AgentSearch (agentsearchhq.com)

io.github.agentsearchhq-coderv1.1.1Updated Oct 3, 2026

AgentSearch web search, page extract and JS page render for agents. Self-hosted API via stdio.

VerifiedSTDIODesktop onlyDeveloper ToolsWeb Search & Scraping

Overview

AI-generated overview

Lets an assistant run web search, page extraction, and JavaScript page rendering through your own self-hosted AgentSearch-compatible API.

What it does
Exposes three read-only tools over stdio: agentsearch_web_search for queries, agentsearch_extract for pulling content from a URL you already have, and agentsearch_render, which renders JavaScript-heavy pages in headless Chromium and returns title, status, meta, and markdown, text, HTML, or links, with an optional screenshot. All three call your own AgentSearch-compatible backend over HTTP.
When to use it
Use it when you already run an AgentSearch-compatible backend and want Cursor, Claude Desktop, or another MCP host to search the web, extract pages, or render single-page apps. Prefer extract for static pages and render when extract returns empty or partial content.
Requirements
Node.js 20 or later, plus your own AgentSearch-compatible API. AGENTSEARCH_BASE_URL is required and has no default; the process exits at startup if it is missing. AGENTSEARCH_API_KEY is optional and sent as a Bearer token. Network access to your backend is needed.
Before you install
AGENTSEARCH_API_KEY is an optional secret sent as an Authorization Bearer header; on a 401 the client retries once without it. The README warns never to commit a real .env. The tools are read-only HTTP, but they send the URLs and queries you give them to your configured backend, and render fetches third-party pages.

Installation

In SourceWeft

  1. Open AgentSearch (agentsearchhq.com) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agentsearch-mcp

MCP (Model Context Protocol) server for people running their own AgentSearch-compatible backend. It exposes web search, page extract, and JavaScript page rendering (headless browser) to Cursor, Claude Desktop, and other MCP hosts over stdio.

AGENTSEARCH_BASE_URL is required and points at that API. There is no built-in default host.

For pay-per-call access with no backend of your own, use Pocket's official MCP server instead:

bash
npx -y @pocket-network/agentic-portal-mcp

That server calls agentsearch-web-search-v1 and agentsearch-web-extract-v1 at $0.005/call over x402. Details: https://agentsearchhq.com/?utm_source=github&utm_medium=readme&utm_campaign=mcp

This package calls your API directly:

  • Search: POST {AGENTSEARCH_BASE_URL}/v1/search with body { "query": "...", "max_results": 5 }
  • Extract: POST {AGENTSEARCH_BASE_URL}/v1/extract
  • Render: POST {AGENTSEARCH_BASE_URL}/v1/render (headless Chromium; OpenAPI spec)

Tools

ToolArgsDescription
agentsearch_web_searchquery (string, required), max_results (number, optional, default 5, clamped 1–5)Web search. Returns pretty-printed JSON. Use for a query; use extract when you already have a URL. Read-only HTTP.
agentsearch_extracturl (absolute URL, required), formats (string[], optional), max_chars (positive integer, optional)Page extract via POST /v1/extract. Use when you already have a URL. Read-only HTTP.
agentsearch_renderurl (absolute http(s) URL, required); optional: formats (markdown|text|html|links, default ["markdown"]), max_chars (1–100000), screenshot, screenshot_format (png|jpeg), full_page, viewport ({width 320–1920, height 240–1600}), wait_until (domcontentloaded|load|networkidle), wait_for_selector, wait_ms (0–1500), block (image|media|font|stylesheet)Renders a JavaScript-heavy page in headless Chromium via POST /v1/render and returns title, status, meta, and the rendered markdown/text/HTML/links (plus optional base64 screenshot). Use when extract returns empty/partial content for an SPA; prefer extract for static pages. Read-only HTTP.

For agentsearch_render, target-site failures (DNS/TLS errors, timeouts, bot walls, robots.txt) come back as a normal result whose JSON has a non-null error object (code, message, retryable); bad input (400), oversize body (413), rate limits (429) and backend faults (500) are MCP errors. The backend enforces a ~4.2 s render deadline.

Requirements

  • Node.js 20+
  • Your own AgentSearch-compatible API. Set AGENTSEARCH_BASE_URL to its base URL. The process exits at startup if that variable is missing.

Install

bash
npx -y @agentsearchhq/agentsearch-mcp# or install into a projectnpm i @agentsearchhq/agentsearch-mcp

From a local checkout:

bash
cd agentsearch-mcpnpm installnpm run build

Scripts: build → tsc, start → node dist/index.js, test → build + node --test test/*.mjs, prepare → runs build.

Binary: agentsearch-mcp → dist/index.js

Environment variables

VariableRequiredNotes
AGENTSEARCH_BASE_URLyesBase URL of your API (no trailing slash). No default.
AGENTSEARCH_API_KEYnoOptional Authorization: Bearer …. On 401 the client retries once without the key.

See .env.example. Never commit a real .env.

Cursor

Project (.cursor/mcp.json) or user (~/.cursor/mcp.json / Cursor Settings → MCP):

json
{  "mcpServers": {    "agentsearch": {      "command": "npx",      "args": ["-y", "@agentsearchhq/agentsearch-mcp"],      "env": {        "AGENTSEARCH_BASE_URL": "https://your-agentsearch-host.example"      }    }  }}

Optional API key:

json
"env": {  "AGENTSEARCH_BASE_URL": "https://your-agentsearch-host.example",  "AGENTSEARCH_API_KEY": "your-key-here"}

Claude Desktop

Edit Claude Desktop config (claude_desktop_config.json):

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
json
{  "mcpServers": {    "agentsearch": {      "command": "npx",      "args": ["-y", "@agentsearchhq/agentsearch-mcp"],      "env": {        "AGENTSEARCH_BASE_URL": "https://your-agentsearch-host.example"      }    }  }}

Restart Claude Desktop after saving.

Local run

bash
npm run buildAGENTSEARCH_BASE_URL=https://your-agentsearch-host.example node dist/index.js# process waits on stdin — Ctrl+C to stop

If AGENTSEARCH_BASE_URL is unset, the process prints an error and exits.

License

MIT

Source: README.md at commit 9654fc0

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.1.1LatestOct 3, 2026