User Agent Details
This will give your details about your Browser and Os and versions
MCP Server
The User Agents Samayas is also available as an MCP (Model Context Protocol) server. AI assistants and agents that speak MCP can analyze user agents directly instead of using the web form.
Endpoint
The server is hosted on this site at the address below, using the streamable HTTP transport (stateless) and no authentication, just like the public API:
Tools
MCP clients discover the tools automatically through the standard tools/list call. The server exposes a single tool:
analyze_user_agent
analyzes a user agent string and returns the browser, device, platform and engine breakdown alongside IP based whois, location and AS number details — the same analysis as the analyze page. The request takes a single required field:
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
userAgent | string | yes | The user agent string to analyze, e.g. Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:87.0) Gecko/20100101 Firefox/87.0. |
Response
The result is a single object with the analyzed string and the browser, platform and device breakdown, followed by network details of the calling client. The IP based fields are derived from the client IP address the request arrives from, so they describe the network the AI assistant runs on, not the analyzed user agent.
| Field | Type | Description |
|---|---|---|
userAgent | string | The analyzed user agent string. |
browser | string | Detected browser name and version. |
platform | string | Detected platform or operating system name. |
device | string | Detected device type. |
ipAddress | string | Client IP address the request arrived from. |
ipName | string | Reverse DNS (PTR) name of the client IP address. |
whoisName | string | Whois organization description of the client IP address. |
whoisDescription | string | Route description of the client IP address. |
location | string | Country of the client IP address. |
asNumber | string | Autonomous System number of the client IP address. |
Setup
Add the server to any MCP client configuration:
{
"mcpServers": {
"user-agents": {
"type": "http",
"url": "https://useragents.samayas.eu/mcp"
}
}
}Claude Code CLI
claude mcp add --transport http user-agents https://useragents.samayas.eu/mcpGitHub Copilot CLI
copilot mcp add user-agents --url https://useragents.samayas.eu/mcpCursor CLI
Cursor has no documented CLI add command — save the configuration above as .cursor/mcp.json in the project, or ~/.cursor/mcp.json globally.
VS Code
Run the MCP: Add Server command from the Command Palette, or save the configuration below as .vscode/mcp.json in the workspace.
{
"servers": {
"user-agents": {
"type": "http",
"url": "https://useragents.samayas.eu/mcp"
}
}
}Claude Desktop
Open the Settings, add a custom connector under Connectors and paste the endpoint URL below.
https://useragents.samayas.eu/mcpTry It
You can inspect the server without writing any configuration: run the MCP Inspector from npm and connect to the endpoint URL above with the Streamable HTTP transport. The Inspector lists the tool with its full JSON schema and lets you call it interactively.
npx @modelcontextprotocol/inspector --transport http https://useragents.samayas.eu/mcpThe MCP endpoint is rate limited to 20 requests per minute per client.
Invalid or missing input returns an MCP tool error (Input is incorrect or invalid). When the rate limit is exceeded, the endpoint responds with HTTP 429 and a Retry-After header.