arcade-mcp CLAUDE.md

arcade-mcp CLAUDE.md is an instructions file for Claude Code from ArcadeAI/arcade-mcp. It costs 4,698 tokens per session, scanned A, original, MIT.

Developer instructions for Arcade MCP, a Python platform that exposes AI tools through the Model Context Protocol and Arcade’s worker API. A monorepo is one repository containing multiple related libraries; this one has five libraries and a command-line tool.

In plain words
What is it for?
Use them when installing dependencies, testing libraries, running checks, building packages, or changing the MCP and worker tool infrastructure.
Why use it?
They explain the project’s two tool interfaces, shared catalog, package layout, and required commands so changes work across the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

About the project

arcade-mcp is a Python framework for creating Model Context Protocol servers and the tools they expose to AI agents. Developers use it to connect agents to internal APIs, custom authentication providers, and specialized services, with support for authorization, evaluation, and deployment. The catalogue entries provide rules, skills, and integrations for working with this framework.

ArcadeAI/arcade-mcp · 1,019 stars · on GitHub · docs.arcade.dev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/arcadeai/arcade-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ArcadeAI/arcade-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for arcade-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arcadeai/arcade-mcp/claude-md.svg)](https://agentmods.dev/instructions/arcadeai/arcade-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arcadeai/arcade-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/arcadeai/arcade-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,698 This file is loaded in full into every session.
When invoked 4,698 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.04698 $0.04698
Opus 5 $0.02349 $0.02349
Sonnet 5 $0.00940 $0.00940
Haiku 4.5 $0.00470 $0.00470

Measured 6d ago against content hash 4957c1e34773, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

arcade-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

Arcade MCP is a Python platform for building tool servers that speak two protocols from the same process:

  1. MCP (Model Context Protocol) — the open standard for AI tool integration (JSON-RPC 2.0 over stdio or HTTP+SSE). Used by Claude Desktop, Cursor, VS Code, etc.
  2. Arcade Worker — Arcade's internal REST+JWT protocol for managed tool execution by the Arcade Engine (/worker/* endpoints).

Both protocols share the same tool catalog. A single MCPApp definition serves both.

Monorepo with 5 interdependent libraries and a CLI. Python 3.10+. Build system: Hatchling. Package manager: uv (always use uv run, never bare pip or python).

Commands

Task Command
Install all packages make install (runs uv sync --extra all --extra dev + pre-commit install)
Run all lib tests make test
Run a single test uv run pytest libs/tests/core/test_toolkit.py::TestClass::test_method
Lint + type check make check (pre-commit + mypy per-lib)
Build all wheels make build

Library Dependency Graph

arcade-core          (base: config, errors, catalog, schema, auth definitions, telemetry)
├── arcade-tdk       (@tool decorator, error adapter chain, auth providers)
├── arcade-serve     (Arcade Worker protocol: /worker/* REST endpoints, JWT auth, OpenTelemetry)
│   └── arcade-mcp-server  (MCPApp, MCPServer, Context, transports, resource server auth)
│       └── arcade-mcp CLI (typer-based: new, login, configure, deploy, server, secret, evals)
└── arcade-evals     (evaluation framework, critics, test suites)

Each lib under libs/arcade-*/ has its own pyproject.toml and version, except arcade-cli and arcade-evals which use the root pyproject.toml. The root pyproject.toml defines the uv workspace members and the arcade CLI entry point.

Versioning Rules

Read the full file on GitHub · 303 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 303 lines · 4,698 tokens per session scan A 4957c1e34773

Subscribe to this mod's changes

arcade-mcp CLAUDE.md is an instructions file published in the GitHub repository ArcadeAI/arcade-mcp (1,019 stars, last pushed yesterday), licensed MIT. It adds 4,698 tokens to every session, about $0.0235 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.