Context7 MCP
MCP Server · Coding, Research
87/100
Rec
Fetch current library documentation and examples directly into coding agents.
Interface-verifiedlow risk
Benchmark-backed AI capability map
Discover the best AI capabilities for your stack
Skills, agent templates, workflows, and MCP servers — each published with a check status, risk label, and traceable evidence.
94capabilities
64risk-reviewed+
16low-risk
41MCP servers
Browse by category
Jump straight into a filtered view by task scenario.
Recommended capabilities
Clear task fit, traceable sources, explicit risk boundaries.
Playwright MCP
MCP Server · Browser, Automation
84/100
Rec
Expose browser automation primitives through MCP for web navigation and testing.
Interface-verifiedmedium risk
OpenAI Agents SDK Template
Agent Template · Automation, Research +1
74/100
Rec
A structured starting point for tool-using agents built with OpenAI Agents SDK.
Install-verifiedmedium risk
Browserbase MCP
MCP Server · Browser, Automation
72/100
Rec
Run browser automation in hosted Browserbase sessions for agents that need web actions.
Install-verifiedmedium risk
Filesystem MCP
MCP Server · File / Document, Coding +1
72/100
Rec
Expose selected local directories to agents for read and write file workflows.
Interface-verifiedhigh risk
Repository Code Review Skill
Skill · Coding, Security
70/100
Rec
Skill profile for reviewing pull requests with correctness, risk, and test coverage rubrics.
Risk reviewedlow risk
Preview · 94
Submit a capability
Submissions go to review first — nothing is published directly.