Sandbox
Sign in
@alDuncanson/Handler
Tools#Any agent#Coding#Testing#Research

A2A protocol client for the terminal

Handler lets you work with A2A services from the command line. You can inspect an agent card, send messages, and use the TUI for interactive sessions, while the MCP server lets other agents call into A2A services.

45 stars•5 forks•Python•Updated 8d ago
Who it's for

Builders who want a terminal client for A2A agents and services.

What it delivers

You can inspect, message, and integrate with A2A services without leaving the terminal.

What it does

Interactive TUI

Open a terminal UI with `handler tui` to talk to an A2A agent and view its card and responses.

Scriptable CLI

Use commands like `handler card get --url http://localhost:8000` and `handler message send --url URL --text "hello"` for automated workflows.

MCP server

Expose A2A access through MCP so other agents can integrate with A2A services directly.

A2A auth and config

Supports global and repo-scoped A2A server configuration with bearer token, API key, mTLS, and OAuth2 client credentials auth.

Docs command

Open the built-in documentation from the CLI with `handler docs`.

How to get it

  1. 1Install Handler from the PyPI package as a uv tool
    uv tool install a2a-handler
  2. 2Or with pipx
    pipx install a2a-handler
  3. 3Or with pip
    pip install a2a-handler
  4. 4Open the interactive terminal UI
    handler tui
  5. 5Inspect an A2A server's agent card
    handler card get --url http://localhost:8000
  6. 6Send a message from the CLI
    handler message send --url URL --text "hello"

README

Handler

CI A2A Protocol PyPI version PyPI - Status Pepy total downloads GitHub stars

Handler is an open-source A2A protocol client for software engineers building, testing, and operating agentic systems. It provides an interactive TUI, a scriptable CLI with structured output, and an MCP server that lets other agents integrate with A2A services directly. Handler also supports global and repo-scoped A2A server configuration with bearer, API key, mTLS, and OAuth2 client credentials auth.

Handler TUI connected to an A2A agent, showing the agent card and a completed assistant response

Install

Install Handler from the PyPI package as a uv tool:

uv tool install a2a-handler

Or with pipx:

pipx install a2a-handler

Or with pip:

pip install a2a-handler

Quick Start

Open the interactive terminal UI:

handler tui

Inspect an A2A server's agent card:

handler card get --url http://localhost:8000

Send a message from the CLI:

handler message send --url URL --text "hello"

Open the full documentation:

handler docs

Run Without Installing

Run Handler with uvx:

uvx --from a2a-handler handler

Run Handler with pipx:

pipx run a2a-handler

Documentation

Read the documentation at https://handler.alduncanson.com.

Files in the repo

Repository payload•16 top-level entries
  • .github
  • assets
  • docs
  • src
  • tests
  • .actrc
  • .gitignore
  • AGENTS.md
  • CONTRIBUTING.md
  • flake.lock
  • flake.nix
  • justfile
  • LICENSE
  • pyproject.toml
  • README.md
  • uv.lock

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More tools

JuliusBrussee/
caveman
JuliusBrussee/cavemanTools

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

105k
1 add
MemPalace/
mempalace
MemPalace/mempalaceTools

The best-benchmarked open-source AI memory system. And it's free.

59k
stablyai/
orca
stablyai/orcaTools

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

66k
farion1231/cc-switchTools

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

132k
diegosouzapw/OmniRouteTools

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

64k
headroomlabs-ai/
headroom
headroomlabs-ai/headroomTools

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

71k