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

We track the Excalidraw 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 Excalidraw 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 Excalidraw?

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 Excalidraw MCP server myself?

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

Connect Excalidraw MCP to your AI agents, securely.

Q: Is Excalidraw MCP secure?

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

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

Get started for free

Get a demo

Try Excalidraw MCP now

What your agents can ask once Excalidraw MCP is connected.

Select the tools your AI agents can call

2 tools from the Excalidraw MCP schema.

Showing 2 tools

read_mereadReturns a cheat sheet with the element format, colour palettes, coordinate tips and examples. The server expects this to be called before create_view.
create_viewwriteTakes a JSON string of standard Excalidraw elements and renders them as SVG in the client, parsing partial JSON during streaming. After the final render, the SVG is captured as a PNG of up to 512 pixels and sent back into the model's context so it can see the diagram and iterate.

What Excalidraw MCP exposes

Excalidraw 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
Rendering	Taking a JSON string of standard Excalidraw elements and rendering it as SVG in the client, parsing partial JSON while it streams and diffing the result as it updates	Write	It writes nothing outside the conversation, but the rendered diagram is captured as a PNG and pushed back into the model's context, so the call both produces and returns content
Reference	A cheat sheet with the element format, colour palettes, coordinate tips and worked examples	Read	The server expects this to be read before the render tool is used, since the element format is specific and a malformed payload simply fails to draw

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

Excalidraw 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 Excalidraw 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.	Excalidraw MCP2 documented tools in a standalone MCP App server that streams Excalidraw diagrams as SVG. It renders through exportToSvg with morphdom diffing rather than mounting the Excalidraw React canvas, and it holds no state outside the conversation.
Coding assistants	Connection & credentialsper user	Rendering1 tool
Internal copilots	Tool access policiesdeny by default	Reference1 tool
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs