Using Polydev with Cline
Get multi-model AI perspectives directly in Cline (VS Code/Cursor extension). When you need different viewpoints on a bug, architecture decision, or code review, Polydev queries multiple AI models in parallel.
Works across all IDEs: Polydev uses the universal Model Context Protocol (MCP) standard. The same MCP server powers Cline, Claude Code, Cursor, Windsurf, and Codex CLI. Just add it to your MCP config and mention "polydev" or "perspectives" in any prompt.
npx polydev-ai@latest
Cline MCP Servers panel with Polydev configured
Install in 60 seconds
1 Install Polydev (requires Node.js):
npm install -g polydev-ai2 Login from any terminal — opens your browser and saves your token automatically:
polydev-ai loginOr get your token manually from polydev.ai/dashboard/mcp-tokens
3 Open Cline settings: Click the gear icon → "MCP Servers" → "Configure"
4 Add Polydev to your Cline MCP config:
{
"mcpServers": {
"polydev": {
"command": "npx",
"args": ["-y", "polydev-ai@latest"],
"timeout": 400
}
}
}If you got your token manually instead of using polydev-ai login, add an env block: "env": { "POLYDEV_USER_TOKEN": "pd_xxx" }
5 Click "Done" and verify Polydev appears in the MCP Servers list with a green indicator
What Polydev adds
MCP Tool
get_perspectives — queries multiple AI models in parallel for diverse viewpoints
Response time
10-40 seconds (parallel queries to multiple providers)
Use cases
Debugging, architecture decisions, code reviews, security analysis
Example: useEffect debugging
In Cline chat, type: Use polydev to help answer: What are common causes of React useEffect infinite loops?
Typing a polydev prompt in Cline
Cline processes the request and queries multiple AI models
How to use it
Just mention "polydev" or "perspectives" in your prompt. Cline's agent will call the get_perspectives MCP tool — the same tool that works in every MCP-compatible IDE:
Debugging
"Use polydev to debug this infinite loop"
Architecture
"Get perspectives on: Redis vs PostgreSQL for caching?"
Code review
"Use polydev to review this API for security issues"
Cline-specific tips
Auto-approve the tool
In MCP Servers settings, enable auto-approve for get_perspectives to skip confirmation prompts.
Works with @file mentions
Combine Polydev with Cline's @file mentions for context-aware multi-model consultation.
Increase timeout
Add "timeout": 400 to your MCP server config. Polydev queries multiple AI models which can take a few minutes for complex prompts.
Auto-Invocation with Custom Instructions
Make Cline automatically consult Polydev when you're stuck. Add this to Cline's Custom Instructions (Settings → Custom Instructions), or create a .clinerules file in your project root:
# Auto-Invoke Polydev for Multi-Model Perspectives
When the user encounters any of these situations, automatically
use the polydev MCP tool (get_perspectives) to consult multiple
AI models before responding:
1. User says "stuck", "confused", "not sure", or "can't figure out"
2. Comparison questions: "Should I use X or Y?"
3. Security or code review requests
4. After 2-3 failed debugging attempts
5. Architecture or design decisions
6. Performance optimization questions
Example: If user says "I'm stuck on this auth bug", call
get_perspectives with the problem context before answering.Tip: The .clinerules file works per-project. For global rules across all projects, use Cline Settings → Custom Instructions.
Troubleshooting
MCP not showing up?
Check JSON syntax in your config file. Ensure proper commas and quotes. Try clicking "Restart Server" in the MCP Servers panel.
Token not found?
Verify your token starts with pd_ and is correctly set in the env section.
npx path issues?
Use the full path in your config. Find it with:
which npxSlow responses?
Multi-model queries take 10-40 seconds since they call multiple APIs in parallel.
Ready to try it?
Free tier: 500 messages/month