# Not Human Search MCP server

> Search an index of websites, APIs and services ranked by how ready they are for AI agents, and check any URL's score.

- Listing: https://mcp.tc/i/not-human-search
- Connect: use the server's own URL `https://nothumansearch.ai/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: Not Human Search
- Homepage: <https://nothumansearch.ai/>

## About

Not Human Search indexes sites and APIs and scores each from 0 to 100 on seven agent-readiness signals: llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules and Schema.org. You can search the index, read per-site reports, list MCP servers, browse top and recent sites, and run live checks on any URL.

It runs as a hosted streamable HTTP endpoint at https://nothumansearch.ai/mcp. No sign-in or API key is needed. Some tools record action interest or prepare provider action tickets, and these are only used when the user explicitly wants a next step.

## What it can do

- Search agent-ready sites and APIs by keyword, category and score
- Get a full 7-signal readiness report for a domain
- Check any URL's agentic readiness live
- Verify that a URL serves a working MCP endpoint
- List indexed sites that expose MCP servers
- Browse top-scored and recently added sites
- Submit a site for crawling and scoring
- Register an email alert for score drops

## Tools (14)

- `search_agents`: Search sites, APIs and services ranked by agentic readiness score, with filters.
- `get_site_details`: Get the full readiness report and signal checks for a domain.
- `get_stats`: Get index statistics such as total sites and average score.
- `submit_site`: Submit a URL for crawling, scoring and indexing.
- `check_url`: Run a live 7-signal readiness check on any URL.
- `verify_mcp`: Probe a URL to confirm it serves a spec-compliant MCP endpoint.
- `register_monitor`: Register an email for alerts when a domain's score drops.
- `list_categories`: List index categories with site counts and average scores.
- `get_top_sites`: Get the highest-scored sites, optionally by category.
- `recent_additions`: List newly indexed sites, newest first.
- `find_mcp_servers`: List indexed sites that expose a live MCP server.
- `record_action_interest`: Record that the principal wants a next step with a returned site.
- `prepare_provider_action`: Prepare a signed ticket for a disclosed provider-funded offer.
- `handoff_provider_action`: Present a ticket to record a handoff and get the provider action URL.

## Example prompts

- "Find payment APIs that have an OpenAPI spec and a score above 80"
- "Check how agent-ready example.com is"
- "Verify whether this URL is a live MCP server"
- "List recently added MCP servers in the developer category"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http not-human-search https://nothumansearch.ai/mcp
```

2. Start Claude Code and type `/mcp`. **not-human-search** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Not Human Search** and paste this URL:

```url
https://nothumansearch.ai/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Not%20Human%20Search&connectorUrl=https%3A%2F%2Fnothumansearch.ai%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://nothumansearch.ai/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://nothumansearch.ai/mcp` as the server URL, then for authentication choose **No authentication**.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=not-human-search&config=eyJ1cmwiOiJodHRwczovL25vdGh1bWFuc2VhcmNoLmFpL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "not-human-search": {
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=not-human-search&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fnothumansearch.ai%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"not-human-search","type":"http","url":"https://nothumansearch.ai/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "not-human-search": {
      "type": "http",
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "not-human-search": {
      "serverUrl": "https://nothumansearch.ai/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add not-human-search --url https://nothumansearch.ai/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.not-human-search]
url = "https://nothumansearch.ai/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http not-human-search https://nothumansearch.ai/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "not-human-search": {
      "type": "http",
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://nothumansearch.ai/mcp`.

## Recent changes

- 2026-10-27 11:36 UTC: Tracking started: 14 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/not-human-search#history (Atom feed: https://mcp.tc/i/not-human-search/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.1.0
- MCP protocol version: 2025-06-18
- Last checked: 2026-11-17 (reachable)
- Listed: 2026-10-27
- Updated: 2026-10-27

---
Source: https://mcp.tc/i/not-human-search (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
