Tool overview
Arcade is listed under AI Infrastructure & MLOps AI tools.
What is Arcade?
Arcade is an MCP runtime for production AI agents. It handles user authorization, policy enforcement, tool execution, governance, and thousands of application actions through hosted or self-hosted components, SDKs, APIs, and integrations with common agent frameworks.
Best for
Developers shipping secure tool-using agents and MCP applications
Who is it for?
Decision note
Accepted for Preview after independent V411 official-source research. Apply only after failures = 0, warnings = 0, unmapped = 0, and review of controlled fields, Arabic v2 parity, outreach, affiliate status, logo QA, rebrand handling, and explicit clears.
Key features
Agent authorization and policy enforcement
Hosted and self-hosted tool execution
MCP tools for business applications
Python and TypeScript developer SDKs
Use cases
Connecting agents to user accounts
Enforcing policy on agent actions
Deploying secure MCP tool servers
Auditing production agent activity
Pros
- Free tier supports prototyping
- Usage pricing is publicly documented
- Supports cloud and self-hosted execution
Limitations
Arcade reduces integration and authorization work but does not make agent decisions inherently safe. Teams must apply least privilege, validate identity sources, constrain tools, test failure paths, monitor audit logs, and require approval for high-impact actions.
Pricing details
Billing options
Pricing note
Arcade offers a Free plan with 2,000 monthly auth events and 2,000 tool calls. Team starts at $25 per month plus usage, with auth events at $0.10 and tool calls at $0.01. Enterprise pricing is custom.
Supported languages
- English
Integrations
Gmail
Slack
Notion
Linear
Please log in to join the discussion.