MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
AI-assisted outbound sales pipeline — FastAPI backend exposing the same service layer over HTTP and MCP
MCPLink onlyFew stars
The code to visualize colon-bench (MICCAI 2026) data and run evaluations of MLLMs on the benchmark.
SkillLink only★ 5
Berkeley Agentic AI class: Enhanced Finance Agent Benchmark with AgentBeats
MCPLink only★ 2Few stars
Open daily datasets on the AI economy: model prices across providers, price changes, company figures with sources, Mindshare, GPU rental prices, Gecko Tests. CC BY 4.0.
MCPLink onlyFew stars
Benchmark harness: CLI vs MCP (eager/deferred) vs Code Mode. 5 tasks × 4 configs × 10 runs = 200 data points. Token counts from Anthropic API usage object.
MCPLink onlyFew stars
Real-time multimodal VLM-to-action inference pipeline + multi-framework benchmark harness (NIM Qwen3-VL, vLLM, SGLang, TensorRT-LLM, ModelOpt, Triton) targeting RTX 5090, RTX PRO 6000 Blackwell, and H
SkillLink only★ 2Few stars
Connecting Language Models to Data Systems in the Energy Sector – An Evaluation of the Model Context Protocol (MCP)
MCPLink onlyFew stars
Medium EC2 instance (t3.micro) running M1–M10 sequential MCP tool chains (2-3 external HTTP calls, 5–100KB payloads). Collects metrics needed for EC2 vs Lambda performance comparison. Handles real mul
MCPLink only★ 1Few stars
Build, test and benchmark agents across a complete simulated enterprise
MCPLink only★ 5
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 itself).
MCPLink only★ 2Few stars
抖音账号对标分析一站式 Agent 技能：抓取→去重→下载→抽帧→GPU口播转写→固定模板对标报告。Crawl any Douyin creator into a data-driven benchmarking report.
SkillLink only★ 1Few stars
AI agent evaluation framework for energy analytics — multi-provider LLMs, benchmark runner, MCP-based tool ecosystem.
MCPLink onlyFew stars
Structured rubric evaluator calculating weighted composite Likert scores across quality criteria
SkillLink only★ 7
Pure Python ROUGE-L and BLEU n-gram lexical overlap precision, recall, and F1 metrics calculation
SkillLink only★ 7
RAG context precision and context recall evaluator measuring retrieved chunk relevance and rank quality
SkillLink only★ 7
Structured rubric evaluator calculating weighted composite Likert scores across quality criteria
SkillLink only★ 7
Pure Python ROUGE-L and BLEU n-gram lexical overlap precision, recall, and F1 metrics calculation
SkillLink only★ 7
RAG context precision and context recall evaluator measuring retrieved chunk relevance and rank quality
SkillLink only★ 7
🥋 A daily-practice dojo for Obsidian: log interview prep and job applications with one click, import your LeetCode solves automatically, and see streaks, topic coverage, and resume win-rates in one a
SkillLink only★ 5
Agent Skill for cross-border product launch readiness: admission checks, target-market benchmarks, localization, documents, labels, pricing, logistics, and remediation.
SkillLink only★ 13
Brian Weisberg's personal site for CFOs and finance leaders. Thought leadership, a toolbox of vetted finance software and communities, benchmarking resources, FP&A Buddy Q&A, and a private reading lib
MCPLink only★ 2Few stars
Parametric price benchmarking for engineering and procurement trade-offs. Agentic first, runs on your data, stays on your machine.
MCPLink only★ 2Few stars
Mode VC AI Chart Lab MCP Server — Query 38 Empirical AI Adoption, LLM Token Economics & Venture Valuation Charts
MCPLink onlyFew stars
Who stands behind it
