- Conduid
- Marketplace
- #benchmarking
MCP servers tagged benchmarking
53 live MCP servers tagged "benchmarking", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with benchmarking.
Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
Goku
Goku is an HTTP load testing application written in Rust
Mcpbench
The evaluation benchmark on MCP servers
Fastapi Bitnet
Running Microsoft's BitNet inference framework via FastAPI, Uvicorn and Docker.
Agentweave
Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware routing and recovery.
Reticle
Browser-native, GPU-accelerated editor for very large hierarchical 2D IC-layout scenes, written in Rust (native and WebAssembly).
LogLead
LogLead performs log loading, log enhancement, log feature engineering, log analysis, log anomaly detection also via MCP-server.
Context Diamond
Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.
Decibench
The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.
Blender Agent Studio
Codex plugin for reproducible Blender modeling, validation, animation, MCP tooling, and agent benchmarking
redline
Zero-infrastructure QA agent — k6 performance + Playwright functional testing with red/green baselines and a deterministic, model-free deploy gate. Clone and run.
Uhbs Standard
Universal Honeypot Benchmarking Standard (UHBS) v4.6.0 — open-source beta framework for vendor-neutral honeypot / deception evaluation
Companmem
the quest for ultimate ai memory
Bottrade
SDK, MCP integrations, examples, and verified benchmarks for AI trading agents.
Fituna
Stop guessing your llama.cpp config. Give it a target tok/s and a quality budget, and it measures quantization levels and GPU offload on your own machine to find the lightest setu…
RedLine
Zero-infrastructure QA agent — k6 performance + Playwright functional testing with red/green baselines and a deterministic, model-free deploy gate. Clone and run.
Web Search Agent Evals
Evaluation harness for web-search agents: 4 agents x 2 tools matrix in isolated Docker containers, with deterministic and LLM-based grading
Cpt AI
AI-powered benchmark regression analyzer with CLI, REST API, and interactive Dashboard. Compares cloud performance runs via OpenSearch + LLM, with automated regression detection.
Agent Smith 42
LLM code-agent framework — Thought→Code→Observation loop, process-isolated sandbox, MBPP + SWE-bench tracks, MCP tools, multi-model OpenRouter benchmarks. 42 School project.
Gpu Perf Tune
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
Saybench
Benchmark the full voice-AI pipeline on your own audio — STT (batch + streaming), LLM TTFT, speech-to-speech, and TTS. WER by failure mode, keyterm recall, real-time-paced latency…
Context Report
An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.
Constellate
Three knowledge planes (embedded, unified, composed) behind one retrieval contract, benchmarked head-to-head on MovieLens ml-25m. Relational, vector, and graph fusion, an MCP cont…
Era
Build, test and benchmark agents across a complete simulated enterprise
Agent Loop Guard
Local runtime guard for coding agents with loop detection and explainable policy decisions.
Goku
Goku is an HTTP load testing application written in Rust
SAGE
Official implementation of SAGE: A deployment-oriented evaluation framework for LLM-based autonomous agents (IEEE Transactions on Artificial Intelligence).
Hotpath
Profile llama.cpp-family GPU inference, run controlled experiments, and compare results with evidence labels. CLI, MCP server and Agent Skill.
Mcpbench
MCP server load tester: concurrent JSON-RPC, per-tool p50/p95/p99, stdio+HTTP/SSE transports, CI regression gating
Tne SDK
TNE-SDK - The Official Python SDK for The Null Epoch - an AI-only MMO where LLMs play autonomously. Connect any model (OpenAI, Anthropic, Ollama, vLLM, etc.) via MCP, TUI launcher…
Token Enhancer
Reduce web pages to clean text before they reach your AI agent’s context window, saving tokens and cutting noise
Claude Code For AI Engineers
Open-source preview of *Claude Code for AI Engineers* - a methodology-first skill pack for RAG eval, agent debugging, MCP servers, paper reproduction, and benchmark reporting. Ful…
Nf Runinsights
Nextflow plugin for cross-run benchmarking. Records per-process metrics for every run into a local or shared history store, compares runs against their own history, and flags regr…
Maverik
Benchmark, compare, and cost-predict your MCP agents — JMeter for AI agents.
Kaepsele
Full-stack AI Chatbot deployment for universities. Includes RAG, secure Code Interpreter, vLLM inference, and educational prompt libraries.
Tracebench
RCAgentBench: a benchmark measuring how tool design and agent instructions affect LLM agents doing root cause analysis on distributed traces.
Pigeon Evals
A End-To-End RAG Pipeline that includes Evaluations, iterations, and swappable components. At its core it allows users to be able to try different embedding models and techniques.
Linkedin Repo Role Recommender Agent
An AI agent built with MCP and LangGraph that analyzes GitHub repositories of LinkedIn users and recommends the top 3 most suitable IT roles for them.
Cortex Mem
Cortex — persistent AI memory for Claude Desktop & Claude Code. Local MCP server with a typed knowledge graph, contradiction detection & background scheduler. 20/20 benchmark, 27/…
Memvid
🧠 Experience advanced memory management with Memvid, a tool for interacting with your knowledge base using LLMs and smart recall features.
Halflist
CI-first conformance testing and benchmarking CLI for MCP servers. Lint your MCP server before your users do.
AI Agent Testing
A research project to measure AI agent robustness. Contains automated testing pipelines and a benchmarking methodology developed to audit Agentic AI architectures for complex reas…
Helios LLM Orchestrator
Local-first MCP multi-LLM orchestrator with task decomposition and benchmark-guided model routing through OpenRouter.
Energyevals
AI agent evaluation framework for energy analytics — multi-provider LLMs, benchmark runner, MCP-based tool ecosystem.
E2H
Evidence-to-Harness toolkit for reproducible AI-agent evaluations, observable evidence, deterministic replay, and verifiable releases.
Flameox
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
Flameox
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
Goku
Goku is an HTTP load testing application written in Rust
Goku
Goku is an HTTP load testing application written in Rust
Flameox
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.