MCP in Follow – O’Reilly

The next was initially revealed in Asimov’s Addendum, September 11, 2025.

Study extra in regards to the AI Disclosures Venture right here.

1. The Rise and Rise of MCP

Anthropic’s Mannequin Context Protocol (MCP) was launched in November 2024 as a strategy to make instruments and platforms model-agnostic. MCP works by defining servers and shoppers. MCP servers are native or distant finish factors the place instruments and sources are outlined. For instance, GitHub launched an MCP server that permits LLMs to each learn from and write to GitHub. MCP shoppers are the connection from an AI utility to MCP servers—they permit an LLM to work together with context and instruments from totally different servers. An instance of an MCP consumer is Claude Desktop, which permits the Claude fashions to work together with hundreds of MCP servers.

In a comparatively quick time, MCP has change into the spine of a whole lot of AI pipelines and purposes. Main gamers like Anthropic and OpenAI have constructed it into their merchandise. Developer instruments equivalent to Cursor (a coding-focused textual content editor or IDE) and productiveness apps like Raycast additionally use MCP. Moreover, hundreds of builders use it to combine AI fashions and entry exterior instruments and knowledge with out having to construct a complete ecosystem from scratch.

In earlier work revealed with AI Frontiers, we argued that MCP can act as a fantastic unbundler of “context”—the info that helps AI purposes present extra related solutions to customers. In doing so, it may possibly assist decentralize AI markets. We argued that, for MCP to actually obtain its objectives, it requires assist from:

1. Open APIs: In order that MCP purposes can entry third-party instruments for agentic use (write actions) and context (learn)
2. Fluid reminiscence: Interoperable LLM reminiscence requirements, accessed through MCP-like open protocols, in order that the reminiscence context accrued at OpenAI and different main builders doesn’t get caught there, stopping downstream innovation

We broaden upon these two factors in a current coverage be aware for these seeking to dig deeper.

Extra usually, we argue that protocols, like MCP, are literally foundational “guidelines of the street” for AI markets, whereby open disclosure and communication requirements are constructed into the community itself, quite than imposed after the actual fact by regulators. Protocols are basically market-shaping units, architecting markets by means of the permissions, guidelines, and interoperability of the community itself. They will have a huge impact on how the business markets constructed on high of them operate too.

1.1 However how is the MCP ecosystem evolving?

But we don’t have a transparent concept of the form of the MCP ecosystem right this moment. What are the commonest use instances of MCP? What kind of entry is being given by MCP servers and utilized by MCP shoppers? Is the info accessed through MCP “read-only” for context, or does it permit brokers to “write” and work together with it—for instance, by enhancing recordsdata or sending emails?

To start answering these questions, we take a look at the instruments and context which AI brokers use through MCP servers. This offers us a clue about what’s being constructed and what’s getting consideration. On this article, we don’t analyze MCP shoppers—the purposes that use MCP servers. We as a substitute restrict our evaluation to what MCP servers are making out there for constructing.

We assembled a big dataset of MCP servers (n = 2,874), scraped from Pulse MCP.¹ We then enriched it with GitHub star-count knowledge on every server. On GitHub, stars are much like Fb “likes,” and builders use them to indicate appreciation, bookmark tasks, or point out utilization.

In observe, whereas there have been loads of MCP servers, we discovered that the highest few garnered a lot of the consideration and, probably by extension, a lot of the use. Simply the highest 10 servers had almost half of all GitHub stars given to MCP servers.

A few of our takeaways are:

1. MCP utilization seems to be pretty concentrated. Which means that, if left unchecked, a small variety of servers and (by extension) APIs might have outsize management over the MCP ecosystem being created.
2. MCP use (instruments and knowledge being accessed) is dominated by simply three classes: Database & Search (RAG), Pc and Net Automation, and Software program Engineering. Collectively, they obtained almost three-quarters (72.6%) of all stars on GitHub (which we proxy for utilization).
3. Most MCP servers assist each learn (entry context) and write (altering context) operations, displaying that builders need their brokers to have the ability to act on context, not simply devour it.

2. Findings

To begin with, we analyzed the MCP ecosystem for focus threat.

2.1   MCP server use is concentrated

We discovered that MCP utilization is concentrated amongst a number of key MCP servers, judged by the variety of GitHub stars every repo obtained.

Regardless of there being hundreds of MCP servers, the highest 10 servers make up almost half (45.7%) of all GitHub stars given to MCP servers (pie chart beneath) and the highest 10% of servers make up 88.3% of all GitHub stars (not proven).

