MCP Server for LLM comparison, benchmarks, and pricing — find the best model for any task

MCP Server for LLM comparison, benchmarks, and pricing — find the best model for any task

Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM. Catches the VulcanBench --cov addopts mis-scoring bug.

Modern CFO Cost Segregation Allocation Benchmarks (v2026.1.0): 45 property-type MACRS 5-year, 15-year, and long-life depreciation allocation bands + remote MCP server (mcp.freecostseg.com) and Overline IQ real estate tax-savings analysis.

MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_claims, get_claim, list_measured. Read-only, CC BY 4.0 data.

LLMTest MCP server — benchmark AI models and get cost-saving suggestions in your IDE

Benchmark AI model inference speed — like speedtest.net but for LLMs. MCP server with zero telemetry.

PoolHall · 台球厅 —— 让每个 AI 智能体拥有一双不完美的手。确定性物理引擎 + Hand Model 手感注入 + MCP Server，Agent 知行曲线 Benchmark。

MCP server for Artificial Analysis API - get LLM model pricing, speed, and benchmarks

Independent model benchmarks in your agent: the Artificial Analysis MCP server for Claude, ChatGPT, Cursor and Gemini CLI

TokenMark MCP server: expose local-LLM benchmark configs + hardware-aware model recommendations to Claude and other agents.

LLM-friendly API cards, an MCP server and a GPU benchmark for CuPy and nvmath-python (cuBLAS, cuFFT, cuSOLVER, cuSPARSE, cuDSS, cuTENSOR)

Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.

Intelligent routing layer for AI agents: recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.

Portable WPE WebKit runtime for AI agents with native input, screenshots, ordered JSONL, and reproducible benchmarks.

Benchmark local LLM inference speed (tokens/sec) on your own hardware — llama.cpp native + cloud APIs, 124-model catalog, optimal-quant picker, and an MCP serve mode.

MCP server for LLMTest — benchmark AI models on real prompts, find cheaper alternatives across 340+ models. Works with Claude Code, Cursor, Windsurf.

Local engines for ATO benchmarks, Payday Super and Division 7A loans, served by the aus-accounting-mcp server. Synthetic data only.

Edit Excel workbooks from an AI agent without re-saving the whole file. CLI, MCP server, Claude Code plugin, benchmark kit.

MCP server over a COIN wargame engine: any host model plays Government or Red Team through tools; seeded replayable games; model benchmark harness. Protocol 2026-07-28.

Enhanced distribution of HOL Guard: AI agent runtime security with MCP server, African threat intelligence, benchmarks, and architecture visualization

A V8 deoptimization toolkit for AI agents and dev workflows: MCP server, findings engine, benchmark harness, and fix-verify comparison for inline caches, deopts, and hidden-class churn

MCP Server implementation of AgentFold - Long-Horizon Web Agents with Proactive Context Management. v2.0 adds analytics, validation, quality evaluation, and performance benchmarking.

MCP server for LLM/VLM model selection — compare 300+ models with real-time benchmarks, pricing, and personalized recommendations. No API key required.

MCP server for performance: code benchmarking, memory analysis, Big O estimation, bundle size analysis, HTTP load testing Install: npx @rog0x/mcp-perf-tools

Official SDKs for the AI Stupid Level Smart Router (benchmark-driven LLM router) and Data API: TypeScript, Python, Vercel AI SDK provider, MCP server, LangChain, n8n.

Benchmark LLMs on your own scenarios with a multi-judge panel. Full MCP server (tools, resources, prompts, progress) plus local GUI, CLI, and desktop app. One OpenRouter key.

Ultimate Kali Defensive Security & System Hardening MCP Server — 78 defensive security tools for firewall management, CIS benchmarks, intrusion detection, malware scanning, container security, zero-trust networking, and more.

A local-first workbench for developing, inspecting, and benchmarking MCP servers against local (LM Studio, Ollama) or remote (OpenRouter) models — Web UI, CLI, and MCP interface over one shared store.

Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.

Safe I/O harness for LLM agents: serial, Modbus TCP, MQTT, file sandbox and ESP32 flashing behind an MCP server, with a JSONL audit journal - plus ironbench, a pass@k benchmark for firmware agents on Wokwi/Renode/real hardware.

