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

We track the Paddle 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 Paddle 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 Paddle?

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 Paddle MCP server myself?

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

Connect Paddle MCP to your AI agents, securely.

Q: Is Paddle MCP secure?

The server itself exposes 3 tools, and some of them can write to your Paddle 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 Paddle.

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

Get started for free

Get a demo

Try Paddle MCP now

What your agents can ask once Paddle MCP is connected.

“Using paddle-sandbox, set up three subscription plans with monthly and annual prices and a 14-day trial”
“Using paddle-live, investigate the failed payment for this customer and tell me whether it's recurring”
“Generate a transaction_line_items report for the past 6 months and flag pricing anomalies across regions”

Select the tools your AI agents can call

3 tools from the Paddle MCP schema.

Showing 3 tools

searchreadLooks up Paddle API methods by name or description, returning the method path, parameters and response shape so the agent knows how to call it.
executehigh riskRuns a JavaScript async function that chains one or more Paddle API calls in a single invocation. Destructive operations are flagged with a destructiveHint annotation and a warning field on the response, but nothing blocks them. Variables do not persist between calls.
report_missing_toolwriteLets the agent flag a missing capability so Paddle can prioritize it. It does not call the Paddle API.

What Paddle MCP exposes

Paddle MCP groups its 3 tools into 2 categories, each with a suggested starting policy.

All 3 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Code Mode	Looking up Paddle API methods by name or description with their parameters and response shape, and running a JavaScript async function that chains one or more Paddle API calls in a single invocation	Read / Write	execute is the whole API behind one tool name: pricing, subscriptions, refunds, adjustments and webhooks all arrive as the same call. Enable ask-permission mode in the client and review each execute before it runs; variables do not persist between calls
Feedback	Reporting a missing capability back to the Paddle team so it can be prioritized	Write	Does not call the Paddle API or touch account data; it sends a note to Paddle. Low risk, but it is still an outbound message from the organization

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

Paddle MCP	3 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 3 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 Paddle 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.	Paddle MCP3 documented tools covering the full Paddle Billing API. Paddle hosts a separate server per environment: live at mcp.paddle.com (OAuth or API key) and sandbox at sandbox-mcp.paddle.com (API key only). Keys are environment-bound and a mismatch fails authentication.
Coding assistants	Connection & credentialsper user	Code Mode2 tools
Internal copilots	Tool access policiesdeny by default	Feedback1 tool
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs