Skip to main content
Glama

check_reliability

Check reliability ratings for APIs and MCP servers using independent synthetic probes and crowdsourced telemetry to assess uptime, latency, and error rates before committing to a service.

Instructions

Look up the independent reliability rating for an API or MCP server. Like checking a restaurant's reviews before booking — see the real uptime, latency, error rate, and community experience before you commit to a service.

Returns a trust score (0-100), current operational status, trend direction, and any known issues. Scores are based on independent synthetic probes and crowdsourced telemetry from real agent traffic — not vendor self-reporting.

Args: service: Service slug (e.g., 'stripe-mcp', 'openai-api') or partial name metrics: Optional list of specific metrics to include: 'uptime', 'latency', 'reliability', 'maintenance', 'community'

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
serviceYes
metricsNo

Implementation Reference

  • The handler for the `check_reliability` tool, which queries the Preflight API for service reliability metrics.
    async def check_reliability(
        service: str,
        metrics: list[str] | None = None,
    ) -> dict:
        """Look up the independent reliability rating for an API or MCP server.
        Like checking a restaurant's reviews before booking — see the real uptime,
        latency, error rate, and community experience before you commit to a service.
    
        Returns a trust score (0-100), current operational status, trend direction,
        and any known issues. Scores are based on independent synthetic probes and
        crowdsourced telemetry from real agent traffic — not vendor self-reporting.
    
        Args:
            service: Service slug (e.g., 'stripe-mcp', 'openai-api') or partial name
            metrics: Optional list of specific metrics to include:
                     'uptime', 'latency', 'reliability', 'maintenance', 'community'
        """
    
        params = {"service": service}
    
        if metrics:
            params["metrics"] = ",".join(metrics)
    
        try:
            async with httpx.AsyncClient(timeout=10) as client:
                resp = await client.get(
                    f"{PREFLIGHT_API}/v1/score", params=params, headers=_headers()
                )
    
                resp.raise_for_status()
    
                return resp.json()
        except httpx.HTTPStatusError as exc:
            return {
                "error": True,
                "status_code": exc.response.status_code,
                "detail": exc.response.text,
            }
        except (httpx.ConnectError, httpx.TimeoutException) as exc:
            return {
                "error": True,
                "status_code": None,
                "detail": f"Connection failed: {exc}",
            }
  • Registration of the `check_reliability` tool using the @mcp.tool decorator.
    @mcp.tool
    async def check_reliability(

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gsmethells/preflight-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server