Pipeworx AI Model Experiments MCP MCP server

This MCP server allows agents to run the same prompts across many AI models simultaneously to compare outputs, latency, and cost. It provides tools to list available models, estimate costs, create and manage experiments, retrieve results with AI-written summaries, and handle prepaid credits via USDC.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by Pipeworx

MCP endpoint (Streamable HTTP)

https://gateway.pipeworx.io/ai-model-experiments/mcp

Vendor documentation

What you can do with it

List available AI models for experimentation
Estimate costs before running experiments
Run experiments across multiple models simultaneously
Retrieve results and AI-written comparison summaries

Tools advertised by the last live check:

ask_pipeworx
ask_pipeworx_beta
ask_pipeworx_grounded
search_within
deep_research
discover_tools
resolve_entity
compare_entities
subscribe
unsubscribe
list_subscriptions
recent_alerts
entity_profile
recent_changes
validate_claim
company_facts
scan_dependency
bet_research
polymarket_arbitrage
polymarket_edges
polymarket_kalshi_spread
polymarket_fill_risk
polymarket_edge_tracker
kalshi_weather_edge
resolution_audit
resolution_diff
release_calendar_markets
pipeworx_trending
suggest_questions
generate_llms_txt
ai_visibility_check
scan_competitor_ai_presence
pipeworx_feedback
remember
recall
forget
experiment_models
experiment_estimate
experiment_create
experiment_status
experiment_results
experiment_list
experiment_cancel
experiment_topup

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http pipeworx-ai-model-experiments-mcp https://gateway.pipeworx.io/ai-model-experiments/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add pipeworx-ai-model-experiments-mcp --url https://gateway.pipeworx.io/ai-model-experiments/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable pipeworx-ai-model-experiments-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "pipeworx-ai-model-experiments-mcp": {
      "url": "https://gateway.pipeworx.io/ai-model-experiments/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "pipeworx-ai-model-experiments-mcp": {
      "type": "streamableHttp",
      "url": "https://gateway.pipeworx.io/ai-model-experiments/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start pipeworx-ai-model-experiments-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "pipeworx-ai-model-experiments-mcp": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/ai-model-experiments/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http pipeworx-ai-model-experiments-mcp https://gateway.pipeworx.io/ai-model-experiments/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "pipeworx-ai-model-experiments-mcp": {
      "url": "https://gateway.pipeworx.io/ai-model-experiments/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "pipeworx-ai-model-experiments-mcp": {
      "serverUrl": "https://gateway.pipeworx.io/ai-model-experiments/mcp"
    }
  }
}

See all 782

Do you run Pipeworx AI Model Experiments MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing