arcade-mcp
Enables teams to extend Claude agents with custom business logic and domain-specific tools without rebuilding infrastructure, reducing integration time and d…
MCP Server Framework and Tool Development library for building custom capabilities into agents.
- Build custom Claude tools that integrate your internal APIs and databases securely
- Create AI agent capabilities without writing complex agent orchestration code
- Extend Claude's abilities with company-specific functions and business logic
Enables teams to extend Claude agents with custom business logic and domain-specific tools without rebuilding infrastructure, reducing integration time and deployment friction.
Engineering teams building agent-driven workflows requiring proprietary tools or legacy system integration.
https://github.com/ArcadeAI/arcade-mcp
By ArcadeAI
How to Get It
claude mcp add arcade-mcp -- npx -y arcade-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
Once it’s connected, paste this into Claude:
Help me build custom Claude tools that integrate my internal APIs and databases securely
Trust Signals Auto-scanned
Data & Access
Community Pulse New
- iOS 13 Review: Join the Dark Side — Hacker News · 3 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 976 GitHub stars; contributors unknown; last commit 1d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 976 GitHub stars; contributors unknown; last commit 1d ago; license MIT.