# AskRobots Search

The AskRobots Search MCP server for Claude Code searches an independent web index and returns page and link details. Agents can use it to find pages, inspect sites, or retrieve stored text.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: askrobots
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/askrobots/askrobots-search-mcp
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/askrobots-search

## What it does

AskRobots Search queries an index built by its own crawler; it does not fetch live pages. Seven read-only tools cover search, stored summaries with sources, page and site details, backlinks, saved page text, and a site directory. Safe search stays enabled.

The hosted server requires an API key and returns 401 without one. The plan costs $25 per month for 500 searches, then $0.05 per search. Store the key in an environment variable and pass it in an authorization header. For Claude Code, run `claude mcp add --transport http askrobots-search https://search.askrobots.com/api/v1/mcp`. The read tool declines pages that block copying.

## Requirements
- Remote server: `https://search.askrobots.com/api/v1/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http askrobots-search https://search.askrobots.com/api/v1/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add askrobots-search --url https://search.askrobots.com/api/v1/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "askrobots-search": {
            "url": "https://search.askrobots.com/api/v1/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "askrobots-search": {
            "type": "http",
            "url": "https://search.askrobots.com/api/v1/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http askrobots-search https://search.askrobots.com/api/v1/mcp
```

## When to use it
- search an independent web index for relevant pages
- inspect a site's indexed pages and incoming links
- retrieve saved page text or a sourced search summary

## Example prompts
- Find pages about setting up an MCP server and show related searches.
- Check which sites link to this page.
- Read the saved page text and find its licensing details.

## Similar
- [Brave Search](https://affpapa.org/en/nevibecode/mcp/brave-search.md) — MCP server · 87579 installs
- [DuckDuckGo & Felo AI Search](https://affpapa.org/en/nevibecode/mcp/duckduckgo-felo-ai-search.md) — MCP server · 12697 installs
- [Exa Search](https://affpapa.org/en/nevibecode/mcp/exa-search.md) — MCP server · 9181 installs
- [web-search](https://affpapa.org/en/nevibecode/skills/web-search.md) — skill · 130800 installs
- [Web Search — Structured Results for AI Agents](https://affpapa.org/en/nevibecode/mcp/web-search-structured-results-for-ai-agents.md) — MCP server · 4334 installs
- [firecrawl-search](https://affpapa.org/en/nevibecode/skills/firecrawl-search.md) — skill · 85300 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
