70515e3356
## Summary
Adds two strictly opt-in env vars that let toolkit developers see
`developer_message` / `stacktrace` content *in* the agent-facing error
message while debugging. Off by default; activation requires a specific
acknowledgement string, not a boolean — `true`/`1` is explicitly
rejected with a warning log.
- `ARCADE_UNSAFE_DEBUG_LEAK_DEVELOPER_MESSAGE_TO_AGENT`
- `ARCADE_UNSAFE_DEBUG_LEAK_STACKTRACE_TO_AGENT`
- Magic ack: `yes-i-accept-leaking-internals-to-the-agent`
Everything goes through a single funnel — `ToolOutputFactory.fail` /
`fail_retry` in `arcade_core/output.py` — so the behavior covers both
the MCP server path and the Arcade Worker path with no call-site
changes. A loud `logger.warning` fires once per process on activation,
and a big header comment in `output.py` tells future maintainers not to
add more flags of this shape (debug info belongs in `logger.debug`, not
in a field that gets shipped to the model and often to end users).
Bumps `arcade-core` 4.6.2 → 4.7.0. Non-breaking, additive.
## Why
Today the project does a lot of work to keep `developer_message` and
`stacktrace` off the agent's context. That's the right default, but it
makes iterating on a new toolkit painful — you end up adding temporary
logging or rebuilds just to see what blew up. This gives toolkit authors
a safe, ugly, loud-on-activation escape hatch.
## Safety design
- Two separate flags so you only leak what you need.
- Magic string (not a boolean) activates the flag. Boolean-style values
are rejected and log a pointer to `output.py`.
- First activation logs a `WARNING` identifying the flag and the risk.
- Flags documented only in `CLAUDE.md`, not in the public README.
- Top-of-file banner in `output.py` explicitly tells maintainers not to
add more flags of this shape.
## Test plan
- [x] Existing test suite passes (1154 tests —
`libs/tests/{core,tool,arcade_mcp_server}`).
- [x] End-to-end smoke test against the built `arcade_core-4.7.0` wheel,
driven through `ToolExecutor.run` (same path toolkits hit). Covered
cases:
- flags off → message unchanged
- `ARCADE_UNSAFE_..._DEVELOPER_MESSAGE_TO_AGENT=true` → flag rejected,
warning logged, message unchanged
- `ARCADE_UNSAFE_..._DEVELOPER_MESSAGE_TO_AGENT=<magic>` → `[DEBUG]
developer_message: ...` appended
- both flags with magic, `ToolRuntimeError` path → developer_message
appended (stacktrace absent because `ToolRuntimeError.stacktrace()`
returned `None`, which is existing behavior)
- stacktrace flag with magic, generic `Exception` path → full
`traceback.format_exc()` appended, activation `WARNING` visible
Made with [Cursor](https://cursor.com)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Adds an opt-in path to include `developer_message` and stacktraces in
agent-facing MCP error messages, which could leak sensitive data if
misconfigured; safeguards (magic ack string + CI/pre-commit guard)
reduce but don’t eliminate risk.
>
> **Overview**
> Adds `arcade_mcp_server/_debug_exposure.py` with two env-gated debug
flags that, only when set to a specific acknowledgement string, append
`developer_message` and/or `stacktrace` into the agent-visible MCP tool
error `message` (and logs one-shot warnings on rejection/activation).
>
> Wires this into the MCP error path in `MCPServer._handle_call_tool`,
documents the flags in `CLAUDE.md`, bumps `arcade-mcp-server` to
`1.21.0`, and adds unit + integration tests plus a pre-commit hook and
GitHub Actions workflow (`scripts/check_debug_leak_flags_off.py`) to
ensure the magic ack string can’t be committed outside a small
allowlist.
>
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit
30e242c454128ec7cc62e169c2afd116be735cb5. Bugbot is set up for automated
code reviews on this repo. Configure
[here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
|
||
|---|---|---|
| .. | ||
| arcade_mcp_server | ||
| Makefile | ||
| pyproject.toml | ||
| README.md | ||
Arcade MCP Server
Arcade MCP (Model Context Protocol) Server enables AI assistants and development tools to interact with your Arcade tools through a standardized protocol. Build, deploy, and integrate MCP servers seamlessly across different AI platforms.
Quick Links
- Quickstart Guide - Get up and running in minutes
- Walkthrough - Learn by example
- API Reference - MCPApp API documentation
Features
- 🚀 FastAPI-like Interface - Simple, intuitive API with
MCPApp - 🔧 Tool Discovery - Automatic discovery of tools in your project
- 🔌 Multiple Transports - Support for stdio and HTTP/SSE
- 🤖 Multi-Client Support - Works with Claude, Cursor, and more
- 📦 Package Integration - Load installed Arcade packages
- 🔐 Built-in Security - Environment-based configuration and secrets
- 🔄 Hot Reload - Development mode with automatic reloading
- 📊 Production Ready - Deploy with Docker, systemd, PM2, or cloud platforms
Getting Started
Installation
pip install arcade-mcp-server
Create Your First Server
from arcade_mcp_server import MCPApp
from typing import Annotated
app = MCPApp(name="my-tools", version="1.0.0")
@app.tool
def greet(name: Annotated[str, "Name to greet"]) -> str:
"""Greet someone by name."""
return f"Hello, {name}!"
if __name__ == "__main__":
app.run()
Run Your Server
# For development
python my_tools.py
# For Claude Desktop
python -m arcade_mcp_server stdio
# For HTTP clients
python -m arcade_mcp_server --host 0.0.0.0 --port 8080
Community
Analytics & Privacy
Arcade MCP Server collects anonymous usage data to help us improve the service and debug issues. We track "MCP server start" events to understand server usage patterns and reliability.
What We Track
When the server starts, we collect the following information:
- Server configuration: transport type (
httporstdio), host, port - Server metadata: tool count, server version
- Runtime environment: Python version, OS type and release
- Timing: device timestamp
- Errors: error messages (if startup fails)
Privacy
- For anonymous users: Events are tracked with an anonymous ID and no user profile is created
- For authenticated users: Events are linked to your account to help us provide better support
- No sensitive data (credentials, tool inputs/outputs, or personal information) is ever collected
Opt Out
To disable usage tracking, set the environment variable ARCADE_USAGE_TRACKING to 0.
License
Arcade MCP Server is open source software licensed under the MIT license.