Doing our best to drive adoption of the Model Context Protocol (MCP). Reach out, we love to chat MCP.
Joined December 2024
- Tweets 223
- Following 67
- Followers 561
- Likes 277
24 Photos and videos
PulseMCP retweeted
Jun 4
Inability to save on costs may be true for teams where every individual is doing AI-assisted dev work from scratch every time they spin up a coding agent.
I think the opportunity here is mostly for teams that have matured towards hardened auto-triggered, cloud agent workflows. The complexity of those is more predictable, the paths (memorialized as Skills) better-trodden.
It seems many @cognition customers are near this point - @ido_pesok wrote up recently how such async sessions are eclipsing interactive ones (x.com/ido_pesok/status/20604…). I bet @FactoryAI customers show a similar profile. But most companies are nowhere close to this yet.
Jun 3
The Factory team seems very smart, and I'm eager to see how well their cost-optimizing new model router works. If they can pull it off, that is a huge accomplishment.
For Amp: we may try to build a model router that picks the best model for a task, but we don't intend to build a cost-optimizing model router based on the current state of the models. Here's why.
Every time we've looked into using cheaper models in Amp, we've benchmarked on tasks that reflect how people use agents for coding today. On these real tasks, the expensive frontier model was not only the best (obviously), but also usually the fastest and cheapest, when measuring end-to-end task completion.
Why? Cheaper-per-token models are less capable, which means that on complex real-world tasks they spend more tokens and time fixing mistakes along the way.
You can find plenty of cases where cheaper models are indeed faster and cheaper end-to-end. But such cases were rarer than we expected, and the differences were fairly small.
If you can easily detect such cases, then there is an opportunity here. But even then, on the AI hedonic treadmill, once people get a taste of frontier intelligence, they don't want to go back to using those more primitive prompts where cheaper models suffice. (Which is a good part of human behavior! It's how we decided to stop living in caves!)
If your tasks can be handled just as well by non-frontier models, I would strongly advise you to uplevel how you use agents and what you produce to stay competitive against people who are using frontier models.
In a power-law world, with rapid intelligence advances, try to get to the frontier and stay there.
3
1
6
2,451
PulseMCP retweeted
A new playbook on @pulsemcp defines the standards for team collaboration on agent skills.
The guide provides a technical walkthrough on using MCP to synchronize agentic workflows and manage shared capabilities across a multi-agent environment. It is a key resource for those building the next generation of collaborative AI infrastructure.
Full playbook available at: bit.ly/4fjVNo0
4
14
1,005
PulseMCP retweeted
Apr 23
The top MCP question from enterprise leaders right now:
"How do I curate an approved list of servers for my org?"
With 13,000 MCP servers out there and new ones shipping daily, "just let people install things" isn't a strategy.
So we teamed up with @tadasayy and @grumpygrowthguy from @pulsemcp to build a curated catalog of trusted MCP servers purpose-built for Speakeasy customers rolling out MCP at scale.
Production-grade, vetted, enterprise-ready. 🤝
3
9
320
PulseMCP retweeted
Feb 13
Software engineers worried about AI absorbing their craft would do well to embrace the change and do what the history of building software has always done: move up the abstraction layer.
Agentic engineering is here. Teams are making it work. The portfolio of very public examples of this adoption grows by the day. I’ve been coaching some of the teams going through this shift in the software engineering trade - and I’ve found that the mindset shift often takes just two very specific “aha” moments.
1
2
5
272
PulseMCP retweeted
Feb 6
Excalidraw in Claude. MCP Apps made by one of the main engineers behind MCP Apps: github.com/antonpk1/excalidr…
54
136
1,629
465,120
Congrats on the launch, @PlanetScale!
Jan 29
Today we're launching the PlanetScale hosted MCP server.
Use your favorite AI agent to explore your data, identify slow queries, and improve database performance.
3
296
PulseMCP retweeted
Jan 26
MCP Apps are officially here. 🎉
Officially released today by @AnthropicAI, @OpenAI, and MCP-UI (@idosal1 and myself).
These apps will run *everywhere*. @claudeai, @code, @goose_oss, even @ChatGPTapp. Everywhere.
*Check out the future of the web*:
blog.modelcontextprotocol.io…
Your work tools are now interactive in Claude.
Draft Slack messages, visualize ideas as Figma diagrams, or build and see Asana timelines.
36
39
376
68,849
PulseMCP retweeted
23 Dec 2025
The MCP ecosystem faces a repeated "chicken or egg" problem with its long tail of rich features. Servers don't implement features until clients support them, & vice-versa.
Sometimes the problem is even worse: servers can't adopt features lest they break (popular) laggard clients
2
6
15
4,867
PulseMCP retweeted
10 Dec 2025
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 category is where MCP really shines
1
2
9
544
PulseMCP retweeted
9 Dec 2025
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 from OpenAI, Google, AWS and Microsoft and the broader MCP community.
9 Dec 2025
Anthropic is donating the Model Context Protocol to the Agentic AI Foundation, a directed fund under the Linux Foundation.
In one year, MCP has become a foundational protocol for agentic AI. Joining AAIF ensures MCP remains open and community-driven. anthropic.com/news/donating-…
13
29
246
24,271
PulseMCP retweeted
5 Dec 2025
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 @datadoghq
Plus some other surprise guests. It's going to be an incredible night. Make sure to RSVP now 🙇♂️
14
3
34
7,541
PulseMCP retweeted
28 Nov 2025
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 case driven way for packaging up tools to be the most effective approach. Our article with @pulsemcp goes into the details of what we've learned, why it is important to have tool groups based on use case or roles, and how it turns out that Model Context Protocol (MCP) already provides a natural way for us to implement this.
We call this approach the Virtual MCP approach, where we use a gateway architecture to quickly group up tools by use case. Critically, tools in a virtual MCP come from multiple MCP servers. Using a virtual MCP setup makes it both easy for end users to configure, and also IT/admins to secure.
As enterprises adopt more agents MCPs, we think these approaches will become critical as we need control and telemetry into what the agents can and are doing.
Thanks for @tadasayy @grumpygrowthguy for the collaboration.
pulsemcp.com/posts/virtual-m…
@MintMCP_AI @MCP_Community
9
19
153
14,589
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 unintentionally loading hundreds.
Our friends @MintMCP_AI partnered with PulseMCP to share how they are tackling this problem with Virtual MCP Servers. Give it a read: pulsemcp.com/posts/virtual-m…
2
3
280
PulseMCP retweeted
18 Nov 2025
"The work on MCP has completely revolutionized the agentic AI landscape" - Jensen Huang 🫡
2
4
12
1,733
PulseMCP retweeted
14 Oct 2025
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 - that server needs a redesign.
The rest can be solved with Agentic MCP Configuration.
1
2
13
1,292
PulseMCP retweeted
29 Sep 2025
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
1
1
6
750
We like how you think :)
22 Sep 2025
all these health data mcp servers on @pulsemcp seem like underrated signal for a good app to be built
290
PulseMCP retweeted
22 Sep 2025
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 :)
2
5
379