98fad93d21
# MCP Server Tool Evaluation Support
## Overview
Add support for evaluating tools from remote MCP servers without
requiring Python callables. Enables direct evaluation of any
MCP-compatible tool server.
## What's New
### Core Features
- **`MCPToolRegistry`**: Evaluate tools from a single MCP server
- **`CompositeMCPRegistry`**: Evaluate tools from multiple MCP servers
simultaneously
- **Automatic loaders**: `load_from_stdio()` and `load_from_http()` to
fetch tools from running servers
- **Automatic namespacing**: Tools prefixed with server name (e.g.,
`server_tool_name`)
- **Smart name resolution**: Use short names if unique, full names if
ambiguous
- **OpenAI strict mode**: Automatic schema conversion prevents parameter
hallucinations
### Usage
**Automatic Loading:**
```python
from arcade_evals import load_from_stdio, MCPToolRegistry
# Load tools automatically from MCP server
tools = load_from_stdio(["npx", "-y", "@modelcontextprotocol/server-github"])
registry = MCPToolRegistry(tools)
```
**Single MCP Server:**
```python
from arcade_evals import MCPToolRegistry, ExpectedToolCall
registry = MCPToolRegistry(mcp_tools)
suite = EvalSuite(catalog=registry)
suite.add_case(
expected_tool_calls=[
ExpectedToolCall(tool_name="tool_name", args={...})
]
)
```
**Multiple MCP Servers:**
```python
from arcade_evals import CompositeMCPRegistry, load_from_stdio
# Load from multiple servers
github_tools = load_from_stdio(["npx", "-y", "@modelcontextprotocol/server-github"])
slack_tools = load_from_stdio(["npx", "-y", "@modelcontextprotocol/server-slack"])
composite = CompositeMCPRegistry(
tool_lists={
"github": github_tools,
"slack": slack_tools,
}
)
suite = EvalSuite(catalog=composite)
suite.add_case(
expected_tool_calls=[
ExpectedToolCall(tool_name="github_list_issues", args={...})
]
)
```
## Implementation
### Files Changed
- **`libs/arcade-evals/arcade_evals/registry.py`** (NEW): Registry
abstractions and implementations
- **`libs/arcade-evals/arcade_evals/loaders.py`** (NEW): Automatic tool
loading from MCP servers
- **`libs/arcade-evals/arcade_evals/eval.py`** (MODIFIED): Enhanced
`ExpectedToolCall` and evaluation logic
- **`libs/arcade-evals/arcade_evals/__init__.py`** (MODIFIED): Exported
new registries and loaders
### Key Technical Details
- Added `BaseToolRegistry` interface for abstraction
- `MCPToolRegistry` handles single server tools
- `CompositeMCPRegistry` manages multiple servers with collision
detection
- `load_from_stdio()` and `load_from_http()` for automatic tool
discovery
- Fixed name normalization bug: MCP tools use underscores (not dots)
- Optimized tool copying: 2.5x faster via shallow copy
## Testing
- ✅ 41 tests passing (25 new tests added)
- ✅ `test_eval_mcp_registry.py`: MCPToolRegistry functionality
- ✅ `test_eval_composite_mcp.py`: CompositeMCPRegistry with multiple
servers
- ✅ Verified backward compatibility with Python tools
## Backward Compatibility
✅ **100% backward compatible** - No breaking changes
## Breaking Changes
**None**
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Adds end-to-end eval UX: examples, a robust CLI runner, and rich
outputs.
>
> - **New examples**: `eval_arcade_gateway.py`,
`eval_stdio_mcp_server.py`, `eval_http_mcp_server.py`,
`eval_comprehensive_comparison.py` with timeouts, error handling, and
track-based comparisons; detailed `README.md`
> - **CLI runner**: `arcade_cli/evals_runner.py` to execute
evals/capture in parallel with progress, error isolation, failed-only
filtering, context inclusion, and multi-provider/model support
> - **Output formatters**: `arcade_cli/formatters/` (txt, md, html,
json) for evals and capture; comparative and multi-model HTML with tabs
and context rendering
> - **Display refactor**: `display.py` now supports writing multiple
formats, failed-only disclaimers, include-context, and improved console
summaries
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
ff8acf9c34a6b61462a019a1ee9df081006517d0. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Francisco Liberal <francisco@arcade.dev>
Co-authored-by: Mateo Torres <torresmateo@gmail.com>
79 lines
2.9 KiB
Python
79 lines
2.9 KiB
Python
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
from arcade_cli.main import cli
|
|
from arcade_core.constants import PROD_ENGINE_HOST
|
|
from typer.testing import CliRunner
|
|
|
|
runner = CliRunner()
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"args, expected_url",
|
|
[
|
|
([], f"https://{PROD_ENGINE_HOST}/dashboard"),
|
|
(["--local"], "http://localhost:9099/dashboard"),
|
|
(["--host", "custom.host.com"], "https://custom.host.com/dashboard"),
|
|
(["-h", "api.arcade.dev", "-p", "9099"], "https://api.arcade.dev:9099/dashboard"),
|
|
(["--local", "--port", "9099"], "http://localhost:9099/dashboard"),
|
|
(["--local", "--tls"], "https://localhost:9099/dashboard"),
|
|
(["--no-tls"], f"http://{PROD_ENGINE_HOST}/dashboard"),
|
|
],
|
|
)
|
|
def test_dashboard_url_construction(args, expected_url):
|
|
"""Test that the dashboard command constructs the correct URL with various args."""
|
|
with (
|
|
patch("webbrowser.open") as mock_open,
|
|
patch("arcade_cli.utils.validate_and_get_config") as mock_validate,
|
|
patch("arcade_cli.main.log_engine_health") as mock_health_check,
|
|
):
|
|
# Setup mocks
|
|
mock_open.return_value = True # Successfully opened browser
|
|
mock_validate.return_value = MagicMock()
|
|
mock_health_check.return_value = None # Successful health check
|
|
|
|
# Run command
|
|
result = runner.invoke(cli, ["dashboard", *args])
|
|
|
|
assert result.exit_code == 0
|
|
mock_open.assert_called_once_with(expected_url)
|
|
mock_health_check.assert_called_once()
|
|
|
|
|
|
def test_fallback_when_browser_fails():
|
|
"""Test fallback message when browser.open fails."""
|
|
with (
|
|
patch("webbrowser.open") as mock_open,
|
|
patch("arcade_cli.utils.validate_and_get_config") as mock_validate,
|
|
patch("arcade_cli.main.log_engine_health") as mock_health_check,
|
|
patch("arcade_cli.main.console.print") as mock_print,
|
|
):
|
|
mock_open.return_value = False # Failed to open browser
|
|
mock_validate.return_value = MagicMock()
|
|
mock_health_check.return_value = None
|
|
|
|
result = runner.invoke(cli, ["dashboard"])
|
|
|
|
assert result.exit_code == 0
|
|
mock_print.assert_any_call(
|
|
f"If a browser doesn't open automatically, copy this URL and paste it into your browser: https://{PROD_ENGINE_HOST}/dashboard",
|
|
style="dim",
|
|
)
|
|
|
|
|
|
def test_health_check_success():
|
|
"""Test successful health check."""
|
|
with (
|
|
patch("webbrowser.open") as mock_open,
|
|
patch("arcade_cli.utils.validate_and_get_config") as mock_validate,
|
|
patch("arcade_cli.main.log_engine_health") as mock_health_check,
|
|
):
|
|
mock_open.return_value = True
|
|
mock_validate.return_value = MagicMock()
|
|
mock_health_check.return_value = None # Successful health check
|
|
|
|
result = runner.invoke(cli, ["dashboard"])
|
|
|
|
assert result.exit_code == 0
|
|
mock_health_check.assert_called_once()
|
|
mock_open.assert_called_once()
|