Give your AI agent a spinal cord: real-time game agents (a model sets goals, reflexes act every frame) and the Spinal Score, a Doom benchmark where 100% is elite human play. Try it: spinal play doom

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, cost columns, a CI regression gate, and an MCP server for coding agents.

PRISM OS-009 reference MCP server — 6 loop-phase machines (compose, interact, observe, reflect, diagnose, config) that benchmark any PULSE-conforming memory system. One of four MCP servers in the [&] three-protocol stack (box-and-box, graphonomous, os-pri

Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).

Archived experiment: local code graph search and team learnings for AI coding agents (Claude Code, Codex, Cursor) as a Rust MCP server and CLI. Tree-sitter, BM25F and call graph ranking, benchmarked on Agent Retrieval Bench against Trail, CodeGraph, Serena and more. Abandoned: agents never used it.

AI computer use for the whole Mac, with any AI: Claude, ChatGPT, Gemini, OpenRouter or a local model. A native MCP server, a menu bar agent that learns shareable skills, and benchmarks you can run on your own model. No API key needed through MCP.

PMLL Memory MCP Server v2.0.3 — persistent memory logic loop with short-term KV cache (peek pattern), Q-promise deduplication, Context+ long-term semantic memory graph, and solution engine. Four-way benchmarked: Combined Context+ + PMLL/peek delivers 36ms

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 regressions with likely causes, over-provisioned resources, and retries. Includes a zero-dependency dashboard, an MCP server for AI assistants, and opt-in AI narration.

Translation QA for locale files — the validator tools need no API key and make zero model calls. **Tools:** check_locales, check_glossary, check_placeholders, diff_locales, review_locales, list_languages (all keyless) + translate_json, translate_file (bring your own Anthropic/OpenAI key). `review_locales` hands translation pairs and judging criteria back to your agent, so meaning-level review runs on the model your client already has. Supports JSON, Flutter `.arb`, Apple `.xcstrings`. Apache-2.0, no account, no telemetry. Benchmark: https://shipi18n.com/benchmark · Docs: https://shipi18n.com/docs/mcp/setup

A full-featured MCP server for the Kaggle API — competitions, datasets, kernels, models, benchmarks, and discussions.

Powerpipe MCP server to run benchmarks, detections and controls using AI.

Hardware-Aware Hugging Face Discovery, Memory Fitting, Empirical Benchmarking & Swappable Local Model Gateway for AI Agents

CLI and MCP server for the Arquimedes 1.04M competition and benchmark math problem database

Test, explain & benchmark regexes + a library of security patterns

Find the best GTM APIs. We benchmark all the GTM APIs and we put the results on our website.

TikTok Business API MCP server — campaigns, video performance, audience targeting and benchmarks from Claude

MCP server for WageAPI — US + EU salary benchmarking, pay transparency compliance. Connect Claude, Cursor, or VS Code to workforce data.

MCP server for local LLM inference on Ryzen AI Max+ 395 with queueing, deadlines and telemetry; benchmark findings

European labor market data — job postings, salary benchmarks, skills demand. MCP server for AI agents.

MCP server for the DecimalAI skills registry — search skills, inspect trust/benchmark evidence, and read the leaderboard from any MCP client.

A full-featured MCP server wrapping the Kaggle API — 52 tools across competitions, datasets, kernels, models, benchmarks, and discussions

MCP server that recommends the best AI model per agent role — from the subscriptions you actually have. Benchmarks, pricing, and the why

MCP server wrapping the Artificial Analysis public API. Enables AI agents to query LLM and multimodal model benchmarks, pricing, speed data, and track model updates via structured diffs.

Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.

Inspectable AI agent memory, context engineering and multi-agent orchestration with an MCP server and logical-fleet benchmarks

Lean MCP server for local/remote shell access, background jobs, and file read/write/edit. Benchmarked 37–90% fewer tokens than Desktop Commander across 11 tasks.

Persistent memory shared across Claude, ChatGPT and other AI assistants, via MCP. Hosted in the EU. Benchmarks and vault code open.

Official Model Context Protocol (MCP) server for Kovitel Vietnam eSIM, carrier APN rescue, and 5G latency benchmarks.

Measure what Chinese/Cantonese actually costs in tokens - and why. MCP server: cross-script comparison, per-token attribution, reproducible benchmark.