Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

AgentSearch (agentsearchhq.com)

by agentsearchhq-coderversion 1.8.1i★ 0iRuns on your computer
Registry nameio.github.agentsearchhq-coder/agentsearch-mcp

How to install

What it does

Free web search + extract/render trial (no key), then pay per call via x402 on Base.

  • Connects Runs on your computer
  • Account or key Needs AGENTSEARCH_WALLET_PRIVATE_KEY
  • Category Search & AI memory

Install

Pick the AI app you use, then copy the settings.

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a AgentSearch (agentsearchhq.com) key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the AgentSearch (agentsearchhq.com) site ↗

  3. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  4. Paste these settings and save the file

    {
      "mcpServers": {
        "agentsearch": {
          "command": "npx",
          "args": [
            "-y",
            "@agentsearchhq/agentsearch-mcp"
          ],
          "env": {
            "AGENTSEARCH_WALLET_PRIVATE_KEY": "your-value"
          }
        }
      }
    }

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Quit Claude and open it again

  6. Try it

    Use AgentSearch (agentsearchhq.com) and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using AgentSearch (agentsearchhq.com) or shows a AgentSearch (agentsearchhq.com) tool in the answer, you are connected

10 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSEARCH_MODE Search mode: free (default; free relay even with a wallet key), paid (pay per search, $0.008 direct or $0.005 via Pocket; needs a key) or auto (paid search when a key is set) · default free
  • AGENTSEARCH_FREE_TRIAL Set to 0 to turn off the no-wallet extract/render free trial (then no-wallet extract/render make no network call). Default on · default 1
  • AGENTSEARCH_PAYMENT_ROUTE Paid route: direct (default since 1.6.0; AgentSearch's own x402 API on Base, search $0.008, extract $0.004, render $0.010, search_and_read $0.009) or pocket (Pocket Network Agentic Portal, $0.005 per… · default direct
  • AGENTSEARCH_X402_DIRECT Legacy 1.5.0 switch: 0 selects the Pocket route (same as AGENTSEARCH_PAYMENT_ROUTE=pocket). Direct is already the default since 1.6.0
  • AGENTSEARCH_MAX_TOTAL_ATOMIC Session spend cap in USDC atomic units (default 1000000 = $1.00). Alias: POCKET_MAX_TOTAL_ATOMIC · default 1000000
  • AGENTSEARCH_MAX_PER_CALL_ATOMIC Optional lower per-call cap in USDC atomic units (hard max 20000 = $0.020 on the default direct route, 5000 = $0.005 on the Pocket route)
  • AGENTSEARCH_BASE_URL Optional self-hosted AgentSearch API base URL; when set, search/extract/render use it with no payment
  • AGENTSEARCH_API_KEY Optional Bearer token for your AgentSearch API
  • AGENTSEARCH_REVIEWS_URL Optional Review Board URL (default https://reviews.agentsearchhq.com)
  • AGENTSEARCH_REVIEW_KEY Optional Review Board key for weighted reviews

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect AgentSearch (agentsearchhq.com) yet

AgentSearch (agentsearchhq.com) runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect AgentSearch (agentsearchhq.com)

  • You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time)
  • You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time)
  • You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time)

B · Others in Search & AI memory that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time)

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a AgentSearch (agentsearchhq.com) key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the AgentSearch (agentsearchhq.com) site ↗

  3. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  4. Paste this command and press Enter

    claude mcp add --scope user agentsearch --env AGENTSEARCH_WALLET_PRIVATE_KEY=your-value -- npx -y @agentsearchhq/agentsearch-mcp

    Replace “your-value” with your key before pressing Enter

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Type /mcp in Claude Code

    You should see AgentSearch (agentsearchhq.com) listed as connected

  6. Try it

    Use AgentSearch (agentsearchhq.com) and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using AgentSearch (agentsearchhq.com) or shows a AgentSearch (agentsearchhq.com) tool in the answer, you are connected

