MCP in Apply – O’Reilly

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

Be taught extra concerning 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 method 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 brief time, MCP has develop into the spine of a whole bunch of AI pipelines and purposes. Main gamers like Anthropic and OpenAI have constructed it into their merchandise. Developer instruments similar 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 information with out having to construct a whole ecosystem from scratch.

In earlier work revealed with AI Frontiers, we argued that MCP can act as a terrific unbundler of “context”—the information 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 word, for these trying to dig deeper.

Extra typically, we argue that protocols, like MCP, are literally foundational “guidelines of the highway” for AI markets, whereby open disclosure and communication requirements are constructed into the community itself, moderately than imposed after the very fact by regulators. Protocols are basically market-shaping units, architecting markets by the permissions, guidelines, and interoperability of the community itself. They’ll have a big effect on how the industrial markets constructed on prime of them operate 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 in the present day. What are the most typical use instances of MCP? What kind of entry is being given by MCP servers and utilized by MCP shoppers? Is the information accessed through MCP “read-only” for context, or does it permit brokers to “write” and work together with it—for instance, by modifying recordsdata or sending emails?

To start answering these questions, we have 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 obtainable 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 information 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 apply, whereas there have been loads of MCP servers, we discovered that the highest few garnered a lot of the consideration and, doubtless 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, 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 information being accessed) is dominated by simply three classes: Database & Search (RAG), Pc & 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 (change context) operations, exhibiting that builders need their brokers to have the ability to act on context, not simply devour it.

2. Findings

To start out 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 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 nearly all of real-world MCP customers are doubtless counting on the identical few companies made obtainable through 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 shopping, database entry, and integration with broadly used platforms like GitHub, Figma, and Blender. This focus sample appears typical of developer-tool ecosystems. Just a few 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 beneath, together with their star depend and what they do.

Among the many prime 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 information from databases, and in Activepieces to automate companies.

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 elemental want for AI methods to work together with net content material. These instruments permit AI to navigate web sites, click on buttons, fill out varieties, and extract information similar to a human would. Agentic shopping has surged, despite the fact that it’s far much less token-efficient than calling an API. Searching brokers usually must wade by a number of pages of boilerplate to extract slivers of information 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—typically the one—method to combine, underscoring the boundaries of in the present day’s APIs.

Among the prime 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 they don’t seem to be 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 an alternative, 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 consumer interactions.

It’s wholesome that third-party builders can construct their very own MCP servers, since this openness encourages innovation. However 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 will be vetted. In contrast, distant third-party servers are more durable to audit, since customers should belief code they will’t simply examine.

At a deeper stage, the repos that presently dominate MCP servers spotlight three encouraging details concerning the MCP ecosystem:

1. First, a number of outstanding MCP servers assist a number of third-party companies for his or her performance. MindsDB and Activepieces function gateways to a number of (usually 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 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 doubtlessly restrictive APIs. As famous above, Browser Use and Playwright entry web companies by an online browser, serving to to bypass API restrictions, however they as a substitute run up in opposition to anti-bot protections. This circumvents the constraints 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 information 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 primarily based 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 had been associated to software program improvement.

The recognition of each Pc & Net Automation (24.8%) and Database & Search (23.1%) additionally is sensible. Earlier than the appearance of MCP, net scraping and database search had 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 information 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 are usually not being constructed simply to reply questions primarily based on information but additionally to take motion and work together with companies on a consumer’s behalf.

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

3. The Significance of A number of Entry Factors

Just a few implications of our evaluation will 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 (similar to GitHub or Slack) occurs to show by its API.” Just a few highly effective digital service suppliers have the facility to close down entry to their servers.

One necessary hedge in opposition to API gatekeeping is that most of the prime servers strive to not depend on a single presentr. As well as, the next two safeguards are related:

• They provide native processing of information on a consumer’s machine each time potential, as a substitute of sending the information for processing to a third-party server. Native processing ensures that performance can’t be restricted.
• If operating a service regionally just isn’t potential (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 information sources, so as a substitute of counting on only one database to learn and write information, 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 are usually not sustainable. Net scraping and bots, accessed through MCP servers, are most likely getting used (no less than partly) to bypass overly restrictive API entry, complicating the more and more widespread apply of banning bots. Even OpenAI is coloring outdoors the API traces, 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 approach is important. This ensures that professional AI automation runs by steady, documented finish factors. In any other case, builders resort to brittle browser automation the place privateness and authorization haven’t been correctly addressed. Regulatory steerage might push the market on this path, as with open banking within the US.

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

• Builders working common MCP servers (above a sure utilization threshold) or offering APIs utilized by prime servers ought to report utilization statistics, entry denials, and rate-limiting insurance policies. This information would assist regulators establish rising bottlenecks earlier than they develop into entrenched. GitHub would possibly 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 develop into unavailable. This isn’t solely useful in figuring out the market construction, but additionally important info for safety and robustness for downstream purposes.

The aim 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 alternative. By addressing each technical structure and market dynamics, these recommended tweaks might assist MCP obtain its potential as a democratizing drive in AI improvement, moderately 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 depend in our dataset.

Appendix

Dataset

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

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

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 reputation.
• Solely the title and outline had been used when categorizing repos with the LLM.
• Categorization was topic to each human and AI errors and plenty 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, similar to people who had a number of servers and people we weren’t in a position to fetch the star depend for. We might miss some common servers by doing this.

MCP Server Use Over Time