A search and web-page reading connection for AI agents, including searches of the web and X (formerly Twitter), plus X data tools. It requires a Desearch API key.

Use it to research topics, find posts or links on X, search websites, and extract text or HTML from a public URL.

It lets an agent find current information and read public pages without relying only on its built-in knowledge. It also brings web and X searches into the agent's workflow.

desearch — Plugin for Gemini CLI by Desearch-ai/mcp-desearch

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Desearch-ai/mcp-desearch

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/desearch-ai/mcp-desearch/gemini-extension/github.svg)](https://agentmods.dev/plugins/desearch-ai/mcp-desearch/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/desearch-ai/mcp-desearch/gemini-extension"><img src="https://agentmods.dev/badge/plugins/desearch-ai/mcp-desearch/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/desearch-ai/mcp-desearch/gemini-extension"><img src="https://agentmods.dev/badge/plugins/desearch-ai/mcp-desearch/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

desearch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

gemini-extension.json · 23 lines

What it actually says

{
  "name": "desearch",
  "version": "0.1.4",
  "description": "AI search, X search and web search for AI agents, plus page extraction and X data tools. Bring your own Desearch API key.",
  "mcpServers": {
    "desearch": {
      "httpUrl": "https://mcp.desearch.ai/mcp",
      "headers": {
        "x-api-key": "${DESEARCH_API_KEY}"
      }
    }
  },
  "contextFileName": "GEMINI.md",
  "settings": [
    {
      "name": "Desearch API key",
      "description": "Your Desearch API key from https://console.desearch.ai/api-keys",
      "envVar": "DESEARCH_API_KEY",
      "sensitive": true
    }
  ]
}

Files

What ships with it

1 file beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

assets/desearch-logo-400.png 12 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago Changed 9e7d96ed1cb3
11d ago First seen · 23 lines scan A d3bf5b628815

Subscribe to this mod's changes

desearch is a plugin published in the GitHub repository Desearch-ai/mcp-desearch (1 stars, last pushed 11d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.

Browser automation Research gemini-cli-extension

tauri-mcp-cli

Exposes Tauri MCP skills that can be used to control the webview of a running Tauri app from an AI assistant.

hypothesi/mcp-server-tauri · not measured

tauri-mcp

Agent Skills for automating and testing Tauri v2 applications.

hypothesi/mcp-server-tauri · not measured

charming

Create, update, and inspect Charming-hosted interactive web apps via the Charming MCP server.

tambo-labs/charming-mcp · not measured

anti-detect-browser-skills

Drive a browser that presents one coherent real device: AntiBrow's kernel-level fingerprints, persistent isolated profiles, and per-profile proxies with matching timezone and WebRTC - from the JavaScript/Python SDK, via MCP tool calls, or as task-level site recipes that return JSON and can run across many identities…

antibrow/anti-detect-browser-skills · not measured

vibesurfer

Agent-native headless browser.

frane/vibesurfer · not measured

groundhog

Web search, read and research through a real stealth-patched Chrome. Text hidden from human readers is stripped before the model reads it and reported, every source carries a SHA-256 provenance receipt, and the SSRF guard is re-checked after redirects.

dmytrome/groundhog · not measured