Render MCP

Connect your AI assistant to Rynko Render using the Model Context Protocol (MCP). Manage templates and generate documents through natural conversation.

Server URL: https://api.rynko.dev/api/mcp-documents

Authentication: Personal Access Token (PAT)

Supported AI Tools

Tool	Config File	Top-Level Key
Claude Desktop	`claude_desktop_config.json`	`mcpServers`
Cursor	`.cursor/mcp.json`	`mcpServers`
Windsurf	`~/.codeium/windsurf/mcp_config.json`	`mcpServers`
VS Code	`.vscode/mcp.json`	`servers`
Zed	`~/.config/zed/settings.json`	`context_servers`
Claude Code	CLI	`--transport http`

Features

Natural Language Templates - Describe what you need and let AI create templates
Cross-Environment Access - Work across all your environments with a single token
Draft-Only Safety - Templates created via MCP are drafts until you publish them
Document Generation - Preview and generate documents directly from chat
Data Import - Parse Excel/CSV files and auto-map columns to template variables
Audit Trail - All MCP operations are logged for security and compliance

Quick Start

Step 1: Generate a Personal Access Token

Log in to your Rynko Dashboard
Go to Settings → Personal Access Tokens
Click Create Token
Enter a label (e.g., "Claude Desktop" or "Cursor")
Select expiry (max 30 days)
Click Create and copy the token immediately — it won't be shown again

warning

Keep your PAT secure. Anyone with this token can access your templates across all environments.

Step 2: Configure Your AI Tool

One-Click Install (Recommended)

Open Claude Desktop → Settings → Extensions
Search for "Rynko" and click Install
Enter your Personal Access Token when prompted
Done! Start chatting about your documents.

Via Connectors (OAuth)

Open Claude Desktop → Settings → Connectors
Click Add Custom Connector
Paste the server URL:
```
https://api.rynko.dev/api/mcp-documents
```
OAuth authorization completes automatically — sign in with your Rynko account when prompted

info

Connectors with OAuth require a Claude Pro, Max, Team, or Enterprise plan.

Via mcp-remote Proxy (PAT)

Claude Desktop does not support custom headers for HTTP transport. Use the mcp-remote proxy to bridge the remote server to stdio:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "rynko": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.rynko.dev/api/mcp-documents",
        "--header",
        "Authorization:${RYNKO_PAT}"
      ],
      "env": {
        "RYNKO_PAT": "Bearer pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

Via stdio npm Package (PAT)

{
  "mcpServers": {
    "rynko": {
      "command": "npx",
      "args": ["-y", "@rynko/mcp-server"],
      "env": {
        "RYNKO_USER_TOKEN": "pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

claude mcp add --transport http rynko https://api.rynko.dev/api/mcp-documents \
  --header "Authorization: Bearer pat_xxxxxxxxxxxxxxxx"

Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "rynko": {
      "url": "https://api.rynko.dev/api/mcp-documents",
      "headers": {
        "Authorization": "Bearer pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

Or use the stdio npm package:

{
  "mcpServers": {
    "rynko": {
      "command": "npx",
      "args": ["-y", "@rynko/mcp-server"],
      "env": {
        "RYNKO_USER_TOKEN": "pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "rynko": {
      "serverUrl": "https://api.rynko.dev/api/mcp-documents",
      "headers": {
        "Authorization": "Bearer pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

Or use the stdio npm package:

{
  "mcpServers": {
    "rynko": {
      "command": "npx",
      "args": ["-y", "@rynko/mcp-server"],
      "env": {
        "RYNKO_USER_TOKEN": "pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

warning

Do not add MCP servers to settings.json — VS Code will show the error: "MCP servers should not be configured in user settings." Use the dedicated mcp.json file instead.

Add to .vscode/mcp.json (workspace) or open via Cmd/Ctrl + Shift + P → "MCP: Open User Configuration" (global):

{
  "servers": {
    "rynko": {
      "type": "http",
      "url": "https://api.rynko.dev/api/mcp-documents",
      "headers": {
        "Authorization": "Bearer pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

tip

Use input variables to avoid hardcoding your token:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "rynko-token",
      "description": "Rynko Personal Access Token",
      "password": true
    }
  ],
  "servers": {
    "rynko": {
      "type": "http",
      "url": "https://api.rynko.dev/api/mcp-documents",
      "headers": {
        "Authorization": "Bearer ${input:rynko-token}"
      }
    }
  }
}

Key Difference

VS Code uses "servers" as the top-level key, while other editors use "mcpServers". Don't mix them up!

Add to ~/.config/zed/settings.json (global) or .zed/settings.json (project):

{
  "context_servers": {
    "rynko": {
      "command": "npx",
      "args": ["-y", "@rynko/mcp-server"],
      "env": {
        "RYNKO_USER_TOKEN": "pat_xxxxxxxxxxxxxxxx"
      }
    }
  }
}

warning

Zed updated its MCP config format in v0.218+. The old nested format ("command": { "path": "npx", ... }) still works but the flat format shown above is now recommended.

note

When opening a project with .zed/settings.json containing MCP configs, Zed will prompt you to trust the worktree before running the server.

Replace pat_xxxxxxxxxxxxxxxx with your Personal Access Token, then restart your AI tool.

When to use remote vs. local (npm)

Remote (HTTP): No Node.js required, simpler setup, works behind corporate proxies
Local (stdio via npm): Works offline, slightly lower latency, no network dependency

Step 3: Verify Connection

After restarting your AI tool, you should see "Rynko" in your available MCP servers. Try asking:

"List my templates"
"What environments do I have access to?"

Available Tools

Environment Tools

Tool	Description
`list_environments`	List all environments you have access to
`get_environment`	Get details of a specific environment

Template Tools

Tool	Description
`list_templates`	List templates in an environment
`get_template`	Get template details and schema
`create_draft_template`	Create a new draft template
`update_draft_template`	Update a draft template
`validate_schema`	Validate template schema before creating
`get_schema_reference`	Get the template schema documentation

Data Tools

Tool	Description
`parse_data_file`	Parse Excel or CSV data to JSON
`map_variables`	Auto-map data columns to template variables

Generation Tools

Tool	Description
`preview_template`	Generate a preview document
`generate_document`	Generate a production document
`get_job_status`	Check document generation status

Asset Tools

Tool	Description
`list_assets`	List uploaded assets in an environment
`upload_asset`	Upload an image or file for use in templates

Integration Tools

Tool	Description
`get_sdk_examples`	Get SDK code examples for Node.js, Python, Java, or REST API

tip

Ask your AI assistant "How do I generate PDFs from my Node.js app?" — it will call get_sdk_examples to return working code with install instructions.

Example Conversations

Creating a New Template

You: Create an invoice template for my consulting business with company logo, client details, line items table, and payment terms.

AI: I'll create an invoice template for you. First, let me check your environments...

[AI uses list_environments, then create_draft_template]

I've created a draft invoice template in your "Production" environment. It includes:

Header with logo placeholder and company name

Client details section

Line items table with quantity, description, rate, and amount

Subtotal, tax, and total calculations

Payment terms footer

Would you like me to generate a preview?

Generating Documents from Data

You: I have a spreadsheet with customer data. Can you generate invoices for each customer?

AI: Of course! Please share the spreadsheet file.

[You attach customers.xlsx]

AI: [Uses parse_data_file] I found 15 customers. Let me map these to your invoice template... [Uses map_variables]

The mapping looks good:

Name → customer.name (95% confidence)

Amount → invoice.total (90% confidence)

Due Date → invoice.dueDate (85% confidence)

Should I generate the invoices?

Security & Permissions

30-Day Max Expiry: PATs expire automatically to limit exposure
SHA-256 Hashing: Tokens are stored as hashes, not plain text
Revocable: Instantly revoke tokens from your dashboard
Draft-Only: Templates created via MCP are always saved as drafts — AI cannot publish to production
Audit Logging: All MCP operations are logged in your project's activity feed

Tier Limits

Feature	Free	Starter	Growth	Scale
Templates	Unlimited	Unlimited	Unlimited	Unlimited
Environments	1	2	5	Unlimited
Document Generation	50/mo	600/mo	4,000/mo	12,000/mo
PAT Creation	1	3	10	Unlimited

info

Template previews do not consume your document quota.

Environment Variables (npm package)

Variable	Required	Description
`RYNKO_USER_TOKEN`	Yes	Your Personal Access Token (starts with `pat_`)
`RYNKO_API_URL`	No	Custom API URL (default: `https://api.rynko.dev/api`)

Troubleshooting

"Invalid token" Error

Verify the token starts with pat_
Check if the token has expired (max 30 days)
Generate a new token from your dashboard

"Environment not found" Error

Ensure you have access to the environment
Your role must be EDITOR or ADMIN to create/modify templates

AI Tool Not Connecting

Check your config file path and JSON syntax
Ensure npx is available in your PATH (for stdio)
Restart your AI tool completely
Check the AI tool's MCP logs for errors

NPM Package

# Install globally
npm install -g @rynko/mcp-server

# Or run directly
RYNKO_USER_TOKEN=pat_xxx npx @rynko/mcp-server

Package: @rynko/mcp-server

Related: Flow MCP | AI Toolkit | Templates

Supported AI Tools​

Features​

Quick Start​

Step 1: Generate a Personal Access Token​

Step 2: Configure Your AI Tool​

One-Click Install (Recommended)​

Via Connectors (OAuth)​

Via mcp-remote Proxy (PAT)​

Via stdio npm Package (PAT)​

Step 3: Verify Connection​

Available Tools​

Environment Tools​

Template Tools​

Data Tools​

Generation Tools​

Asset Tools​

Integration Tools​

Example Conversations​

Creating a New Template​

Generating Documents from Data​

Security & Permissions​

Tier Limits​

Environment Variables (npm package)​

Troubleshooting​

"Invalid token" Error​

"Environment not found" Error​

AI Tool Not Connecting​

NPM Package​

Supported AI Tools

Features

Quick Start

Step 1: Generate a Personal Access Token

Step 2: Configure Your AI Tool

One-Click Install (Recommended)

Via Connectors (OAuth)

Via mcp-remote Proxy (PAT)

Via stdio npm Package (PAT)

Step 3: Verify Connection

Available Tools

Environment Tools

Template Tools

Data Tools

Generation Tools

Asset Tools

Integration Tools

Example Conversations

Creating a New Template

Generating Documents from Data

Security & Permissions

Tier Limits

Environment Variables (npm package)

Troubleshooting

"Invalid token" Error

"Environment not found" Error

AI Tool Not Connecting

NPM Package