Skip to main content
Glama
Sign In
preflight-mcp

preflight-mcp

by gsmethells
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Preflight MCP Server

TrustPilot for APIs, built for AI agents. Independent reliability ratings for every API and MCP server — powered by synthetic probes and crowdsourced agent telemetry.

Install

pip install preflight-mcp

Usage

As a standalone MCP server

preflight-mcp

With Claude Desktop

Add to your Claude Desktop MCP config:

{
  "mcpServers": {
    "preflight": {
      "command": "preflight-mcp"
    }
  }
}

With Claude Code

/plugin install preflight@claude-plugins-official

Tools

check_reliability

Look up the independent reliability rating for any service.

check_reliability(service="openai-api")

compare_services

Compare ratings side by side to pick the most reliable provider.

compare_services(services=["openai-api", "anthropic-api"])

report_outcome

Leave a review — report what happened when you called a service. Improves ratings for everyone.

report_outcome(service="openai-api", outcome="success", latency_ms=200)

Configuration

Variable

Default

Description

PREFLIGHT_API_URL

https://preflight.beamt.io

API base URL

PREFLIGHT_API_KEY

(none)

API key for authenticated requests

Get a free API key at beamt.io/preflight.

License

MIT

Available Tools

3 tools
check_reliabilityA

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'

Inputs: service (required), metrics. Returns: object

compare_servicesA

Compare reliability ratings across multiple services side by side. Like reading comparative reviews — see which provider has the best track record for uptime, latency, and real-world reliability right now.

Returns services ranked by the chosen metric with a recommendation and the reasoning behind it.

Args: services: List of service slugs to compare (max 10) sort_by: Metric to sort by — 'overall', 'uptime', 'latency', 'reliability'

Inputs: services (required), sort_by. Returns: object

report_outcomeA

Leave a review — report the outcome of an API or MCP server call you just made. Like writing a TrustPilot review, your report contributes to the community reliability rating for that service.

The more agents that report, the more accurate the ratings become for everyone.

Args: service: Service slug that was called outcome: Result — 'success', 'error', 'timeout', or 'unexpected' latency_ms: Response time in milliseconds (if available) error_type: If outcome was 'error', the category: 'auth', 'rate_limit', 'server', 'network', 'parse', 'other'

Inputs: service (required), outcome (required), latency_ms, error_type. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: check_reliability evaluates a single service, compare_services compares multiple services side-by-side, and report_outcome submits user feedback. There is no overlap in functionality—an agent would never confuse which tool to use for a given task.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with clear, descriptive names: check_reliability, compare_services, and report_outcome. The naming is uniform and predictable, making it easy for agents to understand each tool's function at a glance.

    Tool Count3/5

    With only 3 tools, the server feels slightly thin for its reliability-checking domain. While the tools cover core functions, additional utilities like listing top-rated services or fetching historical trends might be expected. However, the count is not severely inadequate.

    Completeness4/5

    The toolset covers the essential reliability workflow: checking individual services, comparing them, and contributing data. A minor gap is the lack of a tool to fetch aggregated reliability data (e.g., a leaderboard or trending services), but agents can work around this by using compare_services with a predefined list.

    Resources

    Related MCP Connectors