Skip to content

io.github.IsaiahDupree/agentsearch-mcp

by IsaiahDupree · remote · no sign-in to list tools · v1.0.0 · published by GitHub user IsaiahDupree

LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

Changes · 1

3 tools: 1 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agentsearch https://agentsearch-mcp.vercel.app/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 1Claude Code: ask
  • instant_answerDuckDuckGo Instant Answer API — definitions, entities, and quick facts.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    DuckDuckGo Instant Answer API — definitions, entities, and quick facts. Returns a normalized answer with heading, type (abstract/answer/disambiguation), source, sourceUrl, optional image/definition, and relatedTopics, plus a meta envelope. Not a full web SERP; use web_search for that. Works with no API key.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Claude Code: allow
  • fetch_urlFetches any public http(s) URL, strips boilerplate (scripts, nav, footer, ads), and returns clean text or markdown ready for an LLM context window.No findings

    Why it is in this group

    • The name "fetch_url" says "fetch": a word for reading.
    Description, as the server wrote it
    Fetches any public http(s) URL, strips boilerplate (scripts, nav, footer, ads), and returns clean text or markdown ready for an LLM context window. SSRF-guarded — refuses private/loopback/internal hosts. Returns url, title, format, length, content (and finalUrl when redirected, plus up to 50 extracted links when links=true), with a meta envelope. Works with no API key.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentsearch https://agentsearch-mcp.vercel.app/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agentsearch__web_search",
      "mcp__agentsearch__fetch_url"
    ],
    "ask": [
      "mcp__agentsearch__instant_answer"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agentsearch. Review it before you use it.