Mermaid Chart for AI agents

Mermaid Chart validates Mermaid diagram syntax and renders it as SVG for interactive preview and iteration, without needing a separate diagramming tool. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Design and imagesNo authMCP + RESTmermaidchart.com
AUDIT LOG · MERMAID CHARTPOLICY: acme-support
09:41:07 · claude · u_8f2read
mermaid_chart.validate_and_render_mermaid_diagram
Validate and render mermaid diagram✓ allowed · 212ms
EVERY MERMAID CHART CALL, ON THE RECORD
01 · USE CASES

What agents do in Mermaid Chart.

01

Render a flowchart from syntax

Validate and render a Mermaid flowchart definition into an SVG diagram for review.

02

Check syntax, no publishing

Validate Mermaid syntax before sharing a diagram, catching errors without publishing anything or touching the source document.

03

Preview a diagram before embedding

Render a diagram to preview it in context before embedding it into a document.

02 · ACTIONS

1 Mermaid Chart actions, graded by risk.

Every Mermaid Chart action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

1

Look things up. Allowed by default.

  • mermaid_chart.validate_and_render_mermaid_diagram
    Validate and render mermaid diagram

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Mermaid Chart in three steps.

  1. 01Your users connect Mermaid ChartThey add their Mermaid Chart no auth on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Mermaid Chart through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('mermaid_chart', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Mermaid Chart connects.

Mermaid Chart needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.

The same Mermaid Chart connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
No auth
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Mermaid Chart from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Mermaid Chart and Arc0, answered.

Q01

Can I use Mermaid Chart with Claude, ChatGPT or Cursor?

Yes. Connect Mermaid Chart to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Mermaid Chart actions you allow.

Q02

How do users connect Mermaid Chart?

Mermaid Chart needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.

Q03

Which Mermaid Chart actions can my agent take?

1 in total: 1 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Mermaid Chart?

Yes. Allow read actions and deny writes in the Mermaid Chart policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Mermaid Chart too?

Yes. The same Mermaid Chart connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Mermaid Chart into your agent.

Your users connect Mermaid Chart once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan