MCP Server Framework and Tool Development library for building custom capabilities into agents.
ed89af4b4d
# Backwards-compatible refactoring of the Slack toolkit Several performance improvements, streamlined tool set, and easier to understand tool interfaces. All "old" tools were kept for backwards compatibility, with the same interfaces and response structure (but using the new and more performant tools under the hood). Full revision of unit-tests and evals. ## Streamlined tool set Multiple groups of tools were streamlined into a single one: * "get conversation metadata" from 5 tools to one; * "send message" from 2 tools to one; * "get users in conversation" from 3 tools to one; * "get messages" from 4 tools to one ## New capabilities * Messages retrieved are now populated with the users' names, apart from ID: makes it easier for LLMs to reference who sent a message, were mentioned, or reacted to a message * Retrieve users by username, email, and/or ID (before we only supported ID) * Retrieve multiple users in a single tool call ## Concurrency controls All operations issuing multiple requests concurrently now have a `Semaphore` to limit the concurrency level. The limit can be controlled through the `SLACK_MAX_CONCURRENT_REQUESTS` env var (defaults to 3). ## Networking performance improvement Various operations that used to make multiple API calls are now executed more efficiently: ### Find users by username * Before: a full scan of `users_list` was required (potentially multiple pages for large workspaces); * Now it stops as soon as we have all users needed (yes, it was dumb before) ### Get multiple users by their IDs * Before: for each user ID, we made one API call to the `users_info` endpoint * Now: we call `list_users` and scan the results to match the user IDs (an estimate of 99.5% of Slack workspaces have < 200 users; for large workspaces, we may need to paginate `list_users`) ### Get a conversation by its users * Before: * Call to `list_conversations` (potentially paginating) * For each conversation, one call to `conversations_members` (potentially paginating) * Then loop and find which conversation matches the users' IDs * Now: * A single call to `conversations_open` |
||
|---|---|---|
| .github | ||
| .vscode | ||
| contrib | ||
| docker | ||
| examples | ||
| libs | ||
| porter | ||
| schemas/preview | ||
| toolkits | ||
| .editorconfig | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| .prettierignore | ||
| .prettierrc.toml | ||
| .ruff.toml | ||
| CONTRIBUTING.md | ||
| cspell.config.yaml | ||
| LICENSE | ||
| Makefile | ||
| pyproject.toml | ||
| README.md | ||
| worker.toml | ||
Documentation • Tools • Quickstart • Contact Us
Arcade AI Platform
Arcade is a developer platform that lets you build, deploy, and manage tools for AI agents.
This repository contains the core Arcade libraries, organized as separate packages for maximum flexibility and modularity:
- arcade-core - Core platform functionality and schemas | Source code |
pip install arcade-core| - arcade-tdk - Tool Development Kit with the
@tooldecorator | Source code |pip install arcade-tdk| - arcade-serve - Serving infrastructure for workers and MCP servers | Source code |
pip install arcade-serve| - arcade-evals - Evaluation framework for testing tool performance | Source code |
pip install 'arcade-ai[evals]| - arcade-cli - Command-line interface for the Arcade platform | Source code |
pip install arcade-ai|
To learn more about Arcade.dev, check out our documentation.
Pst. hey, you, give us a star if you like it!
Quick Start
Installation
For development, install all packages with dependencies using uv workspace:
# Install all packages and dev dependencies
uv sync --extra all --dev
# Or use the Makefile (includes pre-commit hooks)
make install
For production use, install individual packages as needed:
pip install arcade-ai # CLI
pip install 'arcade-ai[evals]' # CLI + Evaluation framework
pip install 'arcade-ai[all]' # CLI + Serving infra + eval framework + TDK
pip install arcade_serve # Serving infrastructure
pip install arcade-tdk # Tool Development Kit
Development
Use the Makefile for standard tasks:
# Run tests
make test
# Run linting and type checking
make check
# Build all packages
make build
# See all available commands
make help
Client Libraries
-
ArcadeAI/arcade-py: The Python client for interacting with Arcade.
-
ArcadeAI/arcade-js: The JavaScript client for interacting with Arcade.
-
ArcadeAI/arcade-go: The Go client for interacting with Arcade.
Support and Community
- Discord: Join our Discord community for real-time support and discussions.
- GitHub: Contribute or report issues on the Arcade GitHub repository.
- Documentation: Find in-depth guides and API references at Arcade Documentation.