Ai Model Experiments
Server Details
AI Model Experiments MCP ('Model Lab') — run the same prompts across many
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 5.8% over 22 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- pipeworx-io/mcp-ai-model-experiments
- GitHub Stars
- 0
- Server Listing
- AI Model Experiments
TDQS
Scored across 44 tools
Many tools have overlapping purposes, especially the various data-querying tools (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools) and multiple Polymarket analysis tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread). Descriptions are detailed and attempt to differentiate, but the boundaries between some tools are subtle and may confuse an agent.
Most tool names follow a consistent snake_case verb_noun pattern (e.g., experiment_create, experiment_status, polymarket_edges, resolution_audit). A few names like ask_pipeworx and bet_research are less conventional, but overall the pattern is predictable and readable.
With 44 tools, the surface is quite large and includes many niche or highly specialized tools (e.g., kalshi_weather_edge, generate_llms_txt, polymarket_edge_tracker). While the server covers diverse domains, the count feels heavy and some tools are tangential to the core 'AI Model Experiments' purpose, making it difficult to navigate.
The experiment lifecycle is well covered: create, estimate, list, status, results, cancel, topup, models. However, the server also bundles many unrelated data-query and prediction-market tools that are not part of the experiment workflow, which dilutes the core purpose and creates gaps in coherent coverage of a single domain.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
- Added
company_facts - Added
kalshi_weather_edge - Changed
polymarket_edges2 fields changed- changed
Input schema / properties / min_edge_pp / descriptionPrevious value: -"Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage."New value: +"Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage and Polymarket's own taker fee." - changed
Input schema / properties / slippage_pp / descriptionPrevious value: -"Assumed execution slippage in percentage points per leg (default 0.3). Subtracted from raw |edge| before ranking and Kelly sizing. Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade. Bump for very thin partitions; drop to 0 if you have a smarter fill model."New value: +"Assumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing, ON TOP OF Polymarket's own taker fee — which is NOT zero (rate 0.04-0.07 depending on category, read off each market's own published fee schedule; see fees_pp_applied on every row and fees.ts for the full schedule). Bump slippage for very thin partitions; drop to 0 if you have a smarter fill model — the fee still applies regardless."
- Added
release_calendar_markets - Added
resolution_audit - Added
resolution_diff
1 tool update
- Changed
bet_research2 fields changed- changed
Input schema / examplesPrevious value: -[ - { - "market": "when-will-bitcoin-hit-150k" - }, - { - "market": "https://polymarket.com/event/when-will-bitcoin-hit-150k" - } -]New value: +[ + { + "market": "will-kristi-noem-win-the-2028-republican-presidential-nomination" + }, + { + "market": "https://polymarket.com/event/will-kristi-noem-win-the-2028-republican-presidential-nomination" + } +] - changed
Input schema / properties / market / descriptionPrevious value: -"Polymarket slug (\"when-will-bitcoin-hit-150k\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k?\"). Dated slugs stop resolving once they settle — Polymarket de-indexes resolved markets — so prefer an undated one."New value: +"Polymarket slug (\"will-kristi-noem-win-the-2028-republican-presidential-nomination\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k?\"). Dated slugs stop resolving once they settle — Polymarket de-indexes resolved markets — so prefer an undated one."
2 tool updates
- Changed
bet_research2 fields changed- changed
Input schema / examplesPrevious value: -[ - { - "market": "will-bitcoin-reach-100k-in-july-2026" - }, - { - "market": "https://polymarket.com/event/will-bitcoin-hit-150k-by-june-30-2026" - } -]New value: +[ + { + "market": "when-will-bitcoin-hit-150k" + }, + { + "market": "https://polymarket.com/event/when-will-bitcoin-hit-150k" + } +] - changed
Input schema / properties / market / descriptionPrevious value: -"Polymarket slug (\"will-bitcoin-hit-150k-by-june-30-2026\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k by June 30?\")"New value: +"Polymarket slug (\"when-will-bitcoin-hit-150k\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k?\"). Dated slugs stop resolving once they settle — Polymarket de-indexes resolved markets — so prefer an undated one."
- Changed
polymarket_kalshi_spread2 fields changed- changed
Input schema / examplesPrevious value: -[ - { - "topic": "fed" - }, - { - "topic": "btc" - } -]New value: +[ + { + "topic": "fed" + }, + { + "topic": "btc" + }, + { + "topic": "bitcoin" + }, + { + "topic": "fed rate decision" + } +] - changed
Input schema / properties / topic / descriptionPrevious value: -"Pre-mapped: fed | btc | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president"New value: +"Subject to compare. Canonical keys: fed | btc | eth | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president — but aliases and keywords resolve too (\"bitcoin\", \"fed rate decision\", \"ethereum\", \"inflation\", \"s&p 500\", \"us recession\", \"next pope\", \"2028 election\"). Check resolution.topic_matched_by in the response: \"exact\"/\"alias\" is a curated pairing, \"phrase\"/\"token\" is a keyword guess."
39 tool updates
- First observed
ai_visibility_check - First observed
ask_pipeworx - First observed
ask_pipeworx_beta - First observed
ask_pipeworx_grounded - First observed
bet_research - First observed
compare_entities - First observed
deep_research - First observed
discover_tools - First observed
entity_profile - First observed
experiment_cancel - First observed
experiment_create - First observed
experiment_estimate - First observed
experiment_list - First observed
experiment_models - First observed
experiment_results - First observed
experiment_status - First observed
experiment_topup - First observed
forget - First observed
generate_llms_txt - First observed
list_subscriptions - First observed
pipeworx_feedback - First observed
pipeworx_trending - First observed
polymarket_arbitrage - First observed
polymarket_edge_tracker - First observed
polymarket_edges - First observed
polymarket_fill_risk - First observed
polymarket_kalshi_spread - First observed
recall - First observed
recent_alerts - First observed
recent_changes - First observed
remember - First observed
resolve_entity - First observed
scan_competitor_ai_presence - First observed
scan_dependency - First observed
search_within - First observed
subscribe - First observed
suggest_questions - First observed
unsubscribe - First observed
validate_claim
Related MCP Connectors
Test and compare prompts across any AI provider. Bring your own keys.
65+ AI tools as MCP: research, write, code, scrape, translate, RAG, agent memory, workflows
MCP server for building and testing AI agents with multi-model experimentation and insights.
LLM Orchestration MCP Agent
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceA runnable lab for comparing plain MCP results, FastMCP Prefab UI, server-interactive MCP Apps, and a raw HTML MCP Apps bridge inside ChatGPT and other compatible hosts.-
- AlicenseNot gradedqualityDmaintenanceMCP server that benchmarks AI models on your actual prompts and finds cheaper, faster alternatives.40 npmMIT
- AlicenseNot gradedqualityBmaintenanceContext intelligence for AI coding sessions. 7 MCP tools to score, compare, compress, build, and scan prompts across 9 AI tools. Rule-based, <5ms/prompt, all analysis runs locally.47MIT
- AlicenseNot gradedqualityDmaintenanceMulti-model AI conversation MCP for Claude Desktop. Seamlessly integrate with GPT-4, Gemini, xAI, Perplexity, and local models via Ollama.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.