About perspectives
perspectives is an MCP server for IDE users that queries GPT 5.2, Claude Opus 4.5, Gemini 3, and Grok 4.1 at once. It also provides tools for detecting local CLIs and sending them prompts.
Key features
- 01Query multiple AI models at once
- 02Check local CLI status
- 03Redetect installed CLIs
- 04Send prompts to local CLIs
Use cases
- 01Debug code with several model perspectives
- 02Review an API for security issues
- 03Compare database or caching options
MCP support
The MCP server exposes get_perspectives, get_cli_status, force_cli_detection, and send_cli_prompt tools to clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y polydev-aiPOLYDEV_USER_TOKENSecretYour Polydev API token from polydev.ai/dashboard/mcp-tokensLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
12Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| prompt | string | Yes | The prompt to get perspectives on |
| max_tokens | integer | No | Maximum tokens per response |
| user_token | string | No | Polydev user authentication token (get from dashboard) |
| temperature | number | No | Temperature for model responses |
| max_messages | integer | No | Maximum number of messages to process for tool calls |
| project_memory | enum | No | Project context level - 'none', 'light' (recent files), or 'full' (TF-IDF similarity)none | light | full |
| project_context | object | No | Project context for memory retrieval |
| project_context.excludes | array | No | File patterns to exclude |
| project_context.includes | array | No | File patterns to include |
| project_context.root_path | string | No | Root directory path for project |
Details
From the project READMEPolydev - Multi-Model AI Perspectives
Get unstuck faster. Query GPT 5.2, Claude Opus 4.5, Gemini 3, and Grok 4.1 simultaneously — one API call, four expert opinions.
Why Polydev?
Stop copy-pasting between ChatGPT, Claude, and Gemini. Get all their perspectives in your IDE with one request.
| Metric | Result |
|---|---|
| SWE-bench Verified | 74.6% Resolve@2 |
| Cost vs Claude Opus | 62% lower |
| Response time | 10-40 seconds |
"Different models have different blind spots. Combining their perspectives eliminates yours."
Supported Models
| Model | Provider | Strengths |
|---|---|---|
| GPT 5.2 | OpenAI | Reasoning, code generation |
| Claude Opus 4.5 | Anthropic | Analysis, nuanced thinking |
| Gemini 3 Pro | Multimodal, large context | |
| Grok 4.1 | xAI | Real-time knowledge, directness |
Quick Start
1. Get your free API token
polydev.ai/dashboard/mcp-tokens
| Tier | Messages/Month | Price |
|---|---|---|
| Free | 1,000 | $0 |
| Pro | 10,000 | $19/mo |
2. Install in your IDE
Claude Code
claude mcp add polydev -- npx -y polydev-ai@latest
Then set your token:
export POLYDEV_USER_TOKEN="pd_your_token_here"
Or add to ~/.claude.json:
{
"mcpServers": {
"polydev": {
"command": "npx",
"args": ["-y", "polydev-ai@latest"],
"env": {
"POLYDEV_USER_TOKEN": "pd_your_token_here"
}
}
}
}
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"polydev": {
"command": "npx",
"args": ["-y", "polydev-ai@latest"],
"env": {
"POLYDEV_USER_TOKEN": "pd_your_token_here"
}
}
}
}
Windsurf
Add to your MCP configuration:
{
"mcpServers": {
"polydev": {
"command": "npx",
"args": ["-y", "polydev-ai@latest"],
"env": {
"POLYDEV_USER_TOKEN": "pd_your_token_here"
}
}
}
}
Cline (VS Code)
- Open Cline settings (gear icon)
- Go to "MCP Servers" → "Configure"
- Add the same JSON config as above
OpenAI Codex CLI
Add to ~/.codex/config.toml:
[mcp_servers.polydev]
command = "npx"
args = ["-y", "polydev-ai@latest"]
[mcp_servers.polydev.env]
POLYDEV_USER_TOKEN = "pd_your_token_here"
[mcp_servers.polydev.timeouts]
tool_timeout = 180
session_timeout = 600
Usage
Natural Language
Just mention "polydev" or "perspectives" in your prompt:
"Use polydev to debug this infinite loop"
"Get perspectives on: Should I use Redis or PostgreSQL for caching?"
"Use polydev to review this API for security issues"
MCP Tool
Call the get_perspectives tool directly:
{
"tool": "get_perspectives",
"arguments": {
"prompt": "How should I optimize this database query?",
"user_token": "pd_your_token_here"
}
}
Example Response
🤖 Multi-Model Analysis
┌─ GPT 5.2 ────────────────────────────────────────
│ The N+1 query pattern is causing performance issues.
│ Consider using eager loading or batch queries...
└──────────────────────────────────────────────────
┌─ Claude Opus 4.5 ────────────────────────────────
│ Looking at the execution plan, the table scan on
│ `users` suggests a missing index on `email`...
└──────────────────────────────────────────────────
┌─ Gemini 3 ───────────────────────────────────────
│ The query could benefit from denormalization for
│ this read-heavy access pattern...
└──────────────────────────────────────────────────
┌─ Grok 4.1 ───────────────────────────────────────
│ Just add an index. The real problem is you're
│ querying in a loop - fix that first.
└──────────────────────────────────────────────────
✅ Consensus: Add index on users.email, fix N+1 query
💡 Recommendation: Use eager loading with proper indexing
Research
Our approach achieves 74.6% on SWE-bench Verified (Resolve@2), matching Claude Opus at 62% lower cost.
| Approach | Resolution Rate | Cost/Instance |
|---|---|---|
| Claude Haiku (baseline) | 64.6% | $0.18 |
| + Polydev consultation | 66.6% | $0.24 |
| Resolve@2 (best of both) | 74.6% | $0.37 |
| Claude Opus (reference) | 74.4% | $0.97 |
Available Tools
| Tool | Description |
|---|---|
get_perspectives | Query multiple AI models simultaneously |
get_cli_status | Check status of local CLI tools |
force_cli_detection | Re-detect installed CLI tools |
send_cli_prompt | Send prompts to local CLIs with fallback |
Links
- Website: polydev.ai
- Dashboard: polydev.ai/dashboard
- npm: npmjs.com/package/polydev-ai
- Research: SWE-bench Paper
IDE Guides
License
MIT License - see LICENSE for details.
Built by Polydev AI
Multi-model consultation for better code
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.