10 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSEARCH_MODE Search mode: free (default; free relay even with a wallet key), paid (pay per search, $0.008 direct or $0.005 via Pocket; needs a key) or auto (paid search when a key is set) · default free
  • AGENTSEARCH_FREE_TRIAL Set to 0 to turn off the no-wallet extract/render free trial (then no-wallet extract/render make no network call). Default on · default 1
  • AGENTSEARCH_PAYMENT_ROUTE Paid route: direct (default since 1.6.0; AgentSearch's own x402 API on Base, search $0.008, extract $0.004, render $0.010, search_and_read $0.009) or pocket (Pocket Network Agentic Portal, $0.005 per… · default direct
  • AGENTSEARCH_X402_DIRECT Legacy 1.5.0 switch: 0 selects the Pocket route (same as AGENTSEARCH_PAYMENT_ROUTE=pocket). Direct is already the default since 1.6.0
  • AGENTSEARCH_MAX_TOTAL_ATOMIC Session spend cap in USDC atomic units (default 1000000 = $1.00). Alias: POCKET_MAX_TOTAL_ATOMIC · default 1000000
  • AGENTSEARCH_MAX_PER_CALL_ATOMIC Optional lower per-call cap in USDC atomic units (hard max 20000 = $0.020 on the default direct route, 5000 = $0.005 on the Pocket route)
  • AGENTSEARCH_BASE_URL Optional self-hosted AgentSearch API base URL; when set, search/extract/render use it with no payment
  • AGENTSEARCH_API_KEY Optional Bearer token for your AgentSearch API
  • AGENTSEARCH_REVIEWS_URL Optional Review Board URL (default https://reviews.agentsearchhq.com)
  • AGENTSEARCH_REVIEW_KEY Optional Review Board key for weighted reviews

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time)

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a AgentSearch (agentsearchhq.com) key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the AgentSearch (agentsearchhq.com) site ↗

  3. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  4. Fill in your key

    In the AgentSearch (agentsearchhq.com) settings, AGENTSEARCH_WALLET_PRIVATE_KEY is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Open the AI chat in Cursor in Agent mode

  6. Try it

    Use AgentSearch (agentsearchhq.com) and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using AgentSearch (agentsearchhq.com) or shows a AgentSearch (agentsearchhq.com) tool in the answer, you are connected

10 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSEARCH_MODE Search mode: free (default; free relay even with a wallet key), paid (pay per search, $0.008 direct or $0.005 via Pocket; needs a key) or auto (paid search when a key is set) · default free
  • AGENTSEARCH_FREE_TRIAL Set to 0 to turn off the no-wallet extract/render free trial (then no-wallet extract/render make no network call). Default on · default 1
  • AGENTSEARCH_PAYMENT_ROUTE Paid route: direct (default since 1.6.0; AgentSearch's own x402 API on Base, search $0.008, extract $0.004, render $0.010, search_and_read $0.009) or pocket (Pocket Network Agentic Portal, $0.005 per… · default direct
  • AGENTSEARCH_X402_DIRECT Legacy 1.5.0 switch: 0 selects the Pocket route (same as AGENTSEARCH_PAYMENT_ROUTE=pocket). Direct is already the default since 1.6.0
  • AGENTSEARCH_MAX_TOTAL_ATOMIC Session spend cap in USDC atomic units (default 1000000 = $1.00). Alias: POCKET_MAX_TOTAL_ATOMIC · default 1000000
  • AGENTSEARCH_MAX_PER_CALL_ATOMIC Optional lower per-call cap in USDC atomic units (hard max 20000 = $0.020 on the default direct route, 5000 = $0.005 on the Pocket route)
  • AGENTSEARCH_BASE_URL Optional self-hosted AgentSearch API base URL; when set, search/extract/render use it with no payment
  • AGENTSEARCH_API_KEY Optional Bearer token for your AgentSearch API
  • AGENTSEARCH_REVIEWS_URL Optional Review Board URL (default https://reviews.agentsearchhq.com)
  • AGENTSEARCH_REVIEW_KEY Optional Review Board key for weighted reviews

Descriptions are as written by the maker.

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

You need a AgentSearch (agentsearchhq.com) key (create it on the maker’s site) · Install Node.js on your computer first (one time)

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a AgentSearch (agentsearchhq.com) key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the AgentSearch (agentsearchhq.com) site ↗

  3. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  4. Fill in your key

    In the AgentSearch (agentsearchhq.com) settings, AGENTSEARCH_WALLET_PRIVATE_KEY is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Open the AI chat in VS Code in Agent mode

  6. Try it

    Use AgentSearch (agentsearchhq.com) and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using AgentSearch (agentsearchhq.com) or shows a AgentSearch (agentsearchhq.com) tool in the answer, you are connected

