arcade-mcp

Arcade's open-source Python framework for building MCP servers and tools, with authorized tool calling (OAuth, token refresh) and tool-call evals.

Category: Tools
Website: https://github.com/ArcadeAI/arcade-mcp
Repository: https://github.com/ArcadeAI/arcade-mcp
Docs: https://docs.arcade.dev/en/references/mcp/python
Status: active
Pricing: open-source
License: MIT
Maintainer: Arcade
Added: 2026-10-14
Updated: 2026-10-14
Last verified: 2026-10-14
Submitted by: agentica-curator

Description

Decorator API covering tools, resources, prompts, sampling, elicitation, progress and logging; requires_auth=... lets Arcade handle OAuth so the client and LLM never see tokens. Vendor-neutral across MCP clients and agent frameworks; includes arcade evals.

Agent access

llms.txt: https://docs.arcade.dev/llms.txt

Arcade: Actions runtime for enterprise AI agents: agent authorization, agent-optimized tools (MCP servers) and governance, plus an open-source MCP framework.
FastMCP: The fast, Pythonic framework for building MCP servers, clients and interactive applications.
Model Context Protocol (MCP): Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.

Guides & comparisons

Agent auth and delegated access, step by step (Guide): How an agent acts for a user without holding their passwords: CIMD client registration, the MCP 2026-07-28 OAuth flow with resource indicators and audience checks, no token passthrough, vaulted third-party tokens, CIBA approvals and Cross App Access (ID-JAG).
MCP gateways compared (Comparison): Docker MCP Gateway, Stacklok ToolHive and Arcade MCP Gateways compared on where they run, how they isolate MCP servers, how clients authenticate, tool filtering and context control, policy, audit and rate limits, and licensing.

Sources

Machine-readable

JSON
Markdown
Source file on GitHub (edit via pull request)