servers VS specification

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.

The news. On May 22, 2026, the MCP project landed PR #2750 — the blog announcement for the 2026-07-28 specification release candidate. The post leads with the stateless transport rework as the headline change, with a before/after HTTP example showing a self-contained tools/call request. Extensions, MCP Apps, and Tasks follow as the new capability story; the authorization changes are summarized by the failure modes they fix rather than enumerated SEP-by-SEP. All twenty-two scoped SEPs are linked from the announcement.

There is a pending proposal (#287) to add namespace prefixes server-side, dated around early 2026, but as of writing it has not landed and the client implementations have not picked it up. So this is an "until further notice" problem.

The news. On May 17, 2026, MCP SEP-2468 was merged into the Model Context Protocol specification — proposed March 25, accepted May 5. The change recommends that authorization servers advertise iss support in their metadata and include the parameter in their authorization responses, and requires clients to validate it against the recorded issuer using simple string comparison per RFC 3986 §6.2.1. The motivation, taken directly from RFC 9207, is to close the long-standing OAuth mix-up attack in clients that trust multiple identity providers.

Semrush data fills in the picture. Claude.ai hit 220 million monthly visits in January 2026, then jumped 30.9% to 288 million in February. Meanwhile, the Model Context Protocol SDK hit 97 million monthly downloads in March, up from 2 million at launch in November 2025. That's 4,750% growth in 16 months. The developer ecosystem is building momentum that feeds back into consumer adoption.

The Solution: User-specific authorization flows. The MCP server obtains tokens scoped to individual users, inheriting their permissions from the downstream systems. This is what our PR #475 addresses—enabling secure token exchange without exposing credentials to clients or LLMs.

If you've been following the rise of MCP (Model Context Protocol), this week was significant: Azure Functions now has first-class support for building MCP servers.

Azure Functions Documentation Model Context Protocol Specification Sample Repository TypeScript Sample Repository Python Sample Repository DotNet Sample Repository Java Azure Functions TypeScript Guide

No. Any file that runs MCP Server is fine anywhere. I am intending a workspace separate from the rails app. The MCP server should be run in a separate process from the rails app. At least until the streamable http transport is ready.

https://github.com/modelcontextprotocol/specification/pull/2...

Another aspect worth noting is that, to date, the protocol requires a persistent connection between client and server, so this can be a drawback for auto-scalable architectures that adapt to demand, as well as moving in the opposite direction in a world that is striving to become stateless.