MCPMark - stress-testing MCP benchmark

Benchmark harness that evaluates models and agents on real-world MCP usage. Comparable scores across servers and frontier models.

Saved Apr 25, 2026View source ↗

#mcp #benchmark #evaluation #agent-eval #tool-use

This entry doesn't have a long-form writeup yet. Follow the source link above for the full context.

Featured in

MCP servers and Model Context Protocol tools
Production MCP servers, gateways, frameworks, and clients - everything in this directory that speaks the Model Context Protocol.

Related entries

GitHub ToolFeatured

Qartez MCP - codebase intelligence for AI agents

Rust MCP server that pre-indexes a codebase with PageRank, blast-radius, git co-change, and complexity signals. Agents query the graph instead of grepping files.

Why I saved this - The modification guard - auto-blocks edits to high-PageRank files until the agent runs an impact query - is the most underrated feature in the repo.

#mcp #claude-code #rust #code-intelligence #static-analysis

GitHub Tool

AgentShield - security scanner for AI agents

CLI, GitHub Action, and GitHub App that scan agent configs, MCP servers, and tool permissions for vulnerabilities. Detects skill poisoning and prompt-injection vectors.

#security #mcp #claude-code #agent-security #supply-chain

GitHub Tool

Open Cowork - desktop app for AI coding agents

Open-source Windows/macOS desktop that one-click installs Claude Code, MCP tools, and Skills with sandbox isolation, multi-model support, and Slack/Feishu hooks.

#claude-code #desktop-app #mcp #sandbox #computer-use

GitHub Tool

Oxideterm - all-in-one terminal workspace

Native Rust + Tauri 2 terminal with local shells, SSH, SFTP, remote IDE, AI agent, MCP, RAG, and a file manager - all in one binary. No OpenSSL dependency.

#terminal #ssh #tauri #rust #mcp