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>
This PR adds a simplified Linear toolkit focused on core functionality:
## What's Included
**Tools:**
- `get_issue` - Get detailed information about Linear issues
- `get_teams` - Get team information and details
**Models:**
- `DateRange` enum with comprehensive date range support (TODAY,
YESTERDAY, THIS_WEEK, LAST_WEEK, THIS_MONTH, LAST_MONTH, THIS_YEAR,
LAST_YEAR, LAST_7_DAYS, LAST_30_DAYS)
- Timezone-aware datetime handling following Google toolkit patterns
## What's Simplified
This toolkit has been streamlined by removing:
- Cycles management tools
- Projects management tools
- Users management tools
- Workflows management tools
- Corresponding tests and evaluations for removed features
## Quality Assurance
- All linting and formatting checks pass
- Comprehensive test coverage for included functionality
- Follows established patterns from Google toolkit
---------
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
# PR Description
## Split toolkits
This PR splits the `Microsoft`, `Google`, and `Search` toolkits into
multiple toolkits each.
* `Microsoft` --> `OutlookCalendar`, `OutlookMail`.
* `Google` -----> `GoogleCalendar`, `GoogleContacts`, `GoogleDocs`,
`GoogleDrive`, `Gmail`, `GoogleSheets`
* `Search` -----> `GoogleFinance`, `GoogleFlights`, `GoogleHotels`,
`GoogleJobs`, `GoogleMaps`, `GoogleNews`, `GoogleSearch`,
`GoogleShopping`, `Walmart`, `Youtube`
> The original monolithic toolkits (`Microsoft`, `Google`, `Search`) are
not removed in this PR. The plan is to keep those toolkits around while
we
> 1. Stop documenting the toolkits,
> 2. Stop displaying the toolkits in the dashboard, and
> 3. Help customers migrate over to the new split toolkits.
## Rename toolkits
This PR renames the following toolkits
* `Web` ------------> `Firecrawl`
* `CodeSandbox` ---> `E2B`
> The `Web` and `CodeSandbox` toolkits are not removed in this PR. The
plan is to keep them around while we
> 1. Stop documenting the toolkits,
> 2. Stop displaying the toolkits in the dashboard, and
> 3. Help customers migrate over to the new renamed toolkits.
## Rename tools
Since toolkit names were changed, this called for some tools to be
renamed as well.
* `GoogleSearch.SearchGoogle` ----------------> `GoogleSearch.Search`
* `GoogleShopping.SearchShoppingProducts` --->
`GoogleShopping.SearchProducts`
* `Walmart.SearchWalmartProducts` ------------> `Walmart.SearchProducts`
* `Walmart.GetWalmartProductDetails` --------->
`Walmart.GetProductDetails`
* `Youtube.SearchYoutubeVideos` -------------->
`Youtube.SearchForVideos`
## Google File Picker
Improvements to the Google File Picker experience were also added in
this PR.
The following tools will ALWAYS provide llm_instructions in their
response to "let the end-user know that they have the option to select
more files via the file picker url if they want to":
* `GoogleDocs.SearchDocuments`
* `GoogleDocs.SearchAndRetrieveDocuments`
* `GoogleDrive.GetFileTreeStructure`
The following tools will only provide the file picker URL if a 404 or
403 from the Google API:
* `GoogleDocs.InsertTextAtEndOfDocument`
* `GoogleDocs.GetDocumentById`
* `GoogleSheets.GetSpreadsheet`
* `GoogleSheets.WriteToCell`
Also, a standalone `GoogleDrive.GenerateGoogleFilePickerUrl` tool
exists.
## Other
* The `SearchDocuments` and `SearchAndRetrieveDocuments` tools used to
be organized within the Drive portion of the Google toolkit, but I moved
these into the new GoogleDocs toolkit because they are specific to Docs.
# Progress
- [x] `OutlookCalendar`
- [x] `OutlookMail`
- [x] `GoogleFinance`
- [x] `GoogleFlights`
- [x] `GoogleHotels`
- [x] `GoogleJobs`
- [x] `GoogleMaps`
- [x] `GoogleNews`
- [x] `GoogleSearch`
- [x] `GoogleShopping`
- [x] `Walmart`
- [x] `Youtube`
- [x] `GoogleCalendar`
- [x] `GoogleContacts`
- [x] `GoogleDocs`
- [x] `GoogleDrive`
- [x] `Gmail`
- [x] `GoogleSheets`
- [x] `Firecrawl`
- [x] `E2B`
- [x] File picker
# Discussion
* Repeated code is a consequence of splitting toolkits that use the same
provider. I am open to any ideas that would allow multiple toolkits to
reference common code. Comment your ideas in this PR.
1. Patch, Minor, or Major is selected during workflow dispatch (defaults
to patch)
2. Get most recent release version
3. Calculate new version based on findings from step 2
4. Build wheels
5. Build worker and base-worker
6. Push to GHCR
7. Create new release with release notes
Also, I removed everything related to ECR
This is the first of a few PRs. Deploy to staging will fail until we
have `arcade-core`, `arcade-serve`, and `arcade-ai` released to PyPI.
This PR will release `arcade-core` to PyPI.
