Span-level replay: fork from the failure MCP Server
by @com.textforagents
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
Span-level replay: fork from the failure MCP Server runs hosted, so there is nothing to install on your machine. The command below adds it to Claude Code, and the configs below connect Claude Desktop, Cursor and VS Code straight to the hosted endpoint.
Install
claude mcp add --transport http span-level-replay-fork-from-the-failure https://textforagents.com/products/span-level-replay-fork-from-failure/mcpHosted server
https://textforagents.com/products/span-level-replay-fork-from-failure/mcpThis server runs hosted, so there is no local process to install. The command above adds it to Claude Code, and the client configs below connect Claude Desktop, Cursor, and VS Code straight to the hosted endpoint. Any sign-in the server needs happens when you first connect.
Install with your client
claude mcp add --transport http span-level-replay-fork-from-the-failure https://textforagents.com/products/span-level-replay-fork-from-failure/mcp
Run this in a terminal to add the server to Claude Code.
What this does
Span-level replay: fork from the failure exposes a set of tools to Claude over the Model Context Protocol. It runs as a hosted server, so once you add it with the command above, those tools become callable inside any conversation, with nothing running on your machine.
Frequently asked questions
How do I install Span-level replay: fork from the failure?
Span-level replay: fork from the failure runs hosted, so there is nothing to install locally. The command on this page adds it to Claude Code, and the client configs connect straight to the hosted endpoint at https://textforagents.com/products/span-level-replay-fork-from-failure/mcp.
Which clients work with Span-level replay: fork from the failure?
This page carries setup and config for Claude Code, Claude Desktop, Cursor and VS Code. Any other MCP client that accepts a standard server config can connect to Span-level replay: fork from the failure as well.
Does Span-level replay: fork from the failure need an API key?
This listing does not ask for an API key or any environment variables.
Imported from the Official MCP Registry. The details above come from the registry entry; the maker can claim this listing to correct them, add docs, and see its traffic.
Is this your MCP server?
Claim this listing to see its traffic, fix details yourself, and skip the review queue on future updates.
Add this badge to your README
Show visitors this server is listed in the ClaudeRules directory. The badge links straight to this listing.
[](https://clauderules.net/mcp/com-textforagents-span-level-replay-fork-from-failure)<a href="https://clauderules.net/mcp/com-textforagents-span-level-replay-fork-from-failure" target="_blank" rel="noopener noreferrer"><img src="https://clauderules.net/api/badge/com-textforagents-span-level-replay-fork-from-failure" alt="Listed on clauderules.net" /></a>More Search MCP servers
GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Serena MCP: the IDE for your agent
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
mediar-ai/screenpipe
🎖️ 🦀 🏠 🍎 Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, semantic search, LLM-powered history analysis, and event-triggered actions - enables building c
MCP Toolbox for Databases
MCP Toolbox for Databases enables your agent to connect to your database.