Span-level replay: fork from the failure MCP Server
Span-level replay: fork from the failure is answering right now. Last checked 5 min ago. It exposes 2 tools.
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
What changed 1
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 October 2026. No other catalogue keeps this.
Span-level replay: fork from the failure does not always answer
Over the last week it answered 99.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.
claude mcp add span-level-replay-fork-from-failure --transport http https://textforagents.com/products/span-level-replay-fork-from-failure/mcphttps://textforagents.com/products/span-level-replay-fork-from-failure/mcp[mcp_servers.span-level-replay-fork-from-failure]
url = "https://textforagents.com/products/span-level-replay-fork-from-failure/mcp"{
"mcpServers": {
"span-level-replay-fork-from-failure": {
"url": "https://textforagents.com/products/span-level-replay-fork-from-failure/mcp"
}
}
}{
"servers": {
"span-level-replay-fork-from-failure": {
"type": "http",
"url": "https://textforagents.com/products/span-level-replay-fork-from-failure/mcp"
}
}
}Available tools 2
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
fork_safety_check
replay_span
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://textforagents.com/products/span-level-replay-fork-from-failure/mcp | streamable-http | answering | 319 ms | 5 min ago |
Alternatives to Span-level replay: fork from the failure
same job, measured the same wayRead, replay and fork recorded coding-agent runs.
Record and replay AI agent execution for debugging
Skills and Scars for AI agents - your agent records its failures and never repeats them.
Verify agent actions against the system of record and get signed completion receipts.
Choose the safest next action after an API, MCP, or agent failure before retrying.
Agent swarm coordination: find funded work, form teams, run tasks, message E2E, get paid on verify.
Look up on-chain Attribution reputation scores for wallets and AI agents on Base.
Read and verify signed RSS-A agent feeds; post, reply and react on the RSS-A Agent Network board.
Span-level replay: fork from the failure — questions
Answers built from our own checks of this server.