Which means that nearly all of real-world MCP customers are probably counting on the identical few providers made out there through a handful of APIs. This focus probably stems from community results and sensible utility: All builders gravitate towards servers that resolve common issues like net shopping, database entry, and integration with broadly used platforms like GitHub, Figma, and Blender. This focus sample appears typical of developer-tool ecosystems. A couple of well-executed, broadly relevant options are likely to dominate. In the meantime, extra specialised instruments occupy smaller niches.

2.2    The highest 10 MCP servers actually matter

Subsequent, the highest 10 MCP servers are proven within the desk beneath, together with their star rely and what they do.

Among the many high 10 MCP servers, GitHub, Repomix, Context7, and Framelink are constructed to help with software program improvement: Context7 and Repomix by gathering context, GitHub by permitting brokers to work together with tasks, and Framelink by passing on the design specs from Figma on to the mannequin. The Blender server permits brokers to create 3D fashions of something, utilizing the favored open supply Blender utility. Lastly, Activepieces and MindsDB join the agent to a number of APIs with one standardized interface: in MindsDB’s case, primarily to learn knowledge from databases, and in Activepieces to automate providers.

The dominance of agentic shopping, within the type of Browser Use (61,000 stars) and Playwright MCP (18,425 stars), stands out. This displays the basic want for AI programs to work together with net content material. These instruments permit AI to navigate web sites, click on buttons, fill out varieties, and extract knowledge identical to a human would. Agentic shopping has surged, although it’s far much less token-efficient than calling an API. Searching brokers usually have to wade by means of a number of pages of boilerplate to extract slivers of information a single API request might return. As a result of many providers lack usable APIs or tightly gate them, browser-based brokers are sometimes the best—generally the one—strategy to combine, underscoring the bounds of right this moment’s APIs.

A few of the high servers are unofficial. Each the Framelink and Blender MCP are servers that work together with only a single utility, however they’re each “unofficial” merchandise. Which means that they aren’t formally endorsed by the builders of the appliance they’re integrating with—those that personal the underlying service or API (e.g., GitHub, Slack, Google). As a substitute, they’re constructed by unbiased builders who create a bridge between an AI consumer and a service—usually by reverse-engineering APIs, wrapping unofficial SDKs, or utilizing browser automation to imitate person interactions.

It’s wholesome that third-party builders can construct their very own MCP servers, since this openness encourages innovation. But it surely additionally introduces an middleman layer between the person and the API, which brings dangers round belief, verification, and even potential abuse. With open supply native servers, the code is clear and might be vetted. Against this, distant third-party servers are tougher to audit, since customers should belief code they will’t simply examine.

At a deeper degree, the repos that at the moment dominate MCP servers spotlight three encouraging info in regards to the MCP ecosystem:

1. First, a number of distinguished MCP servers assist a number of third-party providers for his or her performance. MindsDB and Activepieces function gateways to a number of (usually competing) service suppliers by means of a single server. MindsDB permits builders to question totally different databases like PostgreSQL, MongoDB, and MySQL by means of a single interface, whereas Taskmaster permits the agent to delegate duties to a variety of AI fashions from OpenAI, Anthropic, and Google, all with out altering servers.
2. Second, agentic shopping MCP servers are getting used to get round probably restrictive APIs. As famous above, Browser Use and Playwright entry web providers by means of an internet browser, serving to to bypass API restrictions, however they as a substitute run up towards anti-bot protections. This circumvents the restrictions that APIs can impose on what builders are capable of construct.
3. Third, some MCP servers do their processing on the developer’s pc (regionally), making them much less depending on a vendor sustaining API entry. Some MCP servers examined right here can run solely on a neighborhood pc with out sending knowledge to the cloud—that means that no gatekeeper has the facility to chop you off. Of the ten MCP servers examined above, solely Framelink, Context7, and GitHub depend on only a single cloud-only API dependency that may’t be run regionally end-to-end in your machine. Blender and Repomix are utterly open supply and don’t require any web entry to work, whereas MindsDB, Browser Use, and Activepieces have native open supply implementations.

2.3   The three classes that dominate MCP use

Subsequent, we grouped MCP servers into totally different classes based mostly on their performance.

Once we analyzed what varieties of servers are hottest, we discovered that three dominated: Pc & Net Automation (24.8%), Software program Engineering (24.7%), and Database & Search (23.1%).

Widespread use of Software program Engineering (24.7%) MCP servers aligns with Anthropic’s financial index, which discovered that an outsize portion of AI interactions have been associated to software program improvement.

The recognition of each Pc & Net Automation (24.8%) and Database & Search (23.1%) additionally is smart. Earlier than the arrival of MCP, net scraping and database search have been extremely built-in purposes throughout platforms like ChatGPT, Perplexity, and Gemini. With MCP, nevertheless, customers can now entry that very same search performance and join their brokers to any database with minimal effort. In different phrases, MCP’s unbundling impact is extremely seen right here.

