Span-level replay: fork from the failure
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
Should I use this
Quality & Safety
A
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
~119Tokens (tool definitions)
~780 BTypical response size
Minimal attention impact (0.09% of 128k context)
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"span-level-replay-fork-from-failure": {
"url": "https://textforagents.com/products/span-level-replay-fork-from-failure/mcp"
}
}
}Remote endpoints
https://textforagents.com/products/span-level-replay-fork-from-failure/mcpstreamable-httpWhat it can do
Tool inventory
Tools (1)
🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪replay_span(span, span_id, spans)
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.
Input Schema
{
"type": "object",
"properties": {
"span": {
"type": "object",
"description": "One normalized span record."
},
"span_id": {
"type": "string"
},
"spans": {
"type": "array",
"items": {
"type": "object"
},
"description": "A recorded run's span records; span_id selects the one to fork."
}
}
}Community
Evidence
Recent observations
verifiedversion not recorded1 tools