Skip to main content
Glama

faultydata

Server Details

Cited, replayable HTTP failure signatures — test any HTTP client against real outages.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 5 tools

Disambiguation4/5

Each tool targets a distinct action (list, detail, replay instructions, battery start, report score), so an agent can generally tell them apart. Minor overlap exists because get_specimen returns a 'replay signature' while replay_instructions separately explains replaying, which could cause slight confusion about where replay details live.

Naming Consistency4/5

Four tools follow a clear verb_noun pattern (get_report, get_specimen, list_specimens, start_battery). replay_instructions breaks that pattern as a noun phrase, but the overall convention remains readable and predictable.

Tool Count5/5

Five tools is well-scoped for a focused failure-specimen registry with battery scoring. Each tool clearly earns its place without redundancy or thinness.

Completeness4/5

The surface covers listing and fetching specimens, replay guidance, starting a battery, and scoring a report, which matches the core read/run workflow. Minor gaps exist around searching/filtering specimens or checking battery run status, but agents can work around them.

Available Tools

5 tools
get_reportCInspect

Score a battery session and return the report card.

Inputs: token (required).

get_specimenAInspect

Get a specimen's anatomy (the incident story), citation, and replay signature.

Inputs: id (required).

list_specimensAInspect

List every failure specimen in the FaultyData registry as a compact summary (id, title, category, severity, path, real-world flag, test tags). Use get_specimen for the full story and signature.

Inputs: no named parameters.

replay_instructionsBInspect

How to replay a specimen against a client-under-test (URL, curl, params for seed/key).

Inputs: id (required).

start_batteryAInspect

Mint a report-card battery token. The client then runs /run/{token}/{id} per specimen and reports outcomes.

Inputs: client.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Local-first MCP and coding-agent reliability harness that captures bounded, sanitized failure evidence and generates deterministic executable regression tests. Capture is opt-in; no API key or hosted service is required.
      2
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables agents and developers to test HTTP client retry behavior against a synthetic service that emits 429/503 responses followed by 200, with Retry-After headers and server-observed attempt traces, plus optional sharing of synthetic evidence findings.
      MIT
    • A
      license
      C
      quality
      B
      maintenance
      Serves configurable fake service worlds as MCP tools with fault injection, recording every call and enabling seeded pytest assertions on final state.
      4
      2
      Apache 2.0
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources