How is this different from connecting Swagger Functional Testing 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 Swagger Functional Testing MCP API changes?

We track the Swagger Functional Testing 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 Swagger Functional Testing 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 Swagger Functional Testing?

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 Swagger Functional Testing MCP server myself?

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

Connect Swagger Functional Testing MCP to your AI agents, securely.

Q: Is Swagger Functional Testing MCP secure?

The server itself exposes 11 tools, and some of them can write to your Swagger Functional Testing 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 Swagger Functional Testing.

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

Get started for free

Get a demo

Try Swagger Functional Testing MCP now

What your agents can ask once Swagger Functional Testing MCP is connected.

Select the tools your AI agents can call

11 tools from the Swagger Functional Testing MCP schema.

Showing 11 tools

swagger_list_testsreadLists all API tests available in the Swagger Functional Testing account, returning test IDs usable with swagger_run_test or passable to swagger_create_suite. Annotated read-only and idempotent.
swagger_get_test_statusreadReturns the status of a test execution as running, passed or failed, with its run time and a per-step breakdown. Intended to be polled after a run until it settles. Annotated read-only and idempotent.
swagger_create_testwriteCreates an API test from a set of request steps, each with a URL and optionally an HTTP method, request body, headers, redirect handling and assertions on expected status-code ranges and response body. Every step sets a baseUrl that is extracted into a shared parameter. Annotated write, not destructive, not idempotent.
swagger_run_testhigh riskRuns a single API test, sending every request step it defines to its target host. Execution is asynchronous and returns an executionId rather than a result. SmartBear annotates this openWorld, meaning it reaches outside the product.
swagger_get_test_historyreadRetrieves the execution history for a given test in your Swagger Functional Testing workspace.
swagger_list_suitesreadLists all test suites in the workspace, each with the slug that identifies it for the other suite tools. Annotated read-only and idempotent.
swagger_get_suite_statusreadReturns a suite execution's overall status as pending, canceled, passed or failed, whether the run has finished, and a per-test breakdown with pass or fail, runtime, step count and a map of failed step indices to error messages. Annotated read-only and idempotent.
swagger_list_suite_executionsreadLists all executions for a given test suite with their timings, for reviewing execution history. Annotated read-only and idempotent.
swagger_create_suitewriteCreates a test suite from one or more ordered blocks of existing tests. Blocks always run one after another, tests within a block run sequentially unless the block sets parallel, and a block can set up to three automatic retry attempts for failed tests. It optionally saves a tunnel agent override for future runs. Annotated write, not destructive, not idempotent.
swagger_run_suitehigh riskRuns a test suite, firing every request in every block, optionally overriding the saved tunnel agent for this run. Execution is asynchronous and returns an executionId. SmartBear annotates this openWorld, meaning it reaches outside the product.
swagger_cancel_suite_executionhigh riskCancels an ongoing suite execution, for stopping a long-running or accidentally triggered run. The cancelled execution is preserved in run history with status canceled. Annotated write and destructive by SmartBear.

What Swagger Functional Testing MCP exposes

Swagger Functional Testing MCP groups its 11 tools into 2 categories, each with a suggested starting policy.

All 11 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Suites	Listing suites with the slug that identifies each one, creating a suite from ordered blocks of existing tests with optional parallel execution within a block and up to three automatic retries, running a suite with an optional tunnel agent override, polling its overall status with a per-test breakdown of pass, fail, runtime, step count and failed step indices, listing its execution history, and cancelling a run in progress	Read / Write	swagger_run_suite is marked openWorld and fires every request in every block, optionally through a tunnel agent into a private network, so the agent name is as important to log as the suite. Cancelling is vendor-marked destructive but preserves the run in history as canceled
Tests	Listing the API tests in the workspace, creating one from a set of request steps each with a URL, method, body, headers, redirect handling and status-code or response-body assertions, running a single test asynchronously, polling its execution status with a per-step breakdown, and retrieving its paginated run history with failure detail	Read / Write	swagger_create_test stores a set of HTTP requests and swagger_run_test sends them, so the pair is an arbitrary-request primitive rather than a test runner. Review the step URLs and methods at creation, since that is where the destination and the verb are fixed

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

Swagger Functional Testing MCP	11 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 11 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 Swagger Functional Testing 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.	Swagger Functional Testing MCP11 tools in the Functional Testing toolset of SmartBear's MCP server, which also bundles BearQ, BugSnag, Reflect, Swagger Portal and Studio, Contract Testing, QMetry, QTM4J, Zephyr and Collaborator. Functional Testing is available only through the local npm package, not the hosted servers. Each product is enabled by supplying its API token and disabled by leaving it blank, and MCP_CLIENTS takes a comma-separated list to load only the products in use. Every tool publishes four annotations: readOnly, destructive, openWorld and idempotent.
Coding assistants	Connection & credentialsper user	Suites6 tools
Internal copilots	Tool access policiesdeny by default	Tests5 tools
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs