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., "@API Health Check MCP Server check the health of the ticket API endpoint"
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 Model Context Protocol (MCP) server provides tools to check the health status of API endpoints. Specifically designed to monitor the GET localhost:8080/api/ticket endpoint.
Health Check Tool: Checks if the API endpoint is up or down
Response Time Monitoring: Measures and reports API response times
Error Handling: Provides detailed error information when the API is unreachable
Timeout Protection: Automatically times out requests after 10 seconds
Formatted Output: Returns easy-to-read status reports with icons and timestamps
Related MCP server: MCP Health Monitor
Clone this repository
Install dependencies:
npm installBuild the project:
npm run buildAdd this server to your Claude Desktop configuration:
{
"mcpServers": {
"api-health-check": {
"command": "node",
"args": ["C:/Project Workspace/MCP/build/index.js"]
}
}
}npm run build - Build the TypeScript source
npm run watch - Watch for changes and rebuild automatically
npm start - Run the compiled server
check_api_healthChecks the health of the GET localhost:8080/api/ticket endpoint.
Parameters: None
Returns:
API status (up/down)
Response time in milliseconds
HTTP status code (if successful)
Error details (if failed)
Timestamp of the check
Example Output:
ā
API Status: UP
š Checked at: 2024-01-15T10:30:45.123Z
ā±ļø Response time: 150ms
š HTTP Status: 200The server handles various error conditions:
Connection Refused: When the target server is not running
Timeout: When requests take longer than 10 seconds
Host Not Found: When localhost cannot be resolved
HTTP Errors: When the server returns non-200 status codes
This server is built using:
TypeScript
Node.js Fetch API
Check if the GET localhost:8080/api/ticket endpoint is up or down
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry full behavioral context. It implies a GET request but does not disclose possible responses (e.g., boolean, HTTP status), error cases, or side effects (e.g., if the check is read-only).
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 a single sentence that gets straight to the point. Every word is essential, no fluff, and it is front-loaded with the action.
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?
Given no output schema and no annotations, the description lacks crucial behavior details like return format, timeout behavior, or what constitutes 'up' vs 'down'. An AI agent would need more info to interpret the result correctly.
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 input schema has zero parameters (100% coverage trivially), so baseline is 4. The description adds the specific endpoint and method, which is meaningful context not captured in the schema, but no param details are needed.
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 tool checks a specific endpoint (GET localhost:8080/api/ticket) for up/down status. Verb and resource are precise, and with no sibling tools, differentiation is unnecessary.
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 when-to-use or when-not guidance is provided. Since there are no siblings, the context is implied for checking endpoint health before other operations, but alternatives are not discussed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity between tools.
The single tool uses a clear snake_case naming convention, so no inconsistency exists.
A single tool that checks only one hardcoded endpoint is trivial for a health check server, which would typically need multiple endpoints or generic checks.
The tool surface is severely incomplete, as it only covers checking one specific endpoint, lacking support for other endpoints or dynamic health checks.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Uptime monitoring: create and manage HTTP, API, SSL, ping, port and domain checks
Uptime, API and server monitoring with outages, reporting, on-call and status pages.
API monitoring from your editor. Checks the JSON your endpoints return, not just the status code.
Real-time health monitoring and heartbeat tracking for agent services
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/eiabhiram/api-healthcheck-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
