Knowngood

sh.knowngoodPublished by knowngood.shOfficial publisherv1.9.0Updated Oct 24, 2026

Search agent-ready sites or fetch one site's report; every capability probe-verified, dated.

VerifiedStreamable HTTPWeb executableWeb Search & Scraping

Overview

AI-generated overview

Lets an assistant search a directory of agent-ready websites or fetch a single site's dated, probe-verified report.

What you can do
Knowngood exposes a remote MCP endpoint with two apparent capabilities: searching a catalog of sites that are described as agent-ready, and fetching a report for one specific site. Reports are said to be probe-verified and dated, so results carry a timestamp and a check result rather than an unverified claim. No tool list is published in the manifest, so the exact tool names and parameters are not documented here.
When to use it
Worth considering when an assistant needs to judge whether a website is usable by an agent, or wants a dated verification record for a specific site before relying on it. Useful for pre-flight checks and comparisons across candidate sites rather than for general web browsing.
Requirements
A remote streamable HTTP MCP endpoint at the provider's host; no package, runtime, environment variable, header, or authentication is declared. Network access to that endpoint is required.
Before you install
The manifest declares no authentication, so it is unclear whether requests are anonymous or tied to an account, and no privacy or data-handling terms are given. The service is third-party and remote: queries and the sites you look up are visible to the provider. Treat the dated reports as the provider's own verification, not an independent audit, and confirm the current tool list before relying on specific calls.

Installation

In SourceWeft

  1. Open Knowngood 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/sh.knowngood%2Fknowngood/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": {
    "knowngood": {
      "type": "http",
      "url": "https://knowngood.sh/mcp"
    }
  }
}

Tools

3

check_webmcp

Check a site for WebMCP tools

Check a website LIVE for WebMCP tools, and where a browser is available whether any tool actually registers when the page runs. Returns one of: registered, declared_only, declared, not_declared, could_not_ask, or excluded when the site's robots.txt refuses AI input. could_not_ask is a distinct answer and is never reported as a no. Tools are listed, never called. Reads only the site named plus published population figures — it does not consult the index, and running it changes no ranking or listing.

Parametersurlrequired

find_capability

Find agent-ready websites

Find websites where an agent can accomplish a task. Returns probe-verified agent-readiness signals, unverified apparent actions read from page content, the verification tier, how each site was found (it declared agent access, probe discovery, or it was submitted), and a report URL to cite. Returns count:0 with an empty_note when nothing in the index matches — never a nearest guess.

Parameterslimitqueryhas_mdcountryhas_mcphas_webmcpentity_typehas_endpointtransactional

get_site_report

Fetch one site's verification report

Fetch Known Good's dated verification report for one listed website: which capabilities were tested, which passed, when it was probed, what an agent can apparently do there, and how the site was found: whether it declared agent access, came from probe discovery, or was submitted. Answers "is this specific host agent-ready?". Returns found:false for anything not in the index — it never guesses a nearest match. Cite the report URL and its date.

Parametershostrequired

Version history

4
  1. v1.9.0LatestOct 13, 2026
  2. v1.8.0Oct 8, 2026
  3. v1.7.0Sep 23, 2026
  4. v1.6.0Sep 16, 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.