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.
Borrowing it
Nothing to install: this file belongs to ArcadeAI/arcade-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ArcadeAI/arcade-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ArcadeAI/arcade-mcpWrote 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.
[](https://agentmods.dev/instructions/arcadeai/arcade-mcp/claude-md)<a href="https://agentmods.dev/instructions/arcadeai/arcade-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/arcadeai/arcade-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04709 | $0.04709 |
| Opus 5.5 | $0.01884 | $0.01884 |
| Sonnet 5.5 | $0.00942 | $0.00942 |
| Haiku 4.5 | $0.00471 | $0.00471 |
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 15d 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.
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:
- 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.
- 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
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.
- 15d ago Changed · +4 tokens per session cfd190d5b720
- 1mo ago Changed · +7 tokens per session 911f4d2efbc5
- 2mo ago First seen · 303 lines · 4,698 tokens per session scan A 4957c1e34773
arcade-mcp CLAUDE.md is an instructions file published in the GitHub repository ArcadeAI/arcade-mcp (1,064 stars, last pushed today), licensed MIT. It adds 4,709 tokens to every session, about $0.0188 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.