Ant Design ComponentsSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that exposes Ant Design component documentation to Large Language Models (LLMs) like Claude. This server allows an LLM to explore and understand Ant Design components through a set of specialized tools.
Features
- Easy to use - no need to clone the entire Ant Design repository
- Pre-extracted component documentation for faster startup
- List all available Ant Design components
- Get detailed component documentation including descriptions and usage
- View component props and API definitions
- Browse code examples for specific components
- Search for components by name or functionality
Initial Setup
Before using the MCP server for the first time, you need to extract the documentation from the Ant Design repository:
# First, clone the Ant Design repository (can be temporary) git clone https://github.com/ant-design/ant-design.git # Extract documentation cd mcp-antd-components npm run extract # Uses the default ./ant-design path # OR node scripts/extract-docs.mjs /path/to/ant-design # For a custom path # After extraction is complete, the Ant Design repo can be deleted if desired
This will create a data directory with all the extracted component documentation, which the MCP server will use.
Testing the Server
To verify that everything is working correctly, you can run the test script:
npm test # OR node scripts/test-server.mjs
This will run the MCP server and test all available tools with sample queries.
Usage
Command Line
Run the MCP server:
# Run server with pre-extracted data npm start # OR npx -y mcp-antd-components
Claude Desktop Integration
To use this MCP server with Claude Desktop, edit your claude_desktop_config.json configuration file:
{
"mcpServers": {
"Ant Design Components": {
"command": "npx",
"args": ["-y", "mcp-antd-components"]
}
}
}Location of
0f4d877f00b3OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-antd-components -- npx -y [email protected]
{
"mcpServers": {
"mcp-antd-components": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get-component-docs | read | Gets detailed documentation for a specific component |
get-component-example | read | Gets the code for a specific component example |
get-component-props | read | Gets the props and API documentation for a specific component |
list-component-examples | read | Lists all examples available for a specific component with descriptions |
list-components | read | Lists all available Ant Design components |
search-components | read | Search for components by name pattern |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, zod
Gates applied: no_behavioural_pass, no_license.
0f4d877f00b3full audit observations/trust-audit/mcp-server/hannesj__ant-design-components.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 0f4d877f00b3 | SAFE | B | 89 | first audit |
Questions
What tools does Ant Design Components expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Ant Design Components safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Ant Design Components need?
No credential environment variables were found in its source, so it appears to need none.
How does Ant Design Components run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-antd-components at 0.0.1.
How current is this page?
The grade is for one exact copy of the source (0f4d877f00b3), read on 2026-10-08. The repository is watched and re-audited when it changes.