- Conduid
- Marketplace
- #benchmark
MCP servers tagged benchmark
169 live MCP servers tagged "benchmark", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with benchmark.
AI Infra Guard
A full-stack AI Red Teaming platform securing AI ecosystems via AI Infra scan, MCP scan, Agent skills scan, and LLM jailbreak evaluation.
Hotpath Rs
Rust profiler for CPU, memory, SQL, HTTP, and async performance, with Prometheus and Grafana support.
Aenvironment
Standardized environment infrastructure for Agentic AI development.
Goku
Goku is an HTTP load testing application written in Rust
Mcpmark
MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
Arena
mcp_arena is a production-ready Python library for building MCP (Model Context Protocol) servers with intelligent agent orchestration and domain-specific presets.
Mcptoolbenchpp
MCPToolBench++ MCP Model Context Protocol Tool Use Benchmark on AI Agent and Model Tool Use Ability
Selfstarter
Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In ea…
Overtime
Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In ea…
Primitive Bench
The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivere…
Spmind
ICML 2026 autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.
Aaabench
A long-horizon benchmark harness: give a coding agent a real game engine, professional conditions and time, and ask it to build an open-world game. Harness only, no results.
DishwasherBench
A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.
Mini Claude Code
A hand-written terminal coding agent: agent loop, tools, two-level context compaction, safety gate, MCP bridge, self-built benchmark. No agent frameworks.
Skill Optimizer
Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs
Sloptotal
Open-source AI text detector and ChatGPT detector: 23 engines, one calibrated score, every number measured. CLI, MCP server and GitHub Action. Self-hosted, runs on CPU.
AgentTrust
Deterministic safety floor for tool-using AI agents: pre-execution gating, SafeFix suggestions, attack-chain detection, opt-in self-learning LLM judge. Papers: arXiv 2605.04785, 2…
Buried Injections
🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark.
Qwen38 Strix Halo Harness
Local AI coding agent harness for AMD Strix Halo (Ryzen AI Max+ 395): Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks. Works with any OpenAI-compatible…
Top-Celestial-Company-Ltd/DROS-VajraClaw-Hacker
band execution governance gateway and W3C DID security guardrail for AI Agent MCP tool calls.
Asiai
Multi-engine LLM benchmark & monitoring CLI for Apple Silicon
Kb Arena
Benchmark 19 retrieval architectures (vector, contextual, QnA, knowledge graph, LightRAG, hybrid, RAPTOR, PageIndex, BM25, metadata-filtered, temporal, rerank, HyDE, multi-query,…
Assay
An open, reproducible trust layer for AI artifacts — skills, MCP servers, agents, and plugins. Assay inspects code, runs sandboxed behavioral audits, and generates verifiable repo…
LLM Shield Proxy
Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-…
MCPSecBench
MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
Civ6 MCP
An MCP server that lets LLM agents play Civilization VI.
Awesome AI Gateway
⚡ Awesome AI Gateway — curated comparison of 100+ AI gateways & LLM proxies (LiteLLM, OpenRouter, Portkey, Kong, Higress, new-api, Bifrost) by cost, security, compliance & self-ho…
Sir Thaddeus
Private, local-first AI assistant for Windows with permissioned tools, durable memory, and evidence-driven small-model improvements.
Vexp Swe Bench
Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.
AgentDefense Bench
A comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems
Tier
A 1.5B model shown all 80 tools picks the right one half the time — not because it can't call tools, but because it can't find them. Tier adapts the tool presentation to model siz…
1c AI Codegen Research Paper
Научно-исследовательская работа «Экспериментальная оценка эффективности искусственного интеллекта в генерации кода для доменно-специфичных платформ (на примере 1С:Предприятие 8)».…
Evalmonkey
CLI for agent builders to benchmark & chaos test your AI Agents. Text, Voice, Code supported.
Rootly Doom Agent Arena
Benchmark model duels in Doom. An MCP-native arena for real-time model-vs-model evaluations.
Sharpebench
MCP server exposing SharpeBench's luck-robust quantitative evaluation tools for trading agents, including deflated Sharpe, pass^k, process discipline, and risk analysis.
Stress
Stress testing tool for MCP servers
Mcpbr CLI
Model Context Protocol Benchmark Runner - CLI tool for evaluating MCP servers
Larkx
AI codebase indexer and MCP server for Claude Code, Cursor, and Copilot. Pre-index your project into a compact graph and measure real token savings with `larkx bench`.
Hlido MCP Guard
Check an MCP server's independent Hlido trust verdict before it starts — a zero-dependency, no-API-key runtime guardrail for Claude Code, Cursor, Cline, and any stdio MCP client.
Verigent MCP Server
MCP server for Verigent — AI agent verification & counterparty due diligence. Check who you're transacting with, carry your own VG credential, flag bad actors.
Server
MCP server for Verigent — AI agent verification & counterparty due diligence. Check who you're transacting with, carry your own VG credential, flag bad actors.
Keelson
A self-evolving agent harness — permission-gated execution, context folding, and a gated skill-update pipeline, validated with real benchmarks (including one that caught a bug in…
Memorystress
The first longitudinal benchmark for AI memory systems. Test LLM agents, RAG pipelines, MCP servers, and memory backends across 1,000 sessions.
IntentForge
Intent-preserving deterministic CAD pipeline for editable, validated CadQuery models.
OpenPhysicsAI
An open-source physics lab for people and AI agents: 20+ verified solvers for flow, shocks, fire, heat, solids, sound, electromagnetism and orbits, with a native 3D app, a CLI and…
Agent Emulator
Emulation & experimentation platform for trustworthy AI agent infrastructure —trace-driven replay of agent behavior on a sharded blockchain. Built on BlockEmulator-X by HuangLab @…
Benchmark
Head-to-head benchmark comparing the official MCP to the MCP auto-created by Hintas.
Aether
Evidence-driven AI development workbench for model evaluation, project context, and controlled agent execution.
Tessera
Open-source, MCP-native benchmark for whether AI agents reason reliably over fragmented enterprise knowledge — accuracy, provenance, correct refusal.
Redstamp
own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prompt injection and destructive commands before they run; same call, sam…