Official FlowchartAI remote MCP connection configuration, OAuth setup, and plugin manifests.
Official FlowchartAI remote MCP connection configuration, OAuth setup, and plugin manifests.
Official connection configuration for FlowchartAI, a hosted remote MCP server for creating and editing native flowcharts.
https://flowchartai.org/api/mcporg.flowchartai/flowchartai version 1.0.0Add the remote URL to an MCP client that supports Streamable HTTP and OAuth. Sign in to FlowchartAI, inspect the requested permissions and approve the connection. Connections can be revoked in the developer dashboard.
{
"mcpServers": {
"flowchartai": {
"type": "http",
"url": "https://flowchartai.org/api/mcp"
}
}
}mcp.json is the Cursor connection configuration; .mcp.json and .claude-plugin/plugin.json provide the Claude Code plugin configuration. Client-specific setup is documented on the product website. These are configuration files, not a local server package. There is no npm install command or Docker image to run.
Create a scoped key in the developer dashboard and configure your client's secret store to send Authorization: Bearer <YOUR_API_KEY>. Never commit a real key into these files. API keys do not create website sessions.
| Tool | Purpose |
|---|---|
get_capabilities | Read formats, execution limits and charging rules |
get_account | Read allowance, scopes and developer budgets |
create_flowchart | Generate and save a native diagram from text or an image |
edit_flowchart | Edit an owned diagram at its expected version |
list_flowcharts | List saved diagrams |
get_flowchart | Read a diagram and its website editor URL |
save_flowchart | Save a native diagram without an AI generation charge |
list_flowchart_versions | Read saved version history |
export_flowchart | Export editable draw.io XML or JSON |
list_tasks | Read durable operation receipts |
get_task | Read one task and its result |
Saved diagrams open in the existing FlowchartAI web editor. PNG and SVG rendering is available there; server-side MCP exports provide draw.io XML and JSON.
A FlowchartAI account is required. AI generation and edits use the existing account allowance or Credits, with per-task spending caps and key/account daily budgets. There is no separate MCP subscription. Read capabilities and account information before spending, obtain the user's authorized max_credits, and keep a stable idempotency key for retries. A cap below the server estimate returns max_credits_too_low and required_credits without generating. Do not raise a cap without the user's approval.
After an uncertain response, read the task receipt or repeat the exact request with the same idempotency key. Do not create another task to recover the same result. Read a diagram's current version before editing it. Platform-funded repairs are not a second user charge.
This MIT-licensed repository contains public connection metadata, manifests, documentation and a product icon. It does not implement or self-host the backend. The application source is maintained separately in tanchaowen84/flowchartai.
The remote service was verified with official MCP SDK 1.32.1: 11 tools, real OAuth/PKCE, account read, rotating refresh, scoped access and revocation. Hosted ChatGPT/Claude web-client account acceptance is separate and was not completed in that verification session.
Manifest checks:
claude plugin validate .Cursor manifests were checked locally with the official cursor/plugin-template validator. The upstream validation script is kept outside this connection repository. Its optional hooks warning is expected because this plugin contains no hooks. Use a recent Claude Code version that supports the plugin validation command.
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add flowchartai --transport http https://flowchartai.org/api/mcp{
"mcpServers": {
"flowchartai": {
"url": "https://flowchartai.org/api/mcp",
"type": "http"
}
}
}code --add-mcp '{"name":"flowchartai","url":"https://flowchartai.org/api/mcp","type":"http"}'Runs as a hosted service. Your client connects over the network and nothing is installed locally.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/flowchartai-mcp to learn what the "FlowchartAI MCP" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
This server doesn't publish a machine-readable tool manifest, and it doesn't expose a public endpoint we could ask. Connect the server locally to see what it exposes.
Paste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/flowchartai-mcp)GitHub's official MCP server for repos, issues and pull requests
Official SpriteFuse hosted OAuth MCP connection configurations and documentation; proprietary
MCP server for the Guard ecosystem — config validation, docs search and live threat detection for
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "flowchartai-mcp" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
GitHub's official MCP server for repos, issues and pull requests
Developer Tools
Official SpriteFuse hosted OAuth MCP connection configurations and documentation; proprietary
Developer Tools
MCP server for the Guard ecosystem — config validation, docs search and live threat detection for
Developer Tools
One email a week. New agents, MCP servers and skills, and what is actually getting traction.