4 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Eric Gustin
|
e727af3a21
|
Fix MCP capabilities, examples, tests, and more (#657)
# PR Description
Consider this PR the result of a full pass through of this repository.
## Add helper for adding tools to an `MCPApp`
You can now add all of the tools in a module to an `MCPApp` via
`app.add_tools_from_module(...)`
## Edit what `arcade new` generates
First, I updated the backend to use hatchling.
Second, the structure generated before this PR was simple, but did not
create a proper Python module.
This hindered developers in the following ways:
1. Difficult to add the tools in your server to an evaluation suite
2. Difficult to add more than one tool to an MCPApp at a time
3. All other niceties that come with being able to import modules
```
# Before
server/
├── .env.example
├── server.py
└── pyproject.toml
```
This PR updates the structure generated such that a valid Python module
is generated:
```
# After
server/
├── pyproject.toml
└── src/
└── server/
├── __init__.py
├── .env.example
└── server.py
```
## Fix Tool Chaining
`self._ctx.server.executor.run(...)` was being called, but `MCPServer`
does not have an instance of `ToolExecutor` (and it's not intended to be
an instance anyways). I updated `Tool.call_raw` to pass the programmatic
tool call through the `MCPServer._handle_call_tool`. This means that the
programmatic tool calls now go through the same steps that a typical
tool call (initiated by the MCP client) would.
This means that **toolA**, which specifies **requirementsA**, is
permitted to call **toolB**, which specifies **requirementsB**, without
needing to explicitly declare or satisfy **requirementsB**. I believe
this is acceptable because the secrets and/or auth token associated with
**toolB's** `Context` are not exposed to **toolA**, and the secrets
and/or auth token associated with **toolA's** `Context` are not exposed
to **toolB**.
## Fix User Elicitation
1. The read & write streams were created with a maximum queue size of 0.
I increased this to 100.
2. I updated `ServerSession`'s run loop to both read messages from the
stream & process them concurrently. This enables server initiated
requests (like user elicitation and progress reporting) to be handled
while tools are being executed. Otherwise, the server initiated requests
would wait for the tool to finish executing and the tool execution would
wait for the server initiated request to finish.
3.
## Fix Progress Reporting
Progress tokens sent by the client were not being stored. Therefore
there was no way to notify a client with progress updates. I am now
storing the `progressToken`, along with other `_meta` sent from the
client, in the `ServerSession`'s `_request_meta`. I am setting
`_request_meta` whenever the `MCPServer` is handling an incoming message
from a client.
## Fix handling of server names with spaces
Before:
Server name: "The simple server name"
Tool name: whisper_secret
Name seen by client: "The_simple_server_name_WhisperSecret"
After
Server name: "The simple server name"
Tool name: whisper_secret
Name seen by client: "TheSimpleServerName_WhisperSecret"
## Add Integration Tests
The stdio integration test is much more comprehensive than the http
integration test. These tests will let me sleep a bit more at night
## Add Example MCP Servers
Example servers for sampling, user-elicitation, progress reporting,
logging, tool chaining, combining prebuilt tools with custom tools, tool
secrets, tool auth, evaluations, and more!
## Add Docker template
Added a Docker template for running an MCP server in Docker (and removed
the old docker stuff)
|
||
|
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> |
||
|
Sam Partee
|
27a6cd31a3
|
Support Tool Output in ValueSchema of ToolDefinition (#487)
## Before
### Tool: ``GoogleNews.SearchNewsStories``
```python
@tool(requires_secrets=["SERP_API_KEY"])
async def search_news_stories(
context: ToolContext,
keywords: Annotated[
str,
"Keywords to search for news articles. E.g. 'Apple launches new iPhone'.",
],
country_code: Annotated[
CountryCode | None,
"2-character country code to search for news articles. "
"E.g. 'us' (United States). "
f"Defaults to '{DEFAULT_GOOGLE_NEWS_COUNTRY}'.",
] = None,
language_code: Annotated[
LanguageCode,
"2-character language code to search for news articles. E.g. 'en' (English). "
f"Defaults to '{DEFAULT_GOOGLE_NEWS_LANGUAGE}'.",
] = DEFAULT_GOOGLE_NEWS_LANGUAGE,
limit: Annotated[
int | None,
"Maximum number of news articles to return. Defaults to None "
"(returns all results found by the API).",
] = None,
) -> Annotated[dict[str, Any]]:
"""Search for news articles related to a given query."""
...
```
### Tool Definition: ``GoogleNews.SearchNewsStories``
```
{
"name": "SearchNewsStories",
"fully_qualified_name": "GoogleNews.SearchNewsStories",
"description": "Search for news articles related to a given query.",
"toolkit": {
"name": "GoogleNews",
"description": "Arcade.dev LLM tools for getting new via Google News",
"version": "2.0.0"
},
"input": {
"parameters": [
{
"name": "keywords",
"required": true,
"description": "Keywords to search for news articles. E.g. 'Apple launches new iPhone'.",
"value_schema": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
},
"inferrable": true
},
{
"name": "country_code",
"required": false,
"description": "2-character country code to search for news articles. E.g. 'us' (United States). Defaults to 'None'.",
"value_schema": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
},
"inferrable": true
},
{
"name": "language_code",
"required": false,
"description": "2-character language code to search for news articles. E.g. 'en' (English). Defaults to 'en'.",
"value_schema": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
},
"inferrable": true
},
{
"name": "limit",
"required": false,
"description": "Maximum number of news articles to return. Defaults to None (returns all results found by the API).",
"value_schema": {
"val_type": "integer",
"inner_val_type": null,
"enum": null,
},
"inferrable": true
}
]
},
"output": {
"description": "News search results with article details.",
"available_modes": [
"value",
"error"
],
"value_schema": {
"val_type": "json"
}
},
"requirements": {
"authorization": null,
"secrets": [
{
"key": "serp_api_key"
}
],
"metadata": null
},
"deprecation_message": null
},
```
## After
### Enhanced Tool: ``GoogleNews.SearchNewsStories``
```python
"""Type definitions for Google News API responses and parameters."""
from typing_extensions import TypedDict
CountryCode = str
LanguageCode = str
class SearchNewsParams(TypedDict):
"""Input parameters for searching news articles."""
keywords: str
"""Search query terms to find relevant news articles \
(e.g., 'Apple launches new iPhone')."""
country_code: CountryCode | None
"""Optional 2-letter country code to filter news by region \
(e.g., 'us' for United States, 'uk' for United Kingdom)."""
language_code: LanguageCode | None
"""Optional 2-letter language code to filter news by language \
(e.g., 'en' for English, 'es' for Spanish)."""
limit: int | None
"""Optional maximum number of news articles to return. \
If not specified, returns all results from the API."""
class SourceInfo(TypedDict, total=False):
"""Information about the news source/publication."""
name: str
"""Name of the publication (e.g., 'CNN', 'BBC News', 'The New York Times')."""
icon: str
"""URL to the source's favicon or logo image."""
authors: list[str]
"""List of author names for the article, if available."""
class NewsResult(TypedDict, total=False):
"""Individual news article from the Google News API response."""
position: int
"""Ranking position of this result in the search results."""
title: str
"""Headline or title of the news article."""
link: str
"""Full URL to the original news article."""
source: SourceInfo
"""Information about the publication source."""
date: str
"""Publication date and time (e.g., '2 hours ago', 'Dec 15, 2023')."""
snippet: str
"""Brief excerpt or summary from the article content."""
thumbnail: str
"""URL to a high-resolution thumbnail image for the article."""
thumbnail_small: str
"""URL to a low-resolution thumbnail image for the article."""
story_token: str
"""Token for accessing full coverage of this news story across multiple sources."""
