How is this different from connecting Modern Treasury 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 Modern Treasury MCP API changes?

We track the Modern Treasury 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 Modern Treasury 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 Modern Treasury?

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 Modern Treasury MCP server myself?

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

Connect Modern Treasury MCP to your AI agents, securely.

Q: Is Modern Treasury MCP secure?

The server itself exposes 2 tools, and some of them can write to your Modern Treasury 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 Modern Treasury.

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

Get started for free

Get a demo

Try Modern Treasury MCP now

What your agents can ask once Modern Treasury MCP is connected.

Select the tools your AI agents can call

2 tools from the Modern Treasury MCP schema.

Showing 2 tools

search_docsreadQueries the Modern Treasury API and SDK documentation generically, taking a search query, the SDK language to search for, and the amount of detail to return.
executehigh riskRuns TypeScript the agent wrote against the Modern Treasury SDK in a sandbox environment without web or filesystem access. Anything the code returns or prints comes back as the tool result, so this single tool covers the whole payment operations API.

What Modern Treasury MCP exposes

Modern Treasury MCP groups its 2 tools into 2 categories, each with a suggested starting policy.

All 2 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Code Execution	Writing TypeScript against the Modern Treasury SDK and running it in an isolated sandbox, with whatever the code returns or prints coming back as the tool result. This reaches the full API surface, including payment orders, ledgers and ledger entries, counterparties, virtual accounts, expected payments and reconciliation	Write	One tool for the entire API, with no distinction between reading a balance and originating a payment. Approve on the code in the arguments rather than the tool name, and log that code; the sandbox has no web or filesystem access, which bounds the blast radius to the SDK itself
Documentation	Querying the Modern Treasury API and SDK documentation generically, with a language parameter and an adjustable level of detail	Read	Read-only and the right first call: the agent needs the SDK surface before it can write code that compiles, so requiring this ahead of execute reduces guessed method names

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

Modern Treasury MCP	2 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 2 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 Modern Treasury 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.	Modern Treasury MCP2 documented tools in modern-treasury-mcp v4.21.0, built on the code-mode tool scheme. It runs locally over stdio through npx, or remotely with --transport=http using Basic authorization. Credentials are three environment variables: API key, organization ID and webhook key.
Coding assistants	Connection & credentialsper user	Code Execution1 tool
Internal copilots	Tool access policiesdeny by default	Documentation1 tool
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs