LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
PluginRisingofficial publisher

Goose (Block) et ses extensions MCP

Plugin : A set of capabilities installed into an AI application or a host · requires goose

Block's open source agent, extensible via MCP servers, running on your machine.

The best MCP-native agent outside Anthropic, free and local.

Official site GitHub · 55,666 ★
Overall score
7.3 /10
Security: one caveat, see the card
Utility
7.0
Reliability
10.0
Security
One caveat
Ease
5 min · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Managing repetitive tasks on your computer, automating workflows, or interacting with external tools often means juggling multiple applications. Goose centralises these actions into a single agent that runs directly on your machine, without sending your data to a forced third-party service.

Goose works as an autonomous agent: you give it an instruction in plain language, and it chains the necessary steps to complete it, whether that involves writing code, doing research, analysing data, or automating tasks. It connects to over 70 extensions via the open MCP protocol and supports more than 15 model providers, including Anthropic, OpenAI, Google, Ollama, and Azure. You can use your own API key or a local model.

Goose is aimed at developers, technical professionals, and advanced users who want to automate complex tasks on their machine without depending on a closed cloud subscription. It is available as a desktop app on macOS, Linux, and Windows, as well as via the command line.

It is less suited to users looking for a ready-to-use tool with no configuration, or those who are not comfortable managing API keys and enabling extensions. Actions executed on the machine through activated extensions require careful attention to the permissions granted.

What it offers

  • ·Autonomous natural-language agent capable of chaining multiple steps to complete coding, research, writing, or automation tasks.
  • ·Compatibility with more than 15 model providers: Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, Bedrock, and others.
  • ·Connection to over 70 extensions via the open Model Context Protocol (MCP) standard.
  • ·Native desktop app for macOS, Linux, and Windows, plus a full command-line interface.
  • ·Built-in API allowing Goose to be embedded in other applications or workflows.
  • ·Support for local models via Ollama, with no data sent to external servers.
  • ·Ability to create custom distributions with preconfigured providers, extensions, and branding.
  • ·Open source project under the Apache 2.0 licence, hosted at the Linux Foundation via the Agentic AI Foundation (AAIF).

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
macos, linux, windows, cli
Host
goose
Licence
Apache-2.0
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Your data
Data stays local
Maintenance
Active
Last release
23 October 2026

Links and repository checked on 25 October 2026 · added on 1 January 2025

How to install Goose (Block) et ses extensions MCP

1. Go to the official installation page: https://goose-docs.ai/docs/getting-started/installation 2. Download the desktop app for your system (macOS, Linux, or Windows) or install the CLI using the provided command. 3. Launch Goose and configure your model provider: enter your API key (Anthropic, OpenAI, etc.) or connect a local model via Ollama. 4. Enable only the MCP extensions you need, checking the permissions each one requires on your machine. 5. Consult the diagnostics section of the documentation if you encounter any issues before seeking further help.
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash

In the same category

Whole category Orchestrate →