stories: list["NewsResult"]
"""Related news stories from other sources covering the same topic."""
highlight: dict
"""Additional highlighted information about the story."""
class SearchMetadata(TypedDict, total=False):
"""Metadata about the search request and processing."""
id: str
"""Unique identifier for this search request within SerpApi."""
status: str
"""Current processing status ('Processing', 'Success', or 'Error')."""
json_endpoint: str
"""URL to retrieve the JSON results for this search."""
created_at: str
"""Timestamp when the search request was created."""
processed_at: str
"""Timestamp when the search request was processed."""
google_news_url: str
"""Original Google News URL that would return these results."""
total_time_taken: float
"""Total time in seconds taken to process this search."""
class SearchParameters(TypedDict, total=False):
"""Parameters used for the search request."""
engine: str
"""Search engine used (always 'google_news' for this API)."""
q: str
"""Search query string."""
gl: str
"""Country code used for geographic filtering."""
hl: str
"""Language code used for language filtering."""
topic_token: str
"""Token for accessing specific news topics (e.g., 'World', 'Business', 'Technology')."""
publication_token: str
"""Token for accessing news from specific publishers."""
class MenuLink(TypedDict):
"""Navigation link for news categories or topics."""
title: str
"""Display text for the menu item (e.g., 'Technology', 'Sports', 'Business')."""
topic_token: str
"""Token to access this specific topic or category."""
serpapi_link: str
"""SerpApi URL to search within this topic."""
class TopStoriesLink(TypedDict):
"""Link to top stories section."""
topic_token: str
"""Token to access top stories."""
serpapi_link: str
"""SerpApi URL to retrieve top stories."""
class GoogleNewsResponse(TypedDict, total=False):
"""Complete response from the Google News API."""
search_metadata: SearchMetadata
"""Metadata about the search request and processing."""
search_parameters: SearchParameters
"""Parameters that were used for this search."""
news_results: list[NewsResult]
"""List of news articles matching the search criteria."""
menu_links: list[MenuLink]
"""Navigation links to different news categories and topics."""
top_stories_link: TopStoriesLink
"""Link to access top stories."""
title: str
"""Title of the page or topic being displayed."""
class SimplifiedNewsResult(TypedDict):
"""Simplified news article format for tool output."""
title: str
"""Headline of the news article."""
link: str
"""URL to the full article."""
source: str | None
"""Name of the publication source."""
date: str | None
"""When the article was published."""
snippet: str | None
"""Brief excerpt from the article."""
class SearchNewsOutput(TypedDict):
"""Output format for the search_news_stories tool."""
news_results: list[SimplifiedNewsResult]
"""List of news articles in simplified format."""
@tool(requires_secrets=["SERP_API_KEY"])
async def search_news_stories(
context: ToolContext,
keywords: Annotated[
str,
"Keywords to search for news articles. E.g. 'Apple launches new iPhone'.",
],
country_code: Annotated[
CountryCode | None,
"2-character country code to search for news articles. "
"E.g. 'us' (United States). "
f"Defaults to '{DEFAULT_GOOGLE_NEWS_COUNTRY}'.",
] = None,
language_code: Annotated[
LanguageCode,
"2-character language code to search for news articles. E.g. 'en' (English). "
f"Defaults to '{DEFAULT_GOOGLE_NEWS_LANGUAGE}'.",
] = DEFAULT_GOOGLE_NEWS_LANGUAGE,
limit: Annotated[
int | None,
"Maximum number of news articles to return. Defaults to None "
"(returns all results found by the API).",
] = None,
) -> Annotated[SearchNewsOutput, "News search results with article details."]:
"""Search for news articles related to a given query."""
...