10 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSEARCH_MODE Search mode: free (default; free relay even with a wallet key), paid (pay per search, $0.008 direct or $0.005 via Pocket; needs a key) or auto (paid search when a key is set) · default free
  • AGENTSEARCH_FREE_TRIAL Set to 0 to turn off the no-wallet extract/render free trial (then no-wallet extract/render make no network call). Default on · default 1
  • AGENTSEARCH_PAYMENT_ROUTE Paid route: direct (default since 1.6.0; AgentSearch's own x402 API on Base, search $0.008, extract $0.004, render $0.010, search_and_read $0.009) or pocket (Pocket Network Agentic Portal, $0.005 per… · default direct
  • AGENTSEARCH_X402_DIRECT Legacy 1.5.0 switch: 0 selects the Pocket route (same as AGENTSEARCH_PAYMENT_ROUTE=pocket). Direct is already the default since 1.6.0
  • AGENTSEARCH_MAX_TOTAL_ATOMIC Session spend cap in USDC atomic units (default 1000000 = $1.00). Alias: POCKET_MAX_TOTAL_ATOMIC · default 1000000
  • AGENTSEARCH_MAX_PER_CALL_ATOMIC Optional lower per-call cap in USDC atomic units (hard max 20000 = $0.020 on the default direct route, 5000 = $0.005 on the Pocket route)
  • AGENTSEARCH_BASE_URL Optional self-hosted AgentSearch API base URL; when set, search/extract/render use it with no payment
  • AGENTSEARCH_API_KEY Optional Bearer token for your AgentSearch API
  • AGENTSEARCH_REVIEWS_URL Optional Review Board URL (default https://reviews.agentsearchhq.com)
  • AGENTSEARCH_REVIEW_KEY Optional Review Board key for weighted reviews

Descriptions are as written by the maker.

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use AgentSearch (agentsearchhq.com)💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user agentsearch --env AGENTSEARCH_WALLET_PRIVATE_KEY=your-value -- npx -y @agentsearchhq/agentsearch-mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agentsearch": {
      "command": "npx",
      "args": [
        "-y",
        "@agentsearchhq/agentsearch-mcp"
      ],
      "env": {
        "AGENTSEARCH_WALLET_PRIVATE_KEY": "your-value"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "agentsearch": {
      "command": "npx",
      "args": [
        "-y",
        "@agentsearchhq/agentsearch-mcp"
      ],
      "env": {
        "AGENTSEARCH_WALLET_PRIVATE_KEY": "your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "agentsearch": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@agentsearchhq/agentsearch-mcp"
      ],
      "env": {
        "AGENTSEARCH_WALLET_PRIVATE_KEY": "your-value"
      }
    }
  }
}

Values you fill in

  • AGENTSEARCH_WALLET_PRIVATE_KEY secret required env
    Private key of a dedicated wallet with a little USDC on Base; enables paid extract/render via x402, paid to AgentSearch's own API by default (extract $0.004, render $0.010, search_and_read $0.009). W…
  • AGENTSEARCH_MODE env
    Search mode: free (default; free relay even with a wallet key), paid (pay per search, $0.008 direct or $0.005 via Pocket; needs a key) or auto (paid search when a key is set)
  • AGENTSEARCH_FREE_TRIAL env
    Set to 0 to turn off the no-wallet extract/render free trial (then no-wallet extract/render make no network call). Default on
  • AGENTSEARCH_PAYMENT_ROUTE env
    Paid route: direct (default since 1.6.0; AgentSearch's own x402 API on Base, search $0.008, extract $0.004, render $0.010, search_and_read $0.009) or pocket (Pocket Network Agentic Portal, $0.005 per…
  • AGENTSEARCH_X402_DIRECT env
    Legacy 1.5.0 switch: 0 selects the Pocket route (same as AGENTSEARCH_PAYMENT_ROUTE=pocket). Direct is already the default since 1.6.0
  • AGENTSEARCH_MAX_TOTAL_ATOMIC env
    Session spend cap in USDC atomic units (default 1000000 = $1.00). Alias: POCKET_MAX_TOTAL_ATOMIC
  • AGENTSEARCH_MAX_PER_CALL_ATOMIC env
    Optional lower per-call cap in USDC atomic units (hard max 20000 = $0.020 on the default direct route, 5000 = $0.005 on the Pocket route)
  • AGENTSEARCH_BASE_URL env
    Optional self-hosted AgentSearch API base URL; when set, search/extract/render use it with no payment
  • AGENTSEARCH_API_KEY secret env
    Optional Bearer token for your AgentSearch API
  • AGENTSEARCH_REVIEWS_URL env
    Optional Review Board URL (default https://reviews.agentsearchhq.com)
  • AGENTSEARCH_REVIEW_KEY secret env
    Optional Review Board key for weighted reviews

Descriptions are as written by the maker.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
196/wk
Connection
Runs on your computer
Latest versioni
1.8.1
Published to registryi
Nov 14, 2026
Code last changedi
Nov 12, 2026
Maker
agentsearchhq-coder
Packages
npm: @agentsearchhq/agentsearch-mcp
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 14, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account agentsearchhq-coder, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 2 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in with Google to post

User reviews

No reviews yet

Sign in with Google to write a review

Compared with others in Search & AI memoryi

