servers VS goose

Most agents don't speak raw HTTP — they speak MCP. So the real distribution surface is a tiny MCP server that exposes each endpoint as a tool and does the paying under the hood. The agent calls web_search(query); the server hits the paid endpoint, handles the 402 with its operator's wallet, returns JSON. One line to install:

The Model Context Protocol (MCP) is an open standard for connecting AI hosts (Claude, ChatGPT, Cursor, VS Code, and others) to external context and actions through a structured protocol instead of ad-hoc plugins.

Model Context Protocol specification

That changed when I built mpesa-mcp — a Model Context Protocol server that wraps the Daraja API and makes it directly available to Claude, GPT-4, and Gemini.

If you haven't run into it yet, MCP (Model Context Protocol) is an open standard for exposing tools to AI agents. two-go ships an MCP server that runs over stdio with no dependencies, no URL, no account, and no API key. It's all local.

MCP server surface. The CLI is already agent-friendly, so I'm double minded about whether a Model Context Protocol server would make integration smoother. I'm personally not a fan of MCP and prefer skills and CLIs.

As noted in the Model Context Protocol (MCP) Introduction, this protocol allows Claude to interact with systems like GitHub and local databases through a standardized interface.

Keep the project's living context: current task state, decisions, conventions, known footguns as plain Markdown committed to the repo, and expose it to the agent over MCP.

The MCP ecosystem doubles every few months. Bookmark the official MCP servers repository for the canonical list.

Source: https://github.com/aaif-goose/goose

Maybe check out Goose. It is the standard agent harness being developed by The Linux Foundation under the AAIF. Under active development and the implementation seems to have a good leg up on the other popular agents.

https://github.com/aaif-goose/goose

https://goose-docs.ai/

As a maintainer of goose, an open source AI agent, I have spent 2025 and 2026 sifting through pull requests. I do not want to limit who can contribute. I want everyone to be able to contribute. The goal is to understand the context of a PR at a fast pace, even if an external contributor uses an agent to build it. Open source needs infrastructure built to support both human-authored and agent-authored work.

Goose is an open-source AI agent that can act as an MCP Client and has a visual form to configure the extension name, type (STDIO), and the command it runs every time it starts. Internally, it stores config in a YAML file you never touch.

I had 55 pages of documentation to write, 59 screenshots to capture, and a product that was still shipping features and being rebranded weeks before release. I did it in four days with Goose, an open-source AI agent by Block, part of the Linux Foundation, and I want to walk you through exactly how. Not the polished version. The real one: how I built it, how it works, everything that broke along the way, and what I learned from it.

These are already available. Mistral’s Vibe CLI[1] is open source. Tools like goose[2]are API agnostic.

[1] https://github.com/mistralai/mistral-vibe

[2] https://goose-docs.ai/

Much of my previous work with GitHub and Block (goose) was focused on using agents to build faster. Recently joining the team at Entire has pushed me to think more about the next layer: making agentic work durable and accountable.

you can run https://block.github.io/goose/ in headless mode (I work on goose)