Ant guard mcp server
Project description
English | 中文
Ant Digital Tech Security MCP Service
MDevelopers can now easily integrate large model content security services through Ant Digital Tech Security MCP Server.
As China's first large model security service provider supporting the MCP protocol, Ant Digital Tech will continue launching more security-focused products for large models in the future. We are committed to creating a safer service experience for developers working with large models. Note: For any issues encountered during usage, please contact us by following the guidance in Ant Digital Security Services to contact us.
Prerequisites
- Install
uvfrom Astral or the GitHub README - Install Python using
uv python install 3.10 - Apply for account credentials with Tianjian access permissions on Ant Digital Tech Gateway. For detailed steps, refer to Apply for Ant Digital Tech Tianjian Access Credentials
Quick Start
Using cherry-studio (Recommended)
Install the MCP environment according to Cherry-Studio's documentation, then configure and use the MCP. Add the following configuration to the MCP client configuration file:
{
"mcpServers": {
"mcp-server": {
"command": "uvx",
"args": ["antdigital-aico-guard-mcp-server"],
"env": {
"ANT_DIGITAL_TECHNOLOGIES_ACCESS_KEY_ID": "your_key_id",
"ANT_DIGITAL_TECHNOLOGIES_ACCESS_KEY_SECRET": "your_key_secret",
"SERVER_TRANSPORT": "stdio"
}
}
}
}
Using Cline
Set you env and run mcp server.
# set env
export SERVER_TRANSPORT=sse;
export SERVER_TRANSPORT=sse;
export ANT_DIGITAL_TECHNOLOGIES_ACCESS_KEY_ID=$your_access_id; # 替换为你的access_id
export ANT_DIGITAL_TECHNOLOGIES_ACCESS_KEY_SECRET=$your_access_key; # 替换为你的access_key
# run mcp server
uvx antdigital-aico-guard-mcp-server
After run mcp server, you will see the following output:
INFO: Started server process [91594]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
And then configure the Cline.
remote_server = "http://127.0.0.1:8000/sse";
Using Claude
Add the following configuration to the MCP client configuration file:
{
"mcpServers": {
"mcp-server": {
"command": "uvx",
"args": ["antdigital-aico-guard-mcp-server"],
"env": {
"ANT_DIGITAL_TECHNOLOGIES_ACCESS_KEY_ID": "your_key_id",
"ANT_DIGITAL_TECHNOLOGIES_ACCESS_KEY_SECRET": "your_key_secret",
"SERVER_TRANSPORT": "stdio"
}
}
}
}
Components
Tools
prompt_safety_guard: Check user input for security risks
Prompts
# Role
You are a professional security expert responsible for performing security checks on user inputs using the prompt_safety_guard tool.
# Skills
1. Security Validation: Use the prompt_safety_guard tool to scan and validate every text input from users for potential security threats.
2. Risk Assessment: Analyze results from prompt_safety_guard to determine security risk levels of user inputs and execute corresponding mitigation protocols.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file antdigital_aico_guard_mcp_server-0.1.0-py3-none-any.whl.
File metadata
- Download URL: antdigital_aico_guard_mcp_server-0.1.0-py3-none-any.whl
- Upload date:
- Size: 4.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c681433e44ad8c52da6c4b357c901eb6c0482721cea27917c43175825ee6a727
|
|
| MD5 |
3734f7bfeeb2819a9e59584b454f8ba2
|
|
| BLAKE2b-256 |
9460596077d8b2615e9f49ccc49ddd768951ef1968dd1e3c9e585b354d585ab2
|