There are several kinds of MCP servers out there: - Thin wrapper logic that could be an Agent Skill or a CLI tool - CRUD access that does little more than use MCP as a standardized auth mechanism - And the most compelling: buckets of hard-won domain intelligence That third

We are donating MCP to the newly created Agentic AI Foundation. I am thrilled that we found a way to ensure that MCP will always remain neutral. Our commitment to MCP remains the same. We continue to be deeply involved and help steer the ship alongside other core maintainers

MCP Night is next week and we have a STACKED lineup 🔥 @dsp_ – co-creator of MCP @Anthropic @nicknotfun - MCP core @OpenAI Den Delimarksy - Eng @Microsoft @paul_irish – Eng @Google @ritakozlov_ – VP AI @Cloudflare @CraigCannon – Head of DevRel @Supabase @ReillyWood– Eng

One of the biggest challenges with using agents today is figuring out how to provide the LLMs with a toolset that it understands how to use accurately, is not overly broad, and enables meaningful tasks to be completed. After testing out various approaches, we have found a use

MCP gateways help solve aggregation but often contribute to tool overload. When you have 1000+ tools available, agents struggle and context windows explode. When a design team just needs a few tools across Figma, Linear, and Github MCP Servers, they are likely to end up

"The work on MCP has completely revolutionized the agentic AI landscape" - Jensen Huang 🫡 https://t.co/4mcAuc9zTr

MCP often gets criticized for its propensity to bloat context with “tool overload”. I think this criticism is unfounded. The reality is, you should never have more than a few MCP servers active in your context at a given time. And if a single MCP server has too many tools -

Great coverage via @pulsemcp on Anthropic's new policy for their MCP directory TL;DR: if you're building consumer-facing agents and you don't ship remote OAuth for your MCP server, you're ngmi

We like how you think :)

Super excited to be included in the latest MCP Weekly Pulse by the @pulsemcp team! We're only in the 1st or 2nd inning of MCP and agentic systems, but I couldn't be more excited to be building open tooling for MCP developers. V1 of Shinzo is out now, DM me for access :)

How do you price something that's never been priced before? We're excited to share a guest post from @reactiverobot, founder of Ref, who tackled this exact challenge while building what may be the first standalone paid MCP server. Read it here: https://t.co/wkYu6PVWCY His

Thanks to @pulsemcp for this amazing article! The killer feature of MCP is Iteration and closing the loop: https://t.co/AdE1QDOf55

𝗔𝗿𝗲 𝘆𝗼𝘂 𝗷𝗼𝗶𝗻𝗶𝗻𝗴 𝘂𝘀? London is calling 💂 On 2 October, the MCP Dev Summit EU will gather the community for a full day of learning and connection. Details are here: https://t.co/OF6T0fUHGW #MCP #MCPDevsummit #LondonTech

MCP servers have a killer use case: you can use them to “close the agentic loop” for agents like Claude Code, Cursor, Goose, Cline, and others. I’ve found that closing the loop with an MCP server is often what evolves “cute demo” to “actually practical use case”

Story time: I wrote The Sleep Guide ~6 months ago: https://t.co/sRC5zbNtuB A few months ago I started following @pulsemcp 's newsletter to keep on top of AI news (it's great!!) New issue dropped yesterday, and I sent an email saying how much I like the newsletter.

Good automation is opinionated. @PulseMCP built a Goose workflow where each subagent has a single role, clear boundaries, and predictable handoffs so the human stays in charge.

We believe a lot of automation projects fail because they try to change everything at once. Parts II & III of our Goose handbook (w/ @blockopensource ) are now live, covering: ✅ How to sequence your roadmap for continuous value and small wins at every step ✅ Why agent

@blockopensource Parts II & III releasing later today. Full release schedule here:

Flashy AI demos are impressive, but we can't be the only ones frustrated when they break down in real workflows. That's why we've partnered with @blockopensource and the Goose team to create something different: a step-by-step handbook showing how we use AI agents to automate