Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-server-iqiyi what's trending on iQiyi?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project provides an MCP server implementation to access two iQiyi API endpoints:
Get New Releases: Fetches the latest released videos.
Get Trending Videos: Fetches the most popular videos.
The server is built using the FastMCP framework and exposes these functionalities as tools that can be accessed via the MCP protocol.
Get New Releases: Returns a list of newly released videos with details such as title, description, image URL, and video URL.
Get Trending Videos: Returns a list of trending videos with similar details.
Customizable Configuration: Supports environment variables to configure user-specific parameters like IQIYI_UID, IQIYI_AUTH, and IQIYI_DEVICE.
Customizable Logging: Allows specifying a custom log directory and log file path.
Related MCP server: Bilibili MCP Server
get_new_releasesFetches the latest released videos.
Inputs:
count (optional, integer): Number of videos to return (default: 14).
Returns: A formatted string containing details of the latest released videos.
get_trending_videosFetches the most popular videos.
Inputs:
count (optional, integer): Number of videos to return (default: 14).
Returns: A formatted string containing details of the trending videos.
Create a Virtual Environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activateInstall Dependencies
Install the required Python packages using requirements.txt:
pip install -r requirements.txtBelow is an example configuration for integrating this MCP server into your environment:
{
"mcpServers": {
"mcp-server-iqiyi": {
"command": "uv",
"args": [
"--directory",
"D:\\myFile\\code\\mcp-server-iqiyi\\mcp-server-iqiyi",
"run",
"main.py"
],
"autoApprove": [
"get_new_releases",
"get_trending_videos"
],
"disabled": false,
"timeout": 30,
"env": {
"IQIYI_UID": "<YOUR_UID>",
"IQIYI_AUTH": "<YOUR_AUTH_TOKEN>",
"IQIYI_DEVICE": "<YOUR_DEVICE_ID>",
"IQIYI_LOG_DIR": "D:/custom/logs", // Optional: Custom log directory
"IQIYI_LOG_FILE": "D:/custom/logs/mcp-server-iqiyi.log" // Optional: Custom log file path
}
}
}
}IQIYI_UID: Your iQiyi user ID.
IQIYI_AUTH: Authentication token for accessing the iQiyi API.
IQIYI_DEVICE: Device identifier for the API request.
IQIYI_LOG_DIR (Optional): Directory where logs will be stored. Defaults to D:/temp/logs.
IQIYI_LOG_FILE (Optional): Full path to the log file. Defaults to D:/temp/logs/mcp-server-iqiyi.log.
Clone the repository to your local machine.
Configure the MCP server settings as shown in the example above.
Start the MCP server using the configured command:
uv --directory D:\myFile\code\mcp-server-iqiyi\mcp-server-iqiyi run main.pyUse the following tools:
get_new_releases: Fetches the latest released videos.
get_trending_videos: Fetches the most popular videos.
Logs are stored in the directory specified by the IQIYI_LOG_DIR environment variable or the default directory D:/temp/logs. You can also specify a custom log file path using the IQIYI_LOG_FILE environment variable.
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Get newly released videos.
Args:
count: Number of videos to return (default 10)
| Name | Required | Description | Default |
|---|---|---|---|
| count | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, but the description does not disclose key behavioral details such as how 'newly released' is defined, ordering, or pagination. Only the count parameter is mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, no redundant information, and front-loads the purpose. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and only one parameter, the description is too minimal. It omits what kind of response is returned (list of videos?), any filters, or how results are ordered. More context is needed for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description explains the 'count' parameter clearly (Number of videos to return, default 10), adding meaning beyond the schema which only specifies type and default. No other parameters exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Get newly released videos' which identifies the resource and verb, but lacks differentiation from sibling tool get_trending_videos. The term 'newly released' is ambiguous without time frame.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus get_trending_videos or any other context. The description does not provide use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get trending videos based on play count.
Args:
count: Number of videos to return (default 10)
| Name | Required | Description | Default |
|---|---|---|---|
| count | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears the full burden. It only mentions trending based on play count, omitting details like sort order, time range, rate limits, or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences) and front-loaded, though the 'Args:' section is slightly redundant but harmless.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is fairly complete but lacks definition of 'trending' (e.g., time frame, region) and return format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description adds value by explaining the 'count' parameter as 'Number of videos to return (default 10)', which the schema only specifies type and default.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get trending videos') and the criterion ('based on play count'), distinguishing it from the sibling tool 'get_new_releases' which likely returns newest releases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like 'get_new_releases'. The description does not mention exclusions or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_new_releasesget_trending_videosScored across 2 tools
The tools target distinct video categories: new releases vs. trending. While there could be some overlap, the descriptions clearly differentiate them based on release date vs. play count.
Both tools follow the consistent verb_noun pattern (get_new_releases, get_trending_videos), with similar structure and parameter naming.
With only 2 tools, the server is extremely minimal for a video platform. Typical video services require many more operations (details, search, categories, user interactions), so this feels insufficient.
The tool surface covers only basic read operations for two video lists. Missing essential operations like video details, search, categories, or any write actions, making it severely incomplete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Kling AI video generation
MCP server aggregating hot-search boards from 8 Chinese platforms (Weibo, Zhihu, Bilibili, Douyin).
MCP server for Wan AI video generation
MCP server for ByteDance Seedance AI video generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ZHANGYA0/mcp-server-iqiyi'
If you have feedback or need assistance with the MCP directory API, please join our Discord server