Skill Detail

Build authenticated MCP tools and servers with Arcade MCP

Use Arcade MCP to create custom MCP servers and tools with OAuth-aware authorization, evals, and deployment paths for agent tool-calling workflows.

Integrations & ConnectorsMCP
Integrations & Connectors MCP Security Reviewed
⭐ 895 GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill build-authenticated-mcp-tools-and-servers-with-arcade-mcp Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Python, arcade-mcp, an MCP-compatible client, optional Arcade Cloud account for hosted auth and deployment
Install & setup
Install the Python package from PyPI as documented by Arcade, define tools with arcade_mcp_server, configure required auth providers or scopes, then connect the resulting MCP server to Claude, Cursor, VS Code, or another MCP client.
Author
ArcadeAI
Publisher
Company
Last updated
May 21, 2026
Quick brief

Use Arcade MCP when an agent team needs MCP tools for internal APIs, custom OAuth providers, or domain-specific integrations that are not already available as prebuilt servers. The operator defines MCP tools with the Arcade Python framework, declares auth requirements such as OAuth scopes, tests tool-call behavior with Arcade evals, and deploys the server for MCP-compatible clients. Keep the scope to building and operating custom MCP tool surfaces, not listing Arcade as a general hosted platform.

How it works

What this skill actually does

Inputs and prerequisites: Python, arcade-mcp, an MCP-compatible client, optional Arcade Cloud account for hosted auth and deployment.

Setup notes: Install the Python package from PyPI as documented by Arcade, define tools with arcade_mcp_server, configure required auth providers or scopes, then connect the resulting MCP server to Claude, Cursor, VS Code, or another MCP client.

Source and verification boundary: use https://docs.arcade.dev as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.