arcade-mcp/libs/arcade-mcp-server/arcade_mcp_server/middleware/logging.py
Eric Gustin 3424ec8219
MCP Local (#563)
Versions:
* arcade-mcp\==1.0.0rc1
* arcade-mcp-server\==1.0.0rc1
* arcade-core\==2.5.0rc1
* arcade-tdk\==2.6.0rc1
* arcade-serve\==2.2.0rc1

### Summary
Adds first-class MCP support across Arcade, introduces a new MCP server
and CLI, unifies the project under the arcade-mcp name, overhauls
templates/scaffolding, and improves developer tooling, secrets
management, and examples.

### Highlights
- **MCP Server & Core**
- New MCP server with stdio and HTTP/SSE transports, session management,
resumability, and lifecycle handling.
- FastAPI-like `MCPApp` for building servers with lazy init; integrated
worker+MCP HTTP app option.
- Middleware system (logging and error handling), robust exception
hierarchy, and Pydantic-based settings.
- Async-safe managers for tools, resources, and prompts backed by
registries and locks.
- Developer-facing, transport-agnostic runtime context interfaces (logs,
tools, prompts, resources, sampling, UI, notifications).
- Conversion from Arcade ToolDefinition to MCP tool schema; OpenAI JSON
tool schema converter.
  - Parser supports `@app.tool`/`@app.tool(...)` decorators.

- **CLI**
  - New `mcp` command to run MCP servers with stdio or HTTP/SSE.
- New `secret` command to set/list/unset tool secrets (supports .env
input, preserves original casing for lookups).
- `new` command refactored; option to create a full toolkit package with
scaffolding.
  - `chat` command removed.
- `serve.py` imports updated to `arcade_serve.fastapi.telemetry`;
version retrieval now uses `arcade-mcp`.
  - `show.py` refactor to use new local catalog utilities.
- `display_tool_details` improved: adds “Default” column and handles
nested properties.

- **Configuration & Discovery**
- New `configure.py` to set up Claude Desktop, Cursor, and VS Code to
connect to local or Arcade Cloud MCP servers.
- Discovery utilities to find/install toolkits, build `ToolCatalog`s,
analyze files for tools, load kits from directories (pyproject parsing),
and build minimal toolkits.
- Better handling of provider API key resolution and evaluation suite
loading.

- **Templates & Scaffolding**
- Reorganized template structure (minimal vs full); moved
`.pre-commit-config.yaml`, `.ruff.toml`, license, Makefile, README,
tests, and tools layout to correct paths.
  - Minimal template adds `.env.example` for runtime secret injection.
- Template pyproject updated for MCP servers; includes sample server
with greeting and secret-reveal tools.
  - Authorization flow in templates simplified.

- **Repo-wide Renaming & Examples**
- Migrates references from `arcade-ai` to `arcade-mcp` across READMEs,
scripts, and package metadata.
- Examples updated (LangChain/LangGraph/AI SDK/TypeScript) and package
name changed to `arcade-mcp-sdk`.

- **Evals & Core Utilities**
- Evals now use OpenAI tooling format (`OpenAIToolList`, `to_openai`);
`tool_eval` takes `provider_api_key`.
- Core utilities: fixed `does_function_return_value` by dedenting before
parse; version bump to `2.5.0rc1` and dependency cleanup.

- **Tooling & CI**
- `setup-uv-env` action splits toolkit vs contrib dependency
installation.
- Pre-commit: excludes `libs/arcade-mcp-server/mkdocs.yml` and
`libs/tests/` from YAML and Ruff hooks; Ruff per-file ignores (e.g.,
C901 in `libs/**/*.py`, TRY400 in server docs paths).
- Makefile updates for uv env setup, quality checks, tests, builds, and
new `shell` target.
  - Added Makefile to MCP server library to streamline dev workflow.

- **Cleanup**
  - Removed `claude.json` config.
- Simplified stdio entrypoint; removed unused imports (`arcade_gmail`,
`arcade_search`).

