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>
102 lines
3.1 KiB
Python
102 lines
3.1 KiB
Python
"""Formatters for evaluation and capture results output."""
|
|
|
|
from difflib import get_close_matches
|
|
|
|
from arcade_cli.formatters.base import CaptureFormatter, EvalResultFormatter
|
|
from arcade_cli.formatters.html import CaptureHtmlFormatter, HtmlFormatter
|
|
from arcade_cli.formatters.json import CaptureJsonFormatter, JsonFormatter
|
|
from arcade_cli.formatters.markdown import CaptureMarkdownFormatter, MarkdownFormatter
|
|
from arcade_cli.formatters.text import CaptureTextFormatter, TextFormatter
|
|
|
|
# Registry of available formatters for evaluations
|
|
FORMATTERS: dict[str, type[EvalResultFormatter]] = {
|
|
"txt": TextFormatter,
|
|
"md": MarkdownFormatter,
|
|
"html": HtmlFormatter,
|
|
"json": JsonFormatter,
|
|
}
|
|
|
|
# Registry of available formatters for capture mode
|
|
CAPTURE_FORMATTERS: dict[str, type[CaptureFormatter]] = {
|
|
"json": CaptureJsonFormatter,
|
|
"txt": CaptureTextFormatter,
|
|
"md": CaptureMarkdownFormatter,
|
|
"html": CaptureHtmlFormatter,
|
|
}
|
|
|
|
|
|
def get_formatter(format_name: str) -> EvalResultFormatter:
|
|
"""
|
|
Get a formatter instance by name.
|
|
|
|
Args:
|
|
format_name: The format name (e.g., 'txt', 'md').
|
|
|
|
Returns:
|
|
An instance of the appropriate formatter.
|
|
|
|
Raises:
|
|
ValueError: If the format is not supported. Suggests similar format names if available.
|
|
"""
|
|
formatter_class = FORMATTERS.get(format_name.lower())
|
|
if formatter_class is None:
|
|
supported = list(FORMATTERS.keys())
|
|
|
|
# Try to find a close match for better error messages
|
|
close_matches = get_close_matches(format_name.lower(), supported, n=1, cutoff=0.6)
|
|
|
|
error_msg = f"Unsupported format '{format_name}'."
|
|
if close_matches:
|
|
error_msg += f" Did you mean '{close_matches[0]}'?"
|
|
error_msg += f" Supported formats: {', '.join(supported)}"
|
|
|
|
raise ValueError(error_msg)
|
|
return formatter_class()
|
|
|
|
|
|
def get_capture_formatter(format_name: str) -> CaptureFormatter:
|
|
"""
|
|
Get a capture formatter instance by name.
|
|
|
|
Args:
|
|
format_name: The format name (e.g., 'json', 'txt', 'md', 'html').
|
|
|
|
Returns:
|
|
An instance of the appropriate formatter.
|
|
|
|
Raises:
|
|
ValueError: If the format is not supported. Suggests similar format names if available.
|
|
"""
|
|
formatter_class = CAPTURE_FORMATTERS.get(format_name.lower())
|
|
if formatter_class is None:
|
|
supported = list(CAPTURE_FORMATTERS.keys())
|
|
|
|
close_matches = get_close_matches(format_name.lower(), supported, n=1, cutoff=0.6)
|
|
|
|
error_msg = f"Unsupported capture format '{format_name}'."
|
|
if close_matches:
|
|
error_msg += f" Did you mean '{close_matches[0]}'?"
|
|
error_msg += f" Supported formats: {', '.join(supported)}"
|
|
|
|
raise ValueError(error_msg)
|
|
return formatter_class()
|
|
|
|
|
|
__all__ = [
|
|
# Eval formatters
|
|
"FORMATTERS",
|
|
"EvalResultFormatter",
|
|
"HtmlFormatter",
|
|
"JsonFormatter",
|
|
"MarkdownFormatter",
|
|
"TextFormatter",
|
|
"get_formatter",
|
|
# Capture formatters
|
|
"CAPTURE_FORMATTERS",
|
|
"CaptureFormatter",
|
|
"CaptureHtmlFormatter",
|
|
"CaptureJsonFormatter",
|
|
"CaptureMarkdownFormatter",
|
|
"CaptureTextFormatter",
|
|
"get_capture_formatter",
|
|
]
|