Ai Model Experiments
NPM · @PIPEWORX/MCP-AI-MODEL-EXPERIMENTS · 2 COMPONENTS
AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…
Available components
Last scanned (6 hours ago)
Scores higher than 81% of npm servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-ai-model-experiments). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 5 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability74
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1146 tokens (~143/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- Package version: 0.2.0 → 0.2.1 functional
- 29 Oct 26 81
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@pipeworx/mcp-ai-model-experiments@0.2.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | pipeworx-io/mcp-ai-model-experiments |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/pipeworx-io/mcp-ai-model-experiments/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 3587875459 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:65cc8a44b6a4044ae6dfc76aae194fb701e322b99704b60d50e4b7bf422c83ce37f6ba2ba38fb02b60a76ce15e065a6724a091ba5bfa74eee8d758f5f |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
experiment_cancel ~50
Cancel a running experiment: pending cells are skipped (not billed); in-flight cells finish and bill. Example: experiment_cancel({ experiment_id: "..." })
| Name | Type | Req | Description |
|---|---|---|---|
| experiment_id | string | yes | From experiment_create |
No output schema declared.
No examples provided.
experiment_create ~343
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 ≥ max_spend_usd (top up via experiment_topup); bills actual provider cost × 1.5 with a $0.10 minimum per experiment. ASYNC: returns experiment_id immediately — execution starts within ~1 minute; poll experiment_status until complete, then call experiment_results. Do NOT wait synchronously. Set summary:false to skip the AI-written model-comparison summary. Example: experiment_create({ name: "tone test", prompts: ["Rewrite formally: ..."], models: ["anthropic/claude-haiku-4.5", "openai/gpt-5-mini"], reps: 2, max_spend_usd: 2 })
| Name | Type | Req | Description |
|---|---|---|---|
| max_spend_usd | number | yes | REQUIRED hard spend cap in USD for this experiment (max 100). Execution stops when reached. |
| models | array | yes | Model ids from experiment_models (max 12) |
| name | string | – | Short experiment name |
| params | object | – | Optional {system, temperature, max_tokens (default 512)} |
| prompts | array | yes | Prompts to test (max 20) |
| reps | number | – | Repetitions per prompt×model for variance, 1-5 (default 1) |
| summary | boolean | – | AI-written comparison of the models' outputs when the run completes (default true) |
No output schema declared.
No examples provided.
experiment_estimate ~194
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: ["Summarize: ..."], models: ["anthropic/claude-sonnet-4.5", "openai/gpt-5"], reps: 2 })
| Name | Type | Req | Description |
|---|---|---|---|
| models | array | yes | Model ids from experiment_models (max 12) |
| params | object | – | Optional {system, temperature, max_tokens} |
| prompts | array | yes | Prompts to test (max 20) |
| reps | number | – | Repetitions per prompt×model, 1-5 (default 1) |
| summary | boolean | – | Include the AI-written comparison summary stage (default true) |
No output schema declared.
No examples provided.
experiment_list ~43
List your experiments, newest first, with status and spend. Example: experiment_list({ limit: 10 })
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max experiments (default 20) |
No output schema declared.
No examples provided.
experiment_models ~181
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 returned model ids in experiment_create. Example: experiment_models({ search: "claude", min_context: 100000 })
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max models to return (default 30) |
| max_price_per_mtok | number | – | Max billed OUTPUT price in USD per million tokens |
| min_context | number | – | Minimum context window in tokens |
| search | string | – | Substring match on model id or name, e.g. "claude", "gpt", "llama" |
No output schema declared.
No examples provided.
experiment_results ~94
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: "..." })
| Name | Type | Req | Description |
|---|---|---|---|
| experiment_id | string | yes | From experiment_create |
| include_outputs | boolean | – | Include full model outputs per cell (default true) |
No output schema declared.
No examples provided.
experiment_status ~71
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: "..." })
| Name | Type | Req | Description |
|---|---|---|---|
| experiment_id | string | yes | From experiment_create |
No output schema declared.
No examples provided.
experiment_topup ~112
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 credits land instantly. Example: experiment_topup({})
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | – | Intended top-up amount in USD (1-500) — echoed into the instructions |
No output schema declared.
No examples provided.
How do I install the Ai Model Experiments MCP server?
Ai Model Experiments runs locally as an npm package, launched with npx -y @pipeworx/mcp-ai-model-experiments. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @pipeworx/mcp-ai-model-experiments
claude mcp add pipeworx-io-ai-model-experiments -- npx -y @pipeworx/mcp-ai-model-experiments
What is the Ai Model Experiments MCP server?
Ai Model Experiments is an MCP server listed in the public MCP registry as io.github.pipeworx-io/ai-model-experiments. AI Model Experiments MCP ('Model Lab'), run the same prompts across many AI models simultaneously… This page covers its npm package (@pipeworx/mcp-ai-model-experiments).
Is the Ai Model Experiments MCP server safe to use?
Ai Model Experiments scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Ai Model Experiments MCP server expose?
Ai Model Experiments exposes 8 tools: experiment_models, experiment_estimate, experiment_create, experiment_status, experiment_results, and 3 more. Their descriptions and schemas cost roughly 1,088 tokens of context every time the server is loaded.
Is the Ai Model Experiments MCP server still maintained?
Ai Model Experiments is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Ai Model Experiments MCP server under?
Ai Model Experiments declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.