Tool-Confusability Recovery Loop

com.textforagentsPublished by textforagents.comOfficial publisherv2.0.0Updated Oct 29, 2026

Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts.

The publisher's own server: Agent NOTAMs: hazard bulletins for agents

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Remote service that measures confusion between tools in an agent tool catalog, ranks fixes, and issues signed recovery receipts.

What you can do
  • Register a tool catalog with a probe suite and store its green baseline state
  • Start a recovery loop run against the live catalog and track its status
  • Serve a revised catalog for a chosen worklist item and re-probe it
  • Return a signed recovery receipt once a fix is verified
  • Measure a single submitted tool against curated reference stacks and give a pre-publish verdict
When to use it
Useful when you maintain an MCP or agent tool catalog and want to check whether tools are easily confused with one another, get ranked fixes, and keep signed evidence that a revision actually recovered.
Requirements
A remote streamable HTTP endpoint at textforagents.com; no packages, environment variables or headers are declared. Registration is free, but starting a loop run is billed per plan with the first run free.
Before you install
Starting a recovery loop run costs money ($0.05 per plan, first run free), so confirm pricing before repeated runs. Registering a catalog and serving revised catalogs sends your tool definitions to a third-party service; avoid including secrets or private data in catalog entries.

Installation

In SourceWeft

  1. Open Tool-Confusability Recovery Loop in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.textforagents%2Ftool-confusability-regression-gate/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "tool-confusability-recovery-loop": {
      "type": "http",
      "url": "https://textforagents.com/products/tool-confusability-regression-gate/mcp"
    }
  }
}

Tools

6

register_catalog

Register a tool catalog + probe suite; stores the green state. Free.

Parametersprobesrequiredcatalogrequired

start_loop

Start a recovery loop run against the current live catalog ($0.05 / plan / first run free).

Parameterscatalogrequiredcatalog_idrequiredselector_class

apply_fix

Serve the revised catalog for a chosen worklist item of an open loop run.

Parametersitemrequiredloop_idrequired

verify_recovery

Re-probe a loop run whose fix was served and return the signed recovery receipt.

Parametersloop_idrequired

server_author_verdict

Server-author pre-publish verdict: measure one submitted tool against the curated reference stacks; every verdict names its stack.

Parameterstoolrequiredstack

loop_status

Fetch a loop run's status and receipt.

Parametersloop_idrequired

Version history

1
  1. v2.0.0LatestOct 29, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Textforagents integrations

Agent NOTAMs: hazard bulletins for agents

com.textforagentsOfficial publisher

Remote MCP endpoint that gives agents signed, auto-expiring hazard bulletins for tools and APIs, plus pre-flight checks.

Streamable HTTPWeb executableAuth
Security & MonitoringCredential requiredOct 26, 2026

The Bridge Stack — one stack, every LLM linked

com.textforagentsOfficial publisher

The Bridge Stack — one stack, every LLM linked's hosted MCP server, published by textforagents.com; no sign-in required; Streamable HTTP; 3 tools.

Streamable HTTPWeb executable
AI & ML3 toolsNov 3, 2026

Combined Server-Surface Census

com.textforagentsOfficial publisher

Combined Server-Surface Census's hosted MCP server, published by textforagents.com; no sign-in required; Streamable HTTP; 5 tools.

Streamable HTTPWeb executable
5 toolsOct 31, 2026

Widget-storage residue verdict

com.textforagentsOfficial publisher

Widget-storage residue verdict's hosted MCP server, published by textforagents.com; no sign-in required; Streamable HTTP; 3 tools.

Streamable HTTPWeb executable
Browser Automation3 toolsOct 29, 2026

Paid Call Checkout Conformance Probe

com.textforagentsOfficial publisher

Remote MCP probe that pays a merchant's checkout endpoint like an outside buyer and returns a signed conformance verdict, with pricing and payment instructions.

Streamable HTTPWeb executable
Developer Tools3 toolsOct 29, 2026