# MCP Registry

> The MCP Registry is the official metadata catalog of public Model Context Protocol servers, used by marketplaces and clients to discover them.

Source: https://metavert.io/mcp-registry  
Published: 2026-10-07  
Updated: 2026-10-07

The **MCP Registry** is the official, centralized metadata catalog of publicly accessible [Model Context Protocol](https://metavert.io/model-context-protocol) servers, run by the MCP project at `registry.modelcontextprotocol.io`. Its documentation describes it as "the official centralized metadata repository for publicly accessible MCP servers, backed by major trusted contributors to the MCP ecosystem such as Anthropic, GitHub, PulseMCP, and Microsoft." It answers a question the protocol itself leaves open: once thousands of servers exist, how does a client, a marketplace or an agent find the right one and know who published it?

### What It Is and Is Not

The registry stores metadata, not code. Each entry is a `server.json` record containing the server's unique name, where to get it (an npm, PyPI or Docker package, or the URL of a remote server), how to run it, and descriptive data. The code stays in the package registries; the MCP Registry points to it. Closed-source servers may be listed as long as the installation method or endpoint is publicly reachable. Private servers are out of scope, and organizations are expected to run their own registries for those.

Two design choices are easy to miss. The registry is "deliberately unopinionated": it does not rate, rank or curate. And it is not meant to be queried directly by end-user applications. The documentation says it is "intended to be consumed primarily by downstream aggregators, such as MCP server marketplaces," which add curation, ratings and security checks and expose the same OpenAPI interface to host applications. The official registry is the upstream source of truth, and the directories people actually browse sit on top of it.

### Publishing and Verification

Publishers submit entries with the `mcp-publisher` command-line tool. Names use a reverse-DNS format such as `io.github.username/server` or `com.example/server`, and the publisher must prove control of the namespace through GitHub authentication or a DNS or HTTP challenge on the domain. That is the registry's main trust guarantee: an entry under a company's domain was published by someone who controls that domain.

It is a guarantee about identity, not safety. Security scanning is explicitly delegated to the underlying package registries and to downstream aggregators, and maintainers can remove spam or malicious entries after the fact. Since tool descriptions and tool outputs are untrusted input to a model, a verified namespace does not remove the [prompt injection](https://metavert.io/prompt-injection) risk of connecting an unfamiliar server.

### Status and Scale

The registry launched in preview on September 8, 2025 and froze its v0.1 API on October 24, 2025. Its documentation still carried a preview notice when checked in October 2026, warning that breaking changes or data resets may occur before general availability.

Counts of MCP servers should be quoted with a source and a date, because trackers measure different things and disagree widely.

| Source | Figure | What is being counted |
| --- | --- | --- |
| Linux Foundation, December 2025 | "more than 10,000 published MCP servers" | Ecosystem-wide claim in the Agentic AI Foundation announcement |
| Independent snapshot of the official registry, September 10, 2026 | 30,375 unique servers across 99,114 version records | Namespace-verified entries published by maintainers |
| PulseMCP directory, checked October 6, 2026 | 21,742 servers | A curated third-party directory |
| Glama directory, checked October 6, 2026 | 97,041 servers | An automated index of open-source servers |

The spread, from about 22,000 to about 97,000 on the same day, reflects method: automated crawls of code hosts count far more than curated lists, and the sets overlap heavily. Volume also says little about quality. The same independent snapshot of the official registry reported that 62% of servers had exactly one published version, roughly a third had not been updated in 90 days or more, and 23% carried no source-code link. It is a single analyst's reading of the public API and has not been replicated, but it is consistent with a long tail of experiments around a smaller core of maintained servers.

### Why Listing Matters

For a product that wants to be usable by agents, the registry is a distribution point. Marketplaces and client applications draw on registry data to populate their catalogs, so an official entry is the most direct way to appear across them with a verified publisher name and correct installation details, instead of relying on each directory to scrape a README. It is the discovery half of the tools pillar of [agent experience](https://metavert.io/agent-experience): an MCP server that [coding agents](https://metavert.io/ai-coding-agents) and their users cannot find does little good.

Listing is necessary, not sufficient. No public study yet shows how often agents select tools from registry data as opposed to documentation, web search or prior knowledge, and with tens of thousands of entries a listing alone confers no prominence. The sensible framing is hygiene: claim the namespace, publish accurate metadata, keep versions current, and treat downstream marketplaces as the places where selection actually happens. Broader questions of how agents find each other, beyond tool servers, belong to [agent discovery](https://metavert.io/agent-discovery).

## Related Topics

- [Model Context Protocol](https://metavert.io/model-context-protocol) — The protocol whose servers the registry catalogs
- [MCP](https://metavert.io/mcp) — Overview of the protocol and ecosystem
- [Agentic AI Foundation](https://metavert.io/agentic-ai-foundation) — The Linux Foundation body that governs MCP
- [Agent Discovery](https://metavert.io/agent-discovery) — The wider problem of finding agents and tools
- [Agent Experience (AX)](https://metavert.io/agent-experience) — Why being findable by agents matters
- [AI Coding Agents](https://metavert.io/ai-coding-agents) — Major consumers of MCP servers
- [llms.txt vs MCP](https://metavert.io/compare/llms-txt-vs-mcp) — Two ways to make a product usable by agents
- [Prompt Injection](https://metavert.io/prompt-injection) — The main risk of connecting unknown servers
- [Tool Use](https://metavert.io/tool-use) — The model capability MCP standardizes

## Further Reading

- [The MCP Registry](https://modelcontextprotocol.io/registry/about) — Model Context Protocol documentation, checked October 2026
- [Introducing the MCP Registry (preview)](https://blog.modelcontextprotocol.io/posts/2025-09-08-mcp-registry-preview/) — Model Context Protocol Blog, September 2025
- [modelcontextprotocol/registry](https://github.com/modelcontextprotocol/registry) — GitHub, checked October 2026
- [Linux Foundation Announces the Formation of the Agentic AI Foundation](https://www.linuxfoundation.org/press/linux-foundation-announces-the-formation-of-the-agentic-ai-foundation) — Linux Foundation, December 2025
- [The MCP Registry by the Numbers](https://dev.to/amareswer/the-mcp-registry-by-the-numbers-38nc) — Amaresh Pelleti, DEV Community, September 2026
- [PulseMCP server directory](https://www.pulsemcp.com/servers) — PulseMCP, checked October 2026
- [Glama MCP server directory](https://glama.ai/mcp/servers) — Glama, checked October 2026