnyx MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Telnyx directly.

Connect Telnyx MCP to your AI agents, securely.

Q: Is Telnyx MCP secure?

The server itself exposes 6 tools, and some of them can write to your Telnyx account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Telnyx.

One secured endpoint for every Telnyx call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Telnyx MCP now

What your agents can ask once Telnyx MCP is connected.

Select the tools your AI agents can call

6 tools from the Telnyx MCP schema.

Showing 6 tools

list_api_endpointsreadLists or searches every endpoint in the Telnyx API, optionally filtered by a partial name, resource, operation or tag.
get_api_endpoint_schemareadReturns the schema for one endpoint, which is what invoke_api_endpoint's arguments must match. Telnyx requires this to be called before invoking anything.
invoke_api_endpointhigh riskInvokes any endpoint in the Telnyx API by name with an argument object. Annotated destructive and open-world: safety depends entirely on which endpoint is chosen, and agents are told to surface the side-effect risk before calling a write or destructive one.
open_number_intelligencereadOpens the Number Intelligence app for phone number lookup, validation and enrichment workflows, backed by Telnyx Number Lookup.
open_usage_cost_explorerreadOpens the Usage and Cost Explorer app, covering balance, usage reports, billing groups and guarded billing controls.
open_voice_monitorreadOpens the Voice Monitor app for read-only active-call monitoring, call timelines, call status and recording discovery.

What Telnyx MCP exposes

Telnyx MCP groups its 6 tools into 2 categories, each with a suggested starting policy.

All 6 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
API Gateway	Listing and searching every endpoint in the Telnyx API, fetching an endpoint's schema, and invoking it with arguments matching that schema	Read / Write	The discovery pair is safe; invoke_api_endpoint is the whole API and is annotated destructive and open-world. Enforce the schema-first sequence and gate invocation by the endpoint name in the arguments, not by the tool name
MCP Apps	Opening three interactive apps: phone number lookup, validation and enrichment; balance, usage reports and billing groups; and active-call monitoring with call timelines, status and recording discovery	Read	The openers themselves are read-only no-ops. Each app is a separate MCP endpoint with its own tools and its own Bearer auth, so what the app can do is not bounded by the opener

Connect Telnyx MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Telnyx
Find Telnyx in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Telnyx MCP or block it. You allow the exact tools each agent can call, one by one.

Telnyx MCP	6 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 6 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Telnyx MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Telnyx MCP6 documented tools at api.telnyx.com/v2/mcp over streamable HTTP. Authentication is a Bearer API key; the server card states there is no OAuth or PKCE in v1. The MCP Apps layer is marked experimental and each app is a separate endpoint.
Coding assistants	Connection & credentialsper user	API Gateway3 tools
Internal copilots	Tool access policiesdeny by default	MCP Apps3 tools
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs