mcpField
P
perspectives

perspectives

Local
github.com/polydev-aiAI & Agents0Updated 39w ago

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

  1. 01Query multiple AI models at once
  2. 02Check local CLI status
  3. 03Redetect installed CLIs
  4. 04Send prompts to local CLIs

Use cases

  1. 01Debug code with several model perspectives
  2. 02Review an API for security issues
  3. 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.

mcp.json · Universal config
{
"mcpServers": {
"backspacevenkat-perspectives": {
"command": "npx",
"args": [
"-y",
"polydev-ai"
],
"env": {
"POLYDEV_USER_TOKEN": "<POLYDEV_USER_TOKEN>"
}
}
}
}
Run commandnpx -y polydev-ai
Environment variables to set
POLYDEV_USER_TOKENSecretYour Polydev API token from polydev.ai/dashboard/mcp-tokens

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmpolydev-ai1.8.70

Tools

12

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
promptstringYesThe prompt to get perspectives on
max_tokensintegerNoMaximum tokens per response
user_tokenstringNoPolydev user authentication token (get from dashboard)
temperaturenumberNoTemperature for model responses
max_messagesintegerNoMaximum number of messages to process for tool calls
project_memoryenumNoProject context level - 'none', 'light' (recent files), or 'full' (TF-IDF similarity)none | light | full
project_contextobjectNoProject context for memory retrieval
project_context.excludesarrayNoFile patterns to exclude
project_context.includesarrayNoFile patterns to include
project_context.root_pathstringNoRoot directory path for project

Details

From the project README

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.

npm version SWE-bench Verified License: MIT


Why Polydev?

Stop copy-pasting between ChatGPT, Claude, and Gemini. Get all their perspectives in your IDE with one request.

MetricResult
SWE-bench Verified74.6% Resolve@2
Cost vs Claude Opus62% lower
Response time10-40 seconds

"Different models have different blind spots. Combining their perspectives eliminates yours."


Supported Models

ModelProviderStrengths
GPT 5.2OpenAIReasoning, code generation
Claude Opus 4.5AnthropicAnalysis, nuanced thinking
Gemini 3 ProGoogleMultimodal, large context
Grok 4.1xAIReal-time knowledge, directness

Quick Start

1. Get your free API token

polydev.ai/dashboard/mcp-tokens

TierMessages/MonthPrice
Free1,000$0
Pro10,000$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)
  1. Open Cline settings (gear icon)
  2. Go to "MCP Servers" → "Configure"
  3. 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.

ApproachResolution RateCost/Instance
Claude Haiku (baseline)64.6%$0.18
+ Polydev consultation66.6%$0.24
Resolve@2 (best of both)74.6%$0.37
Claude Opus (reference)74.4%$0.97

Read the full paper →


Available Tools

ToolDescription
get_perspectivesQuery multiple AI models simultaneously
get_cli_statusCheck status of local CLI tools
force_cli_detectionRe-detect installed CLI tools
send_cli_promptSend prompts to local CLIs with fallback

Links

IDE Guides

License

MIT License - see LICENSE for details.


Built by Polydev AI
Multi-model consultation for better code

Comments

Markdown supported

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.