MCP server

Ai Model Experiments

io.github.pipeworx-io/ai-model-experiments

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…

Website Source

At a glance

Type

MCP server

Publisher

pipeworx.io (verified by the MCP Registry)

Status

Working at last check

Tools

50

Token cost

About 28,311 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.ai-model-experiments]
url = "https://gateway.pipeworx.io/ai-model-experiments/mcp"

Gemini CLI

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

Cursor

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

VS Code

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

Antigravity

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

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"ai-model-experiments","server_url":"https://gateway.pipeworx.io/ai-model-experiments/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"ai-model-experiments","server_url":"https://gateway.pipeworx.io/ai-model-experiments/mcp"}

Tools

• experiment_cancel ~115 tokens
  Cancel a running experiment: pending cells are skipped (not billed); in-flight cells finish and bill. Example: experiment_cancel({ experiment_id: "..." })
• experiment_create ~619 tokens
  Model Lab: run one prompt across many AI models at once and compare their outputs, cost, and latency side by side. Create and start an experiment: run each prompt against each model (× reps), collecting output, tokens, latency, and billed cost per cell. PREPAID: requires Pipeworx credit balance ≥ ma
• experiment_estimate ~385 tokens
  Dry-run cost estimate for an experiment BEFORE creating it — cell count and estimated billed cost range (at our 1.5× pricing) for prompts × models × reps. Free to call, no side effects, does not need credit balance. Same spec shape as experiment_create. Example: experiment_estimate({ prompts: ["Summ
• experiment_list ~86 tokens
  List your experiments, newest first, with status and spend. Example: experiment_list({ limit: 10 })
• experiment_models ~287 tokens
  List AI models available for experiments (about 300 across Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Qwen and more), with context window and OUR per-token prices (provider cost × 1.5 — what experiments actually bill). Filter by name/vendor search, minimum context, or max price. Use the ret
• experiment_results ~203 tokens
  Results of an experiment: per-model aggregates (mean latency, tokens, total billed cost, error rate), per-cell outputs, and the AI-written summary comparing how the models differed (if enabled). Use include_outputs:false for aggregates only. Example: experiment_results({ experiment_id: "..." })
• experiment_status ~140 tokens
  Progress of an experiment: cell counts by state (pending/running/ok/error/skipped), spend so far vs cap, and whether it is complete. Poll this after experiment_create (every few seconds). Example: experiment_status({ experiment_id: "..." })
• experiment_topup ~173 tokens
  How to add prepaid credits for experiments (and your current balance). Payment is x402 — USDC on Base, paid in-band by any wallet-equipped agent: POST https://gateway.pipeworx.io/credits/topup?amount_usd=10 responds HTTP 402 with payment requirements; retry with PAYMENT-SIGNATURE to settle and the c

Browse

• Claude tools
• GitHub tools
• Payments
• GitHub and code hosting
• Calling other AI models
• Travel and flights

Related MCP servers

• AI PM Lab
  Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.
• Jean — Molecular Biology & Genomics
  Validated molecular biology tools: cloning, primers, CRISPR, Sanger, alignment, qPCR, phylogenetics
• Susurration
  A playground built for AI agents: run a flock, leave verified traces, propose exhibits. Be curious.
• Basis
  Crypto market data, 200 indicators, order flow and a chart link. No account, no API key.
• Tmdb
  TMDB v3 MCP.
• Synchronity
  Shop connected e-commerce stores: search, compare, cart, and checkout with buyer approval.
• fnlowl
  Read and manage fnlowl widgets, leads, email sequences and analytics from an AI assistant.
• IA-QA — 130+ QA & Dev Tools for AI Agents
  130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.pipeworx-io/ai-model-experiments.svg)](https://aptlynx.net/servers/io.github.pipeworx-io/ai-model-experiments)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents