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>
## Summary
Updated the Mastra example project to include leveraging multiple
toolkits into one Mastra agent. Additionally, the `package.json`
versions were pinned to the latest versions to avoid potential issues
with breaking changes as Mastra progresses through v0.x.x packages.
Also, by pinning the version, it demonstrates the latest confirmed
arcade-js compatibility version.
These changes were initiated when trying to debug an
[issue](https://github.com/ArcadeAI/arcade-ai/issues/560) using Arcade
toolkits with Mastra agents. Notably, I confirmed that there is no flaw
in arcade-js, which was suspected in the issue, by successfully using
the toolkits with the latest Mastra packages.
## Changes
* inboxTravelAgent created showcasing `GoogleFlights`, `GoogleHotels`,
and `Gmail` Arcade toolkits together
* package.json versions pinned to the latest working versions.
## Testing
Ran the Mastra project locally and invoked the tools via the agent chat
interface.
### 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>
Update our example with the latest version of `arcade-js`. This means we
can delete all the utility functions we created here, since we now have
first-class `Zod` support and they are no longer needed.
> [!WARNING]
> Don't merge until this
[PR](https://github.com/ArcadeAI/arcade-js/pull/127) is merged.
MCP stdio Implementation:
The PR adds support for standard input/output (stdio) as a transport
mechanism for the Message Control Protocol. This is a replacement to the
SSE (Server-Sent Events) transport that was worked on in PR #359 but
will not be merged as it's not deprecated.
This will allow developers to use Arcade tools (written by the dev or
Arcade) in Claude, Cursor, windsurf, etc.
The engine Gateway already supports adding HTTPS streamable (replacement
for SSE) MCP servers as tool servers, and will soon support full gateway
capability in the client API as well.
To use any existing Toolkit just
## Examples
### Quickstart setup with existing toolkits
```bash
pip install arcade-ai
pip install <name of toolkit> # ex. arcade-google
arcade serve --mcp
```
### Run with Claude
Just add the following to the Claude config
```json
{
"mcpServers": {
"arcade": {
"command": "bash",
"args": ["-c", "export ARCADE_API_KEY=arc_xxxx && /path/to/python /path/to/arcade serve --mcp"]
}
}
}
```
### Customizing the Tool Server
Developers can customize their served tools and server furthermore by
importing the worker sdk
```python
import arcade_google # pip install arcade_google
import arcade_search # pip install arcade_search
from arcade.core.catalog import ToolCatalog
from arcade.worker.mcp.stdio import StdioServer
# 2. Create and populate the tool catalog
catalog = ToolCatalog()
catalog.add_module(arcade_google) # Registers all tools in the package
catalog.add_module(arcade_search)
# 3. Main entrypoint
async def main():
# Create the worker with the tool catalog
worker = StdioServer(catalog)
# Run the worker
await worker.run()
if __name__ == "__main__":
import asyncio
asyncio.run(main())
```
Then to run with claude, just run this python file instead of the prebuilt server used in ``arcade serve --mcp``
This PR adds a new example showcasing how to integrate Arcade tools with
LangGraph.js to create a ReAct agent. The example is based on the
[LangChain React Agent
JS](https://github.com/langchain-ai/react-agent-js/tree/main)
repository.
It is unnecessary to call `arcadeClient.tools.list` first and then
`arcadeClient.tools.formatted.get` for each tool. We can simply use the
`arcadeClient.tools.formatted.list` function.
Small update to reflect some changes to the `langchain-arcade` package
in the last release.
---------
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
- **New Class Structure**: Introduced `ToolManager` and
`AsyncToolManager` classes (`ArcadeToolManager` is deprecated)
- **Async Support**: Full async implementation for modern LangChain
applications
- **Better Tool Management**: New methods for adding individual tools
and toolkits
- **CI/CD**: for langchain_arcade
## Upgrade Changes
```python
# Old pattern
manager = ArcadeToolManager(api_key="...")
tools = manager.get_tools(toolkits=["Google"])
# New pattern
manager = ToolManager(api_key="...")
manager.init_tools(toolkits=["Google"])
tools = manager.to_langchain()
```
Now supports underscores vs dots in tool names for better model
compatibility.
# CrewAI Integration
crewai-arcade enables you to add Arcade tools and Arcade Auth into your
CrewAI applications. Just create an `ArcadeToolManager` and add your
tools to your CrewAI Agent/Tasks.
## Initializing the ArcadeToolManager
There are two main ways to initialize your `ArcadeToolManager`
1. Default handling of tool authorization and execution:
```py
"""
When you provide a user id to the ArcadeToolManger,
it will handle the tool authorization and tool execution for you
"""
manager = ArcadeToolManager(default_user_id="me@example.com,
api_key="...")
```
2. Custom handling of tool authorization and execution
```py
"""
Provide a callback function to the `ArcadeToolManager` that handles
tool authorization and tool execution. The callback function will be
called whenever your CrewAI
application wants to call a tool.
"""
def custom_tool_executor(
manager: ArcadeToolManager, tool_name: str, **tool_input: dict[str, Any]
) -> Any:
"""Custom tool executor for the ArcadeToolManager
ArcadeToolManager's default executor handles authorization and tool
execution.
This function overrides the default executor to handle authorization and
tool execution
in a custom way.
"""
# Your custom tool auth logic goes here
# Your custom tool execution logic goes here
...
manager = ArcadeToolManager(executor=custom_tool_executor,
api_key="...")
```
## Tool Registration
1. Initialize the tools in the manager
```py
"""
Clears any existing tools in the manager and replaces them with tools
and toolkits that are provided.
"""
manager.init_tools(tools=["Google.ListEmails"], toolkits=["Slack"])
```
2. Add tools to the manager
```py
"""
Adds tools and toolkits to the manager's internal tool list.
"""
manager.add_tools(tools=["Google.ListEmails"], toolkits=["Slack"])
```
3. Retrieve tools and toolkits from the manager
```py
"""
Retrieves the provided tools and toolkits as CrewAI StructuredTools.
"""
manager.get_tools(tools=["Google.ListEmails"], toolkits=["Slack"])
```
## Auth Helpers
The `ArcadeToolManager` provides multiple helper methods for when you
need to create
a custom auth flow.
1. `authorize_tool` handles the whole authorization flow for you. This
is used internally when a custom auth flow is not needed.
2. `requires_auth(tool_name)` checks if the provided tool has
authorization requirements.
3. `authorize(tool_name, user_id)` authorizes the use of the provided
tool for the provided user ID
4. `is_authorized(tool_name, user_id)` checks if a tool is authorized
for use by the provided user ID
5. `wait_for_auth(auth_response)` waits for an authorization process to
complete before returning
## Tool Execution Helpers
1. `execute_tool` handles the whole tool execution flow for you. This is
used internally when a custom tool execution flow is not needed.
---------
Co-authored-by: lgesuellip <lgesuellipinto@uade.edu.ar>
Co-authored-by: lpetralli <123559656+lpetralli@users.noreply.github.com>
Co-authored-by: lgesuellip <102637283+lgesuellip@users.noreply.github.com>
Co-authored-by: “lgesuellip” <“lgesuellipinto@uade.edu.ar”>
## PR Description
Changes `pip install 'arcade-ai[fastapi]'` to `pip install arcade-ai`.
In other words, FastAPI is now a required dependecy of arcade-ai.
Additionally, I snuck in some minor cleanup changes.
# PR Description
* This PR updates code in `examples/` to be compatible with version
1.0.0
* This PR removes the Spotify examples since the Arcade hosted worker
doesn't currently cataloge the Spotify toolkit. We can reintroduce these
examples when it does.
* This PR performs various renames across the codebase for
`arcade-ai.com` --> `arcade.dev` and `Arcade AI` --> `Arcade`
This PR updates the LangChain Arcade integration to v1.0.0, making the
following key changes:
• Bumped the package version in pyproject.toml from 0.2.0 to 1.0.0.
• Changed the default parameter in ArcadeToolManager from
langgraph=False to langgraph=True.
• Updated dependencies to require langgraph≥0.2.67,<0.3.0 and simplified
extras.
• Adjusted example scripts to remove explicit authorization_url
references in favor of a unified URL field.
• Updated docs and environment references to align with new usage
patterns and emphasize environment variables.
These changes unify and streamline the LangGraph-based tooling while
ensuring compatibility with the latest 1.0.0 release.
This PR enhances the Docker build and deployment process for the Arcade
Worker by:
- **Modularizing Docker Builds:**
- Introduces a new `INSTALL_TOOLKITS` build argument in the `Dockerfile`
to conditionally include toolkits. this enables the creation of a
`arcadeai/worker-base` which can be used to build custom containers in a
multi-stage build. an example of this is included in the example dir.
- Adds `docker-base` Makefile target to build a lightweight base image
without toolkits.
- **Publishing to GitHub Container Registry (GHCR):**
- Adds Makefile targets `publish-ghcr` and `gh-login` for pushing images
to GHCR.
- Supports publishing both base and full images with toolkits to GHCR.
- **Docker Compose:**
- Add Docker compose file and setup
- Renames the `actor` service to `worker`
- Adds an `nginx` service in `docker-compose.yml` to proxy requests to
the Arcade Engine.
- Introduces an `nginx.conf` file for the Nginx service.
- **Streamlining Toolkit Installation:**
- Moves toolkit installation from the `start.sh` script to the Docker
build process.
- Creates a `toolkits.txt` file to manage toolkit dependencies which can
be edited easily when we want to add a new toolkit. Developers can also
use this approach as shown in the example.
- **Improving Configuration Files:**
- Updates `docker.engine.yaml` and `env.example` to align with the new
setup.
TODO:
- CI/CD needs to be adjusted so that images are pushed to ghcr on
release.
- AWS resources need to be renamed actor -> worker @EricGustin
This can go in after the above two items are resolved.
---------
Co-authored-by: Wils Dawson <wils@arcade-ai.com>
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
Co-authored-by: sdreyer <sterling@arcade-ai.com>
Co-authored-by: Sterling Dreyer <sdreyer21@gmail.com>
Co-authored-by: Nate Barbettini <nathanaelb@gmail.com>
**PR Description**
This update bumps the integration’s version to `0.2.0` and brings
several important changes to how `langchain-arcade` interfaces with
Arcade tools:
1. **Updated Tool Definition Imports**
• Replaces `arcadepy.types.shared.ToolDefinition` with
`arcadepy.types.ToolGetResponse as ToolDefinition`.
• The parameter extraction is now done via `tool_def.input.parameters`
instead of the previous `tool_def.inputs.parameters`.
2. **Authorization Flow Adjustments**
• Uses `auth_response.url` instead of `auth_response.authorization_url`.
• The `authorize` and `is_authorized` methods now rely on the Arcade
client’s updated arguments (`client.auth.status(id=authorization_id)`).
3. **Tool Execution Parameter Renaming**
• The `execute` method now expects `input=kwargs` instead of
`inputs=kwargs`, aligning with Arcade’s new API spec.
4. **Tool Retrieval Enhancements**
• `_retrieve_tool_definitions` is revised to better handle pagination
and tool listing (including when no tools/toolkits are explicitly
provided).
5. **Version & Dependency Updates**
• Increases `langchain-arcade` to `0.2.0`.
• Switches `arcadepy` dependency to `~1.0.0rc1`.
• Updates example requirements to consume
`langchain-arcade[langgraph]>=0.2.0`.
These changes may affect existing code that relies on older parameter
names (`inputs.parameters` → `input.parameters`) and the renamed execute
argument. Please ensure any integrations or custom usage of Arcade tools
is updated accordingly.
Refactor toolkit implementation examples following the removal of two
Spotify tools in
[PR#196](https://github.com/ArcadeAI/arcade-ai/pull/196), due to Spotify
API deprecation announcement.
## PR Description
This PR adds 7 examples.
* `call_a_tool_directly_with_auth.py` - Simple example that uses Arcade
client to execute a tool that lists Gmail emails
* `call_a_tool_directly.py` - Simple example that uses Arcade client to
execute a tool that adds two numbers together
* `call_a_tool_with_llm.py` - Simple example that uses the LLM api to
star the arcade-ai repository
* `get_auth_token.py` - Simple example that gets a Google auth token and
then calls the Google API
* `call_multiple_tools_directly_with_auth.py` - A more involved example
that directly calls multiple spotify tools sequentially
* `call_multiple_tools_with_llm.py` - A more involved example that uses
an llm to call multiple spotify tools sequentially
* `simple_chatbot.py` - Simple chatbot that uses arcade tools and has
history
---------
Co-authored-by: Nate Barbettini <nathanaelb@gmail.com>
Fixes a circular import issue where `arcade.sdk -> arcade.core` but also
`arcade.core -> arcade.sdk`. My mistake!
Moved some of the shared classes down into `core`, and re-exported them
to `sdk` to keep the expected interface for devs.
This PR ensures that `arcade.core` does not show up anywhere in "user
space". This is crucial for helping developers understand what objects
are safe to use, and helps maintain a good developer experience.
Specific changes:
- `ToolAuthorizationContext` and `ToolContext` are now visible via
`arcade.sdk`
- `ToolCatalog` is now visible via `arcade.sdk`
- `Toolkit` is now visible via `arcade.sdk`
- `config` is now visible via `arcade.sdk.config`
```
authors = ["Arcade AI <dev@arcade-ai.com>"]
```
vs
```
authors = ["Arcade AI <dev@arcade-ai.com"]
```
There is also now a ``make`` command for ``make install-toolkits``
On the last few PRs I have noticed two problems:
1. `ruff format` fails even though it seems OK on our local machines
(sometimes, not always)
2. Nate's and Sam's machines kept flip-flopping a specific piece of
formatting back and forth, indicating a subtle difference of config
hiding somewhere
3. This was reproducible by running `ruff format` in the terminal,
followed by `make check`. The former would edit files, and then `make
check` would edit them back!
This PR addresses both issues, and further standardizes our editor &
linter configs to be super stable.
Specifically:
1. The main fix for the above, the pre-commit hook was pinned to a super
old version of ruff.
This resulted in subtle differences in behavior between our machines,
and on CI.
2. Moved ruff settings from `pyproject.toml` to `.ruff.toml`
pyproject files in subdirectories (e.g. `toolkits/**`) were overriding
the main pyproject file and erasing the custom ruff config we set at the
root. This meant that our ruff config was applied to `arcade` but not to
any of the other packages.
By moving the config to `.ruff.toml` at the root, all projects will
inherit the same ruff linting & formatting config.
4. Un-ignored the `.vscode/` directory so that we can share
vscode/cursor workspace settings.
This is valuable for standardizing settings like the default formatter
(ruff) and default test framework (pytest).
However, it's important that going forward we _only_ commit things here
that should apply across all of our machines.
5. To avoid any conflict between prettier and ruff, prettier now
explicitly ignores *.py files
6. Finally, `ruff format` and `make check` agree. A number of files are
newly auto-formatted.
This PR includes several improvements to the Arcade client and adds
LangGraph examples:
1. Enhanced error handling in the Arcade client:
- Improved HTTP error handling in `BaseArcadeClient`
- Simplified request methods in `SyncArcadeClient` and
`AsyncArcadeClient`
2. Updated `ToolResource` class:
- Changed base path from `/v1/tool` to `/v1/tools`
- Added `tool_version` parameter to `authorize` method
3. Improved Toolkit discovery:
- Updated `find_all_arcade_toolkits` to search only in the current
Python interpreter's site-packages
5. Added LangGraph examples:
- New `langgraph_auth.py` example demonstrating Gmail authentication
- New `langgraph_with_tool_exec.py` example showing tool execution
within a LangGraph
6. Minor updates:
- Changed default `BASE_URL` to `https://api.arcade.com/`
- Updated import error message for eval dependencies
---------
Co-authored-by: Nate Barbettini <nate@arcade-ai.com>
In this PR:
- Handle and require fully-qualified tool names `Toolkit.ToolName` in
the actor
Also, unrelated changes/fixes:
- Cleaned up the logic around actor secrets and `$ARCADE_ACTOR_SECRET`
- Removes experimental Flask actor for now
Note: Must be merged along with
https://github.com/ArcadeAI/Engine/pull/87
* Renamed `arcade_arithmetic` to `arcade_math`
* Deleted `arcade_github` toolkit for the next release. This will be
reintroduced later.
* Added 5 tools to `arcade_x` toolkit
- post_tweet
- delete_tweet_by_id
- search_recent_tweets_by_username
- search_recent_tweets_by_keywords
- lookup_single_user_by_username
# PR Description
## Summary
Changes include renaming the `arcade_gmail` toolkit to `arcade_google`,
adding unit tests for Google toolkit, add new tools to the Google
toolkit.
## Changes
### Makefile
- Added a new `make test-toolkits` target to iterate over all toolkits
and run pytest on each one.
### Added new tools for the google toolkit
1. `send_email`
This tool sends an email using the Gmail API.
2. `write_draft_email`
This tool creates a draft email using the Gmail API.
3. `update_draft_email`
This tool updates an existing draft email using the Gmail API.
4. `send_draft_email`
This tool sends a draft email using the Gmail API.
5. `delete_draft_email`
This tool deletes a draft email using the Gmail API.
6. `list_draft_emails`
This tool retrieves a list of draft emails using the Gmail API.
7. `list_emails_by_header`
This tool searches for emails by a specific header using the Gmail API.
- `sender`: The sender's email address to search for.
- `limit`: The maximum number of emails to retrieve.
8. `list_emails`
This tool retrieves a list of emails using the Gmail API.
9. `trash_email`
This tool moves an email to the trash using the Gmail API.
