com.textforagents/span-level-replay-fork-from-failure
Span-level replay: fork from the failure
Is the Span-level replay MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-26.
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
alive probed 2026-11-15 · unchanged since 2026-10-26 · HTTP 200
- Endpoint
- https://textforagents.com/products/span-level-replay-fork-from-failure/mcp (streamable-http)
- Host
- textforagents.com
- Protocol
- 2024-11-05
- Reports itself as
- span-level-replay-fork-from-failure 1.0.0
- Capabilities
- tools
- Instructions
- none
- Of a 1M window
- <0.1 % of a 1M context window
- Count
- 464 tokens in Claude, exact, measured 2026-10-25. With the Claude Code prefix mcp__…__ on each tool name: 502. The o200k_base estimate is 272. Counted again when the tool definitions change. Method.
- Website
- https://textforagents.com/products/span-level-replay-fork-from-failure/
- Registry
- active, updated 2026-10-20 · registry entry
- Changes
- 4 recorded, reachable in 3 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.71×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| fork_safety_check | 271 | 159 | 58 % |
| replay_span | 193 | 113 | 42 % |
Compare this server with others.
More servers
Other registry entries on textforagents.com, the ones next to this name; all of them.
- com.textforagents/seller-funded-verification-bond · alive
- Shared team memory for agents com.textforagents/shared-team-agent-memory · needs auth
- Silent tool-failure outcome monitor com.textforagents/silent-tool-failure-outcome-monitor · needs auth
- Single-Use Agent Burn Receipt com.textforagents/single-use-agent-burn-receipt · alive
- Spawn-tree fan-out governor com.textforagents/spawn-tree-fanout-governor · needs auth
- com.textforagents/stage-completeness-receipts · alive
- Standing-offer envelopes: offline agent deals com.textforagents/standing-offer-envelopes-offline-agent-deals · alive
- Sterile Cockpit for Irreversible Actions com.textforagents/sterile-cockpit-for-irreversible-actions · alive
Servers that mention failure.
- AFMR Discovery ai.afmr/discovery · alive
- ai.imaginode/imaginode · needs auth
- ai.nullary/nullary · alive
- ai.plith/plith · alive
- Agent Rescue Desk Production Triage app.netlify.agent-rescue-desk/production-triage · alive
- BuyerAware com.buyerawareapp/buyeraware · alive
- com.clauxel.a2areplayreceipt/a2areplayreceipt-mcp · no DNS
- Claidex MCP com.claidex/failure-intelligence · not found
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-25 20:41 | alive | 143 ms | 2 | 464 | 272 |
| 2026-10-23 09:44 | alive | 77 ms | 2 | 272 | |
| 2026-10-21 09:49 | alive | 126 ms | 1 | 113 | |
| 2026-10-20 09:44 | server error |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers initialize and tools/list. Nothing to fix.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.