2.4   Brokers work together with their environments

Lastly, we analyzed the capabilities of those servers: Are they permitting AI purposes simply to entry knowledge and instruments (learn), or as a substitute do agentic operations with them (write)?

Throughout all however two of the MCP server classes checked out, the most well-liked MCP servers supported each studying (entry context) and writing (agentic) operations—proven in turquoise. The prevalence of servers with mixed learn and write entry means that brokers aren’t being constructed simply to reply questions based mostly on knowledge but additionally to take motion and work together with providers on a person’s behalf.

The 2 exceptions are Database & Search (RAG) and Finance MCP servers, through which read-only entry is a standard permission given. That is probably as a result of knowledge integrity is vital to making sure reliability.

3. The Significance of A number of Entry Factors

A couple of implications of our evaluation might be drawn out at this preliminary stage.

First, concentrated MCP server use compounds the dangers of API entry being restricted. As we mentioned in “Protocols and Energy,” MCP stays constrained by “what a specific service (equivalent to GitHub or Slack) occurs to reveal by means of its API.” A couple of highly effective digital service suppliers have the facility to close down entry to their servers.

One necessary hedge towards API gatekeeping is that lots of the high servers attempt to not depend on a single presentr. As well as, the next two safeguards are related:

• They provide native processing of information on a person’s machine each time attainable, as a substitute of sending the info for processing to a third-party server. Native processing ensures that performance can’t be restricted.
• If operating a service regionally isn’t attainable (e.g., e-mail or net search), the server ought to nonetheless assist a number of avenues of getting on the wanted context by means of competing APIs. For instance, MindsDB features as a gateway to a number of knowledge sources, so as a substitute of counting on only one database to learn and write knowledge, it goes to nice lengths to assist a number of databases in a single unified interface, primarily making the backend instruments interchangeable.

Second, our evaluation factors to the truth that present restrictive API entry insurance policies aren’t sustainable. Net scraping and bots, accessed through MCP servers, are most likely getting used (not less than partially) to bypass overly restrictive API entry, complicating the more and more frequent observe of banning bots. Even OpenAI is coloring exterior the API traces, utilizing a third-party service to entry Google Search’s outcomes by means of net scraping, thereby circumventing its restrictive API.

Increasing structured API entry in a significant approach is significant. This ensures that reputable AI automation runs by means of secure, documented finish factors. In any other case, builders resort to brittle browser automation the place privateness and authorization haven’t been correctly addressed. Regulatory steering might push the market on this course, as with open banking within the US.

Lastly, encouraging higher transparency and disclosure might assist determine the place the bottlenecks within the MCP ecosystem are.

• Builders working well-liked MCP servers (above a sure utilization threshold) or offering APIs utilized by high servers ought to report utilization statistics, entry denials, and rate-limiting insurance policies. This knowledge would assist regulators determine rising bottlenecks earlier than they change into entrenched. GitHub may facilitate this by encouraging these disclosures, for instance.
• Moreover, MCP servers above sure utilization thresholds ought to clearly checklist their dependencies on exterior APIs and what fallback choices exist if the first APIs change into unavailable. This isn’t solely useful in figuring out the market construction, but additionally important data for safety and robustness for downstream purposes.

The objective is to not get rid of all focus within the community, however to make sure that the MCP ecosystem stays contestable, with a number of viable paths for innovation and person alternative. By addressing each technical structure and market dynamics, these advised tweaks might assist MCP obtain its potential as a democratizing drive in AI improvement, quite than merely shifting bottlenecks from one layer to a different.

Footnotes

1. For this evaluation, we categorized every repo into certainly one of 15 classes utilizing GPT-5 mini. We then human-reviewed and edited the highest 50 servers that make up round 70% of the entire star rely in our dataset.

Appendix

Dataset

The total dataset, together with descriptions of the classes, might be discovered right here (constructed by Sruly Rosenblat):

https://huggingface.co/datasets/sruly/MCP-In-Follow

Limitations

There are just a few limitations to our preliminary analysis:

• GitHub stars aren’t a measure of obtain counts and even essentially a repo’s recognition.
• Solely the title and outline have been used when categorizing repos with the LLM.
• Categorization was topic to each human and AI errors and lots of servers would probably match into a number of classes.
• We solely used the PulseMCP checklist for our dataset, different lists had totally different servers (e.g. Browser Use isn’t on mcpmarket.com).
• We excluded some repos from our evaluation, equivalent to people who had a number of servers and people we weren’t capable of fetch the star rely for. We could miss some well-liked servers by doing this.

MCP Server Use Over Time