MCP in Apply – O’Reilly

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

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

1. The Rise and Rise of MCP

Anthropic’s Mannequin Context Protocol (MCP) was launched in November 2024 as a approach 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 assets are outlined. For instance, GitHub launched an MCP server that enables LLMs to each learn from and write to GitHub. MCP shoppers are the connection from an AI software 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 1000’s of MCP servers.

In a comparatively quick time, MCP has turn into the spine of lots of of AI pipelines and functions. Main gamers like Anthropic and OpenAI have constructed it into their merchandise. Developer instruments resembling Cursor (a coding-focused textual content editor or IDE) and productiveness apps like Raycast additionally use MCP. Moreover, 1000’s 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 functions present extra related solutions to shoppers. In doing so, it will probably assist decentralize AI markets. We argued that, for MCP to really obtain its targets, it requires assist from:

1. Open APIs: In order that MCP functions can entry third-party instruments for agentic use (write actions) and context (learn)
2. Fluid reminiscence: Interoperable LLM reminiscence requirements, accessed by way of 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 develop upon these two factors in a current coverage notice, for these seeking to dig deeper.

Extra typically, 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, somewhat than imposed after the very fact by regulators. Protocols are basically market-shaping gadgets, architecting markets by the permissions, guidelines, and interoperability of the community itself. They will have a big effect on how the business markets constructed on high of them perform too.

1.1 However how is the MCP ecosystem evolving?

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

To start answering these questions, we take a look at the instruments and context which AI brokers use by way of 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 functions that use MCP servers. We as a substitute restrict our evaluation to what MCP servers are making accessible for constructing.

We assembled a big dataset of MCP servers (n = 2,874), scraped from Pulse.¹ We then enriched it with GitHub star-count knowledge on every server. On GitHub, stars are just 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 many of the consideration and, doubtless by extension, many of the use. Simply the highest 10 servers had practically half of all GitHub stars given to MCP servers.

A few of our takeaways are:

1. MCP utilization seems to be pretty concentrated. Because of this, 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), Laptop & Net Automation, and Software program Engineering. Collectively, they obtained practically 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 (change 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 danger.

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 1000’s of MCP servers, the highest 10 servers make up practically half (45.7%) of all GitHub stars given to MCP servers (pie chart under) and the highest 10% of servers make up 88.3% of all GitHub stars (not proven).

Because of this the vast majority of real-world MCP customers are doubtless counting on the identical few companies made accessible by way of a handful of APIs. This focus doubtless stems from community results and sensible utility: All builders gravitate towards servers that remedy common issues like net looking, 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 inclined 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 under, 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 software. 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 companies.

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

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

It’s wholesome that third-party builders can construct their very own MCP servers, since this openness encourages innovation. Nevertheless it additionally introduces an middleman layer between the consumer 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. In contrast, distant third-party servers are tougher to audit, since customers should belief code they’ll’t simply examine.

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

1. First, a number of distinguished MCP servers assist a number of third-party companies for his or her performance. MindsDB and Activepieces function gateways to a number of (typically competing) service suppliers by a single server. MindsDB permits builders to question totally different databases like PostgreSQL, MongoDB, and MySQL by a single interface, whereas Taskmaster permits the agent to delegate duties to a spread of AI fashions from OpenAI, Anthropic, and Google, all with out altering servers.
2. Second, agentic looking MCP servers are getting used to get round probably restrictive APIs. As famous above, Browser Use and Playwright entry web companies by 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 in a position to 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 completely on an area pc with out sending knowledge to the cloud—that means that no gatekeeper has the ability 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 fully 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.

After we analyzed what varieties of servers are hottest, we discovered that three dominated: Laptop & 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 Laptop & Net Automation (24.8%) and Database & Search (23.1%) additionally is sensible. Earlier than the appearance of MCP, net scraping and database search have been extremely built-in functions 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 functions 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 preferred 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 should not being constructed simply to reply questions based mostly on knowledge but in addition to take motion and work together with companies on a consumer’s behalf.

The 2 exceptions are Database & Search (RAG) and Finance MCP servers, wherein read-only entry is a standard permission given. That is doubtless as a result of knowledge integrity is essential 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 selected service (resembling GitHub or Slack) occurs to show by its API.” A couple of highly effective digital service suppliers have the ability to close down entry to their servers.

One necessary hedge towards API gatekeeping is that most 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 knowledge on a consumer’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 working a service regionally shouldn’t be 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 competing APIs. For instance, MindsDB capabilities 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, basically making the backend instruments interchangeable.

Second, our evaluation factors to the truth that present restrictive API entry insurance policies should not sustainable. Net scraping and bots, accessed by way of MCP servers, are in all probability getting used (at the least partially) to bypass overly restrictive API entry, complicating the more and more frequent observe of banning bots. Even OpenAI is coloring outdoors the API strains, utilizing a third-party service to entry Google Search’s outcomes by net scraping, thereby circumventing its restrictive API.

Increasing structured API entry in a significant method is important. This ensures that authentic AI automation runs by 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 route, 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 turn into entrenched. GitHub may facilitate this by encouraging these disclosures, for instance.
• Moreover, MCP servers above sure utilization thresholds ought to clearly record their dependencies on exterior APIs and what fallback choices exist if the first APIs turn into unavailable. This isn’t solely useful in figuring out the market construction, but in addition important data for safety and robustness for downstream functions.

The purpose 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 consumer selection. By addressing each technical structure and market dynamics, these recommended tweaks might assist MCP obtain its potential as a democratizing pressure in AI improvement, somewhat than merely shifting bottlenecks from one layer to a different.

Footnotes

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

Limitations

There are a number of limitations to our preliminary analysis:

• GitHub stars aren’t a measure of obtain counts and even essentially a repo’s reputation.
• 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 doubtless match into a number of classes.
• We solely used the Pulse record 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, resembling those who had a number of servers and people we weren’t in a position to fetch the star rely for. We could miss some well-liked servers by doing this.

MCP Server Use Over Time