```
### Enhanced Tool Definition: ``GoogleNews.SearchNewsStories``
```json
{
"name": "SearchNewsStories",
"fully_qualified_name": "GoogleNews.SearchNewsStories",
"description": "Search for news articles related to a given query.",
"toolkit": {
"name": "GoogleNews",
"description": "Arcade.dev LLM tools for getting new via Google News",
"version": "2.0.0"
},
"input": {
"parameters": [
{
"name": "keywords",
"required": true,
"description": "Keywords to search for news articles. E.g. 'Apple launches new iPhone'.",
"value_schema": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"inferrable": true
},
{
"name": "country_code",
"required": false,
"description": "2-character country code to search for news articles. E.g. 'us' (United States). Defaults to 'None'.",
"value_schema": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"inferrable": true
},
{
"name": "language_code",
"required": false,
"description": "2-character language code to search for news articles. E.g. 'en' (English). Defaults to 'en'.",
"value_schema": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"inferrable": true
},
{
"name": "limit",
"required": false,
"description": "Maximum number of news articles to return. Defaults to None (returns all results found by the API).",
"value_schema": {
"val_type": "integer",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"inferrable": true
}
]
},
"output": {
"description": "News search results with article details.",
"available_modes": [
"value",
"error"
],
"value_schema": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"news_results": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {
"title": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Headline of the news article."
},
"link": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "URL to the full article."
},
"source": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Name of the publication source."
},
"date": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "When the article was published."
},
"snippet": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Brief excerpt from the article."
}
},
"description": "List of news articles in simplified format."
}
},
"inner_properties": null,
"description": null
}
},
"requirements": {
"authorization": null,
"secrets": [
{
"key": "serp_api_key"
}
],
"metadata": null
},
"deprecation_message": null
},
```
---------
Co-authored-by: Eric Gustin <eric@arcade.dev>
|
||
|
Sam Partee
|
b6b4cd0a4c
|
🏗️ Restructure: Multi-Package Architecture + uv Migration (#412)
### Overview Major restructuring from monolithic `arcade-ai` package to modular library architecture with standardized uv-based dependency management.  ### New Package Structure - **`arcade-tdk`** - Lightweight toolkit development kit (core decorators, auth) - **`arcade-core`** - Core execution engine and catalog functionality - **`arcade-serve`** - FastAPI/MCP server components - **`arcade-ai`** - Meta package that includes CLI functionality. Optionally include evals via the `evals` extra. Optionally include all packages via the `all` extra. ### Key Benefits - **Lighter Dependencies**: Toolkits now depend only on `arcade-tdk` (~2 deps) vs full `arcade-ai` (~30+ deps) - **Faster Builds**: uv provides 10-100x faster dependency resolution and installation - **Better Modularity**: Clear separation of concerns, consumers import only what they need - **Standard Tooling**: Eliminates custom poetry scripts, uses standard Python packaging ### Migration Impact - All 20 toolkits converted from poetry → uv with `arcade-tdk` dependencies plus `arcade-ai[evals]` and `arcade-serve` dev dependencies. When developing locally, devs should install toolkits via `make install-local`. - Modern Python 3.10+ type hints throughout - Standardized build system with hatchling backend - Enhanced Makefile with robust toolkit management commands - Removed `arcade dev` CLI command - Reduce the number of files created by `arcade new` and add an option to not generate a tests and evals folder. This foundation enables faster development cycles and cleaner dependency chains for the growing toolkit ecosystem. ### Todo After this PR is merged - [ ] Post-merge workflow(s) (release & publish containers, etc) - [ ] Release order plan. @EricGustin suggests releasing in the following order: 1. `arcade-core` version 0.1.0 2. `arcade-serve` version 0.1.0 and `arcade-tdk` version 0.1.0 3. `arcade-ai` version 2.0.0 4. Patch release for all toolkits (all changes in toolkits are internal refactors) - [ ] [Update docs](https://github.com/ArcadeAI/docs/pull/318) --------- Co-authored-by: Eric Gustin <eric@arcade.dev> Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com> |
Renamed from arcade/arcade/core/utils.py (Browse further)