The server itself exposes 8 tools, and some of them can write to your AWS 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 AWS.

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

We track the AWS 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 AWS 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 AWS?

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 AWS MCP server myself?

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

Connect AWS MCP to your AI agents, securely.

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

Get started for free

Get a demo

Try AWS MCP now

What your agents can ask once AWS MCP is connected.

Select the tools your AI agents can call

8 tools from the AWS MCP schema.

Showing 8 tools

aws___search_documentationreadSearch across all AWS documentation, including API references, best practices, and service guides.
aws___read_documentationreadRetrieve and convert AWS documentation pages to markdown format.
aws___retrieve_skillreadRetrieve domain-specific expertise for a particular AWS domain.
aws___list_regionsreadList the AWS regions available to the account.
aws___get_regional_availabilityreadCheck regional availability of AWS services, APIs, and CloudFormation resources.
aws___get_tasksreadRetrieve the status of tasks started through the server.
aws___get_presigned_urlreadGenerate a presigned URL for an AWS resource.
aws___run_scripthigh riskExecute Python code in a sandboxed environment with AWS API access.

What AWS MCP exposes

AWS MCP groups its 8 tools into 2 categories, each with a suggested starting policy.

All 8 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Knowledge	Documentation search, service guides, skills, regions and availability	Read	Allow documentation searches
API	Authenticated AWS API calls, sandboxed scripts, presigned URLs and task status	Read / Write	Scope IAM credentials; approve any call that changes infrastructure

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

AWS MCP	8 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 8 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 AWS 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.	AWS MCP8 documented tools.
Coding assistants	Connection & credentialsper user	Knowledge5 tools
Internal copilots	Tool access policiesdeny by default	API3 tools
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs