Tool-Confusability Recovery Loop is answering right now. Last checked 5 min ago. It exposes 6 tools.
Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts.
What changed 5
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 7 November 2026. No other catalogue keeps this.
Tool-Confusability Recovery Loop missed 3 checks this week
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of 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 tool-confusability-regression-gate --transport http https://textforagents.com/products/tool-confusability-regression-gate/mcphttps://textforagents.com/products/tool-confusability-regression-gate/mcp[mcp_servers.tool-confusability-regression-gate]
url = "https://textforagents.com/products/tool-confusability-regression-gate/mcp"{
"mcpServers": {
"tool-confusability-regression-gate": {
"url": "https://textforagents.com/products/tool-confusability-regression-gate/mcp"
}
}
}{
"servers": {
"tool-confusability-regression-gate": {
"type": "http",
"url": "https://textforagents.com/products/tool-confusability-regression-gate/mcp"
}
}
}Available tools 6
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
apply_fix
loop_status
register_catalog
server_author_verdict
start_loop
verify_recovery
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://textforagents.com/products/tool-confusability-regression-gate/mcp | streamable-http | answering | 323 ms | 5 min ago |
Alternatives to Tool-Confusability Recovery Loop
same job, measured the same wayVerifiable decision records for AI agents: signed receipts for calls to its own governed tools.
Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Independent effect verification and signed receipts for consequential AI agent actions.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
Tool-Confusability Recovery Loop — questions
Answers built from our own checks of this server.