### PR Description
* Adds workflow that checks for changes in any pyproject.toml, and if
its version has changed, then tests, builds wheel, then publishes to
PyPI
* Updates the Dockerfile for our new structure
* Updates porter yamls
* Updates `make full-dist`
* Removes a couple unused workflows
Check out https://github.com/ArcadeAI/arcade-ai/actions/runs/15622059209
to see how the new workflow works (note that it failed publishing to
PyPI on purpose)
12 tools for the new Confluence toolkit.
| Name | Description |
|----------------------------------|------------------------------------------------------------------------------------|
| Confluence.CreatePage | Create a new page at the root of the given
space. |
| Confluence.UpdatePageContent | Update a page's content. |
| Confluence.RenamePage | Rename a page by changing its title. |
| Confluence.GetPage | Retrieve a SINGLE page's content by its ID or
title. |
| Confluence.GetPagesById | Get the content of MULTIPLE pages by their
ID in a single efficient request. |
| Confluence.ListPages | Get the content of multiple pages by their ID.
|
| Confluence.ListAttachments | List attachments in a workspace. |
| Confluence.GetAttachmentsForPage | Get attachments for a page by its
ID or title. |
| Confluence.SearchContent | Search for content in Confluence. |
| Confluence.GetSpace | Get the details of a space by its ID or key. |
| Confluence.ListSpaces | List all spaces sorted by name in ascending
order. |
| Confluence.GetSpaceHierarchy | Retrieve the full hierarchical
structure of a Confluence space as a tree structure.|
### Confluence Clients
Confluence has deprecated most of their V1 endpoints, so most of the
tools use V2. However, we still need a V1 client to support search. The
V1 search API has not been deprecated yet, because there is no V2
equivalent. But we need to be aware in the future for when this
deprecation happens.
### Future work
* Content of pages are returned in the Confluence `storage` format. This
is the format that Confluence uses to store pages internally. We should
understand the storage format more deeply, and write utility function to
transform this format into plain text.
* Better protections against extremely large pages. I've tested up to
6,000 word pages.
* Tools for blog posts
* Tool for getting the children of a page. (`get_space_hierarchy` will
suffice for now)
* Allow for numerical titles
Add hot-reload capability
adds watchfiles dependency and changes uvicorn server logic
but does not have any breaking changes.
---------
Co-authored-by: Eric Gustin <eric@arcade.dev>
Co-authored-by: sdreyer <sterling@arcade-ai.com>
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
The Asana toolkit is not published yet, so it cannot be added to the
worker's toolkit list. This is causing container build/publish on main
branch to fail.
Reviewer:
1. DM me to get a client ID/secret for the Hubspot app and login
credentials for a sample Hubspot account
2. For now, you'll need to run the engine on the branch
`nate/token-introspection` for the auth flow to work with Hubspot
3. Add the following to `auth.providers` in your engine yaml:
```yaml
- id: arcade-hubspot
description: 'Hubspot provider'
enabled: true
type: oauth2
provider_id: hubspot
client_id: ${env:HUBSPOT_CLIENT_ID}
client_secret: ${env:HUBSPOT_CLIENT_SECRET}
```
## 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.
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>
This PR improves the Docker build process by shifting from building the
project within the Docker image to using pre-built wheels. The main
changes are:
1. **Updated Makefile:**
- **`VERSION` Variable:** Set to `0.1.0.dev0` to reflect the new default
development version.
- **`docker` Target:**
- Added steps to build the Arcade and toolkit wheels before building the
Docker image.
- Exports the required extras (`fastapi`, `evals`) to a
`requirements.txt` file.
- **`full-dist` Target:**
- Builds distributions for the main project and all toolkits.
- Copies all the built wheels to a centralized `./dist` directory.
- **`clean-dist` Target:**
- Cleans build artifacts from `./dist`, `arcade/dist`, and
`toolkits/*/dist` directories.
2. **Modified Dockerfile:**
- **Copy Pre-built Wheels:** Adjusted to copy wheels and the
`requirements.txt` from the `./dist` directory into the Docker image.
- **Installation Process:**
- Installs the Arcade wheel with the necessary extras.
- Installs toolkits from the copied wheel files, eliminating the need to
build them inside the Docker image.
- **Simplification:** Removed unnecessary commands, such as installing
build tools and copying the entire codebase, to streamline the
Dockerfile.
3. **Toolkits `pyproject.toml` Updates:**
- Changed the `arcade-ai` dependency version from `^0.1.0` to `0.1.*` in
all toolkit `pyproject.toml` files to ensure compatibility with the new
versioning scheme.
4. **Docker Makefile Adjustments:**
- Set the `VERSION` variable to `0.1.0.dev0` to align with the main
Makefile.
- Ensures consistent versioning across Docker-related build processes.
**Benefits:**
- **Efficiency:** Building wheels outside the Docker context reduces the
Docker image build time and resource consumption. overall docker image
size reduced by **1Gb**!!!
- **Reliability:** Using pre-built wheels ensures consistency across
different environments and simplifies dependency management.
- **Maintainability:** The Dockerfile and Makefiles are cleaner and more
straightforward, making them easier to understand and maintain.
**Notes:**
- Developers should run `make docker` to build and run the Docker
container using the new process.
- Ensure that any CI/CD pipelines are updated to accommodate these
changes in the build process. @sdreyer
