MCP Server Framework and Tool Development library for building custom capabilities into agents.
30739dc44a
Adds `Jira.GetAvailableAtlassianClouds` tool, which provides a list of clouds available (checking which Clouds were actually authorized by the current auth token). Refactors the interface of every tool to accept an `atlassian_cloud_id` argument (when not provided, try to get a unique cloud ID - if multiple are available, raises a Retryable error with the list of Clouds available instructing to select one). Gets rid of all caching. Now storing the global semaphore to the context object. The global semaphore is important because some tools depend on others, and each tool instantiates its own Jira HTTP client. Storing the semaphore in the context object ensures that all HTTP clients will respect the concurrency limit. Removes from tool responses the Atlassian URLs linking to objects in the Jira GUI (users, projects, issues, etc. We do not keep track of the cloud name anymore, which is required to build the objects' URLs. Extends/refactors unit tests accordingly. Evals checking LLM behavior when: - a cloud ID is explicitly mentioned in the prompt; - no cloud ID is mentioned; - a "multiple clouds available" error is raised and the user is prompted to pick one; - user request triggers another tool call after having previously picked a cloud ID (in the same chat context); |
||
|---|---|---|
| .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.