Skip to content

Span-level replay: fork from the failure

by textforagents.com · remote · no sign-in to list tools · v1.0.0 · published by com.textforagents

Fork-replay one recorded span from a failed agent run and get an attribution verdict.

Changes · 2
CompareRegistry entry

2 tools: 2 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http span-level-replay-fork-from-failure https://textforagents.com/products/span-level-replay-fork-from-failure/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 2Claude Code: ask
  • fork_safety_checkExamine ONE recorded span (or a run's span set) forensically — canonicalization, env binding, completeness, stub coverage — and return the fork-safety verdict (FORK-SAFE-LIVE / FOR…No findings

    Why it is in this group

    • The name "fork_safety_check" says "fork": a word for a change.
    Description, as the server wrote it
    Examine ONE recorded span (or a run's span set) forensically — canonicalization, env binding, completeness, stub coverage — and return the fork-safety verdict (FORK-SAFE-LIVE / FORK-SAFE-STUBBED / FORK-DEGRADED / FORK-UNSAFE) WITHOUT executing the span or forking anything. $0.01 per span checked on the hosted surface.
  • replay_spanFork-replay ONE recorded span from a failed agent run and return an attribution verdict (determinism vs tool drift vs env drift vs world-state vs model decision), without re-runnin…No findings

    Why it is in this group

    • The description's first verb is "fork": a word for a change.
    Description, as the server wrote it
    Fork-replay ONE recorded span from a failed agent run and return an attribution verdict (determinism vs tool drift vs env drift vs world-state vs model decision), without re-running the whole run.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http span-level-replay-fork-from-failure https://textforagents.com/products/span-level-replay-fork-from-failure/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__span-level-replay-fork-from-failure__replay_span",
      "mcp__span-level-replay-fork-from-failure__fork_safety_check"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as span-level-replay-fork-from-failure. Review it before you use it.