How is this different from connecting AssemblyAI 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 AssemblyAI MCP API changes?

We track the AssemblyAI 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 AssemblyAI 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 AssemblyAI?

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 AssemblyAI MCP server myself?

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

Connect AssemblyAI MCP to your AI agents, securely.

Q: Is AssemblyAI MCP secure?

The server itself exposes 5 tools, and some of them can write to your AssemblyAI 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 AssemblyAI.

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

Get started for free

Get a demo

Try AssemblyAI MCP now

What your agents can ask once AssemblyAI MCP is connected.

Select the tools your AI agents can call

5 tools from the AssemblyAI MCP schema.

Showing 5 tools

submit_transcriptwriteStarts an async transcription of a public audio or video URL and returns a transcript_id and status immediately. Accepts the full async transcription parameter surface: prompting, language detection, speech models, diarization, guardrails (PII redaction, profanity filtering, content safety), inline Speech Understanding and webhooks.
get_transcriptreadFetches the current state of a transcript, with full results once status is completed. Agents poll this roughly every 3 seconds. Output renders as labeled text sections plus raw fields in structuredContent.
understand_transcriptwriteRuns Speech Understanding on an already-completed transcript, covering translation, speaker identification, custom formatting, chaptered summarization and action items, without re-submitting the audio.
summarize_transcriptwriteProduces a freeform or custom-prompt summary of a completed transcript via the LLM Gateway. Styles are bullets, paragraph, headline, action_items or custom.
delete_transcripthigh riskPermanently deletes a transcript and its data. Irreversible, and intended only on explicit user request.

What AssemblyAI MCP exposes

AssemblyAI MCP groups its 5 tools into 3 categories, each with a suggested starting policy.

All 5 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Transcription	Starting an async transcription of a public audio or video URL and fetching its state and full results	Read / Write	Guardrails live in submit_transcript's parameters: redact_pii, filter_profanity and content_safety. Set them at submit time, because they cannot be applied afterwards
Speech Understanding	Running translation, speaker identification, custom formatting, chaptered summarization and action items on an already-completed transcript, plus freeform or custom-prompt summaries	Read / Write	Both route through the LLM Gateway and cost credits per call; request the features inline at submit time when the need is known up front
Lifecycle	Permanently deleting a transcript and its data	Read / Write	Irreversible, and the server's own documentation says to call it only on explicit user request

Connect AssemblyAI 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 AssemblyAI
Find AssemblyAI 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 AssemblyAI MCP or block it. You allow the exact tools each agent can call, one by one.

AssemblyAI MCP	5 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 5 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 AssemblyAI 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.	AssemblyAI MCP5 documented tools. Tool names are permanent under the server's additive-only contract, and new inputs are always optional.
Coding assistants	Connection & credentialsper user	Transcription2 tools
Internal copilots	Tool access policiesdeny by default	Speech Understanding2 tools
Workflow automations	Request & response inspectioninline	Lifecycle1 tool
Compatible MCP clients	Activity monitoringalerts and logs