Evaluate model or agent outputs.
Complete API testing platform MCP server with 14 tools: performance testing (benchmark, load, stress, spike, soak, smoke, A/B compare, profile), functional validation, multi-step workflow chains, OpenAPI contract checking, fuzzing, security scanning, and
CLIWatch CLI — manage benchmarks, view results, and get AI-agent-friendly docs for CLI testing
The agent-native profiler for three.js games: an always-on flight recorder, per-entity cost attribution, and a deterministic bench — so a coding agent can measure, attribute, and verify instead of guessing.
Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.
Adaptive web research for AI coding agents — 91% of Deep Research quality at 5% cost
VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol
Assess UK lease tenant break clauses with grounded citations and a measured hallucination rate.
Trust and reputation scores for AI agent service selection
A cheap, deterministic first-pass filter for unsupported claims in LLM output, computed without a second model call. Not a standalone hallucination detector. MCP server plus the reference implementation of Touchstone Standard 1.0.
Model Context Protocol server for Tigo Energy solar system monitoring and analytics
MCP server for 3XB Web Entity Intelligence — score any person or org from live web data
Load-test a URL, ping it by phase, ramp to find the capacity, compare runs: JSON reports, guardrails
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
Pokemon TCG MCP server: PSA grading, collection management, and multi-provider pricing.
Enhanced Subject Researcher MCP - Iterative target-driven research with multi-vertical search, quality metrics, and sophisticated claim mining
MCP server for ShieldPi Watchtower — run LLM security scans, generate drop-in guardrails from scan findings, operate the AI SOC analyst (incident triage + kill-chain reconstruction), and query the live agent monitor from Claude Desktop / Cursor / Continue.
Find retiring LLM calls in code and test the replacement model on real traffic before switching.
Roost public MCP servers for AI agents: a payment pre-flight check (roost-corpus-mcp) and a finance-agent safety test (roost-eval-mcp). Advisory, zero-config, no API key.
MCP server with 215+ tools for DaVinci Resolve scripting API (v20.3)
A code-first evaluation framework for testing LLM agents' ability to use MCP tools