# MCP Server Registry Search (`myagizm/mcp-server-registry`) Actor

Search the public MCP server registry and export current server versions with endpoints, packages, repository links, and status metadata.

- **URL**: https://apify.com/myagizm/mcp-server-registry.md
- **Developed by:** [MYM](https://apify.com/myagizm) (community)
- **Categories:** AI, Agents, MCP servers
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$1.00 / 1,000 current server records

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## MCP Server Registry Search

Search current public MCP server definitions and export clean records for agent directories, tool discovery, and integration inventories. Results include server versions, official status, remote transport endpoints, packages, and repository links when the registry provides them.

### What you can collect

- Current server name, title, version, and description
- Official active/status metadata and publication/update timestamps
- Streamable HTTP or other remote endpoint URLs and transport types
- Package identifiers, repository/website links, and tool names when available
- Full public server definition as JSON text for downstream processing

By default, entries that the registry marks as older versions are excluded. The Actor follows the registry's continuation cursor to find current versions, up to the configured page limit.

### Input

| Field | Type | Description |
|---|---|---|
| `searchQuery` | string | Optional case-insensitive filter over server name, title, and description |
| `maxItems` | integer | Maximum returned records, from 1 to 1,000 |
| `cursor` | string | Optional continuation cursor from the previous run's `STATS` key |
| `maxPages` | integer | Maximum pages per run, from 1 to 10 |

Example:

```json
{"searchQuery":"filesystem","maxItems":25,"maxPages":5}
```

### Output and pagination

Each dataset item is one current server version. The `overview` view shows server name, version, status, description, remote URLs, repository, and registry timestamps. Full records retain the public definition as JSON. The `nextCursor` field on each returned row can be passed as `cursor` in a later run to continue without skipping unreturned rows.

### Pricing and limits

Pay per returned dataset item: $0.001 per item ($1 per 1,000 records). Invalid inputs finish SUCCEEDED with no rows or charge and an OUTPUT reason; upstream/registry failures and unverified empty searches remain FAILED. Runs make bounded direct requests to the public registry; no proxy, login, or third-party key is required.

### 中文说明

## MCP 服务器目录搜索

搜索公开 MCP 服务器定义，并为 Agent 目录、工具发现和集成清单导出结构化记录。结果包括服务器版本、官方状态、远程传输端点、软件包和仓库链接（以注册表提供的信息为准）。

### 可获取的数据

- 当前服务器名称、标题、版本和描述
- 官方状态、发布时间和更新时间
- Streamable HTTP 等远程端点及传输类型
- 软件包标识符、仓库/网站链接，以及可用的工具名称
- 下游处理所需的完整公开服务器定义 JSON

默认排除注册表标记为旧版本的记录。Actor 会按注册表的 continuation cursor 查找当前版本，并遵守配置的最大页数。

### 输入参数

| 字段 | 类型 | 说明 |
|---|---|---|
| `searchQuery` | 字符串 | 可选，不区分大小写地匹配服务器名称、标题和描述 |
| `maxItems` | 整数 | 最多返回 1 到 1,000 条记录 |
| `cursor` | 字符串 | 可选，使用上次运行 `STATS` 键中的 cursor 继续分页 |
| `maxPages` | 整数 | 每次运行最多请求 1 到 10 页 |

示例：

```json
{"searchQuery":"filesystem","maxItems":25,"maxPages":5}
```

### 输出与分页

每条数据集记录代表一个当前服务器版本。`overview` 视图展示服务器名称、版本、状态、描述、远程 URL、仓库和注册表时间。完整记录保留公开服务器定义 JSON。每条记录中的 `nextCursor` 可作为下一次运行的 `cursor`，继续浏览而不会跳过未返回的条目。

### 价格与限制

按返回的数据集条目计费：每条 $0.001（每 1,000 条 $1）。无效输入会以 SUCCEEDED 结束、无结果且不收费，原因写入 OUTPUT；上游/注册表错误及未经验证的空结果仍为 FAILED。每次运行只会向公开注册表发送有上限的直接请求；无需代理、登录或第三方密钥。

### Errors & billing

Input errors finish with status SUCCEEDED, no results and no charge; see the OUTPUT record for the reason.

#### 错误与计费

输入错误会以 SUCCEEDED 状态结束，无结果且不收费；原因请查看 OUTPUT 记录。

# Actor input Schema

## `searchQuery` (type: `string`):

Optional case-insensitive text filter over server name, title, and description. Leave blank to list current server versions.

## `maxItems` (type: `integer`):

Maximum number of current registry records to return.

## `cursor` (type: `string`):

Optional cursor returned in the run's STATS key to continue from a later registry page.

## `maxPages` (type: `integer`):

Maximum number of registry pages to fetch in one run; each page is capped at 100 entries.

## Actor input object example

```json
{
  "searchQuery": "",
  "maxItems": 100,
  "maxPages": 5
}
```

# Actor output Schema

## `results` (type: `string`):

Registry entries shown in the overview table.

## `fullJson` (type: `string`):

Complete server definitions and endpoints.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "searchQuery": "",
    "maxItems": 100,
    "maxPages": 5
};

// Run the Actor and wait for it to finish
const run = await client.actor("myagizm/mcp-server-registry").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "searchQuery": "",
    "maxItems": 100,
    "maxPages": 5,
}

# Run the Actor and wait for it to finish
run = client.actor("myagizm/mcp-server-registry").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "searchQuery": "",
  "maxItems": 100,
  "maxPages": 5
}' |
apify call myagizm/mcp-server-registry --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,myagizm/mcp-server-registry"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/k2UN0PMICvNFOY4ck/builds/VfkdI25nLWbU7nkUQ/openapi.json