
Perspectives
- Updated January 29, 2026
- polydev-ai/perspectives-mcp
Perspectives is a MCP server that queries GPT 5.2, Claude Opus 4.5, Gemini 3, and Grok 4.1 in parallel for comparable answers.
About
Perspectives MCP (published as io.github.backspacevenkat/perspectives) routes one prompt through four frontier models so developers see disagreement before committing to a stack, pricing model, or launch angle. Setup is Polydev-token gated via POLYDEV_USER_TOKEN and stdio npm transport, which keeps secrets in env vars your MCP host already manages. The value is not a single “best” answer but a structured panel for triangulation, especially when you lack a cofounder to argue the other side. Budget for API usage through Polydev and treat outputs as advisory input paired with your own customer evidence.
- Single MCP flow queries GPT 5.2, Claude Opus 4.5, Gemini 3, and Grok 4.1
- Polydev-backed npm package polydev-ai v1.8.70
- Requires POLYDEV_USER_TOKEN from polydev.ai dashboard
- GitHub: polydev-ai/perspectives-mcp
Perspectives by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env POLYDEV_USER_TOKEN=YOUR_POLYDEV_USER_TOKEN polydev-ai -- npx -y polydev-aiAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | polydev-ai |
|---|---|
| Transport | STDIO |
| Auth | Required |
| Last updated | January 29, 2026 |
| Repository | polydev-ai/perspectives-mcp ↗ |
What it does
Run the same product or architecture question against GPT 5.2, Claude Opus 4.5, Gemini 3, and Grok 4.1 in one MCP call before you lock scope.
Who is it for?
Best when you want a cheap “panel of models” during validation and recurring strategic choices.
Skip if: Workflows that must stay on a single vendor for compliance or teams that cannot use Polydev tokens.
What you get
You get side-by-side perspectives in one agent session so you can stress-test decisions before implementation.
- Parallel answers from four named model families in one tool call
- Faster disagreement surfacing before you write plans or code
- Reusable MCP wiring for strategic prompts across journey phases
By the numbers
- Package version 1.8.70
- Models referenced: GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1
- 1 required secret: POLYDEV_USER_TOKEN
README.md
Polydev - 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
Recommended MCP Servers
How it compares
Multi-LLM query MCP, not a code review skill or a single-provider chat integration.
FAQ
Who is Perspectives for?
Developers and small teams who want multiple frontier models on the same question without manual copy-paste.
When should I use Perspectives?
Use it while scoping an MVP and anytime later you need a second, third, and fourth opinion on a non-trivial product decision.
How do I add Perspectives to my agent?
Create a POLYDEV_USER_TOKEN at polydev.ai/dashboard/mcp-tokens, add the stdio npm server polydev-ai to MCP config, and invoke perspectives tools from your host.