MCP App StoreMCP App Store
from aeon-bench-pod21
Execute end-to-end LLM benchmarks using AEON Bench Pod. From model verification to leaderboard submission.
This skill provides the operational blueprint for running verified LLM evaluations using the AEON Bench Pod. It allows an agent to deploy a local benchmarking appliance, verify model weights against Hugging Face, execute a comprehensive suite (text, agentic, vision, audio, video, and performance), and submit attested results to the public leaderboard.
Use this skill when asked to benchmark, score, or evaluate an LLM's performance. It is the primary path for generating 'attested' results that rank on the AEON leaderboard, moving beyond simple smoke tests to a full-scale verified evaluation.
aeon_pod_mcp.py for headless agent control.Any AI agent capable of executing shell commands (Docker) and utilizing MCP tools.
This skill has not been reviewed by our automated audit pipeline yet.
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
ACP Checkout — MCP Binding
Guidance to expose ACP checkout REST operations as MCP tools so agents can perform commerce flows (create/update/complete/cancel checkout).
Skyvern — AI Browser Automation
Cloud-first AI browser automation platform and SDKs for extracting data, filling forms, downloading files, and running multi-step web workflows from agents or c
Forcemanager Automation (Rube MCP)
Automate Forcemanager tasks via Rube MCP (Composio); discovers tools, ensures active connections, and runs toolkit workflows safely.
Code Mode for MCP Servers
Add a sandboxed code mode tool to an MCP server so LLMs run small processing scripts against large API responses and only the script output enters the model con
DAUB UI
A drop-in CSS+JS component library with 70+ carefully designed components and 20 theme families for fast, consistent UI building.