### Breaking Changes
- **CLI**: `chat` command removed; use `mcp`, `secret`, and updated
`new`.
- **Naming**: All users should update references from `arcade-ai` to
`arcade-mcp`.
- **Templates**: File paths moved; downstream scripts referencing old
template locations may need updates.

### Getting Started
- Run an MCP server:
  - `arcade mcp --stdio --toolkits your_toolkit`
  - `arcade mcp --http --toolkits your_toolkit`
- Manage secrets:
  - `arcade secret set your_toolkit KEY=value`
  - `arcade secret list your_toolkit`
  - `arcade secret unset your_toolkit KEY`
- Configure clients:
- `arcade configure` to set up Claude Desktop, Cursor, and VS Code for
local/Arcade Cloud MCP.

---------

Co-authored-by: Sam Partee <sam@arcade-ai.com>
Co-authored-by: Shub <125150494+shubcodes@users.noreply.github.com>
2025-09-25 15:28:15 -07:00

121 lines
3.6 KiB
Python

"""Logging middleware for MCP server."""
import logging
import time
from typing import Any
from arcade_mcp_server.middleware.base import CallNext, Middleware, MiddlewareContext
logger = logging.getLogger("arcade.mcp")
class LoggingMiddleware(Middleware):
"""Middleware that logs all MCP messages and timing information."""
def __init__(self, log_level: str = "INFO"):
"""Initialize logging middleware.
Args:
log_level: The log level to use for message logging
"""
self.log_level = getattr(logging, log_level.upper(), logging.INFO)
async def on_message(
self,
context: MiddlewareContext[Any],
call_next: CallNext[Any, Any],
) -> Any:
"""Log all messages with timing information."""
start_time = time.time()
# Log the incoming message
self._log_request(context)
try:
# Process the message
result = await call_next(context)
except Exception as e:
# Log error
elapsed = time.time() - start_time
self._log_error(context, e, elapsed)
raise
else:
# Log success
elapsed = time.time() - start_time
self._log_response(context, result, elapsed)
return result
def _log_request(self, context: MiddlewareContext[Any]) -> None:
"""Log incoming request."""
if not logger.isEnabledFor(self.log_level):
return
method = context.method or "unknown"
msg_type = context.type
# Build log message
parts = [f"[{msg_type.upper()}]", f"method={method}"]
if context.request_id:
parts.append(f"request_id={context.request_id}")
if context.session_id:
parts.append(f"session_id={context.session_id}")
# Log message details based on method
if hasattr(context.message, "params"):
params = getattr(context.message, "params", None)
if params:
if hasattr(params, "name"):
parts.append(f"name={params.name}")
elif hasattr(params, "uri"):
parts.append(f"uri={params.uri}")
logger.log(self.log_level, " ".join(parts))
def _log_response(
self,
context: MiddlewareContext[Any],
result: Any,
elapsed: float,
) -> None:
"""Log response with timing."""
if not logger.isEnabledFor(self.log_level):
return
method = context.method or "unknown"
elapsed_ms = int(elapsed * 1000)
# Build log message
parts = ["[RESPONSE]", f"method={method}", f"elapsed={elapsed_ms}ms"]
if context.request_id:
parts.append(f"request_id={context.request_id}")
# Add result info based on type
if isinstance(result, list):
parts.append(f"count={len(result)}")
elif hasattr(result, "content"):
content = getattr(result, "content", [])
if isinstance(content, list):
parts.append(f"content_blocks={len(content)}")
logger.log(self.log_level, " ".join(parts))
def _log_error(
self,
context: MiddlewareContext[Any],
error: Exception,
elapsed: float,
) -> None:
"""Log error with timing."""
method = context.method or "unknown"
elapsed_ms = int(elapsed * 1000)
parts = ["[ERROR]", f"method={method}", f"elapsed={elapsed_ms}ms"]
if context.request_id:
parts.append(f"request_id={context.request_id}")
parts.append(f"error={type(error).__name__}: {error!s}")
logger.error(" ".join(parts))