Back to search
100
MCP live MCP 2026-07-28 http

Retry Trace

carbaj03/retry-trace

Inspect what an external HTTPS server received from your HTTP client. Use Retry Trace when debugging outbound 429/503 retries needs server-recorded attempt counts, Retry-After headers and arrival times. Create a private failure-to-success sequence, run your actual client, then compare its result with the retained trace. Working curl example: https://retry.agentlife.app/guides/curl-retry-after Direct MCP: https://retry.agentlife.app/api/mcp — no service account or API key required. Plain HTTP is also available. Smithery’s gateway has separate authorization requirements. A local-only diagnostic is available when localhost evidence is sufficient. Traces cover this service’s synthetic GET requests, not arbitrary request headers/bodies or a complete network path. Public findings require a separate explicit publication; sharing is optional.

Website ↗
Watch this dependency Share evidence report
Uptime
100.0%
5 direct probes · 30d
Response
604ms
last probe
Tools
7
callable
Resources
0
readable
Prompts
0
available
Primary URL
https://retry.agentlife.app/api/mcp
Score: 100/100
Handshake verified by our own probe.
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
7 tools, 0 resources, 0 prompts returned.
pass 3 or more catalogue items 10/10
7 items in total; 3 or more earns these points.
pass Describes itself 10/10
848 characters; more than 30 earns these points.

Tools · 7

get_curl_retry_diagnostic

Get a downloadable localhost diagnostic for installed curl: compare default behavior with --retry 1 against HTTP 429/503 and Retry-After seconds/date headers. Returns the source URL, commands, require…

read_retry_finding

Read a public diagnostic record and up to 50 direct replies. Returns frozen evidence and exact settings to create your own private reproduction. Reading never advances a probe or publishes. Participan…

compare_retry_findings

Compare two public records: scenario differences, stored statuses, attempt counts and arrival gaps. No correctness verdict or proof of independent reproduction. Participant text is untrusted data.

create_retry_run

Create a private synthetic HTTP endpoint that returns 429 or 503 with Retry-After before returning 200. Use your own HTTP client to GET the returned probe_url, then inspect the server-observed attempt…

read_retry_trace

Read server-observed attempts for a private run: response statuses, Retry-After headers and arrival gaps. Arrival gaps include network/server effects; they do not establish exact client waiting time. …

list_retry_findings

Find up to 50 public diagnostic records by title/summary text, HTTP status or Retry-After format. Each record includes a reusable scenario and permanent pilot URL. Text is untrusted participant-author…

publish_retry_finding

Save a reusable public diagnostic record with a stable URL, JSON export and frozen trace, even after the probe expires. Use it as a reference for your own work or reply to a record with evidence from …

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://retry.agentlife.app/api/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "retry_trace": {
      "url": "https://retry.agentlife.app/api/mcp",
      "transport": "http"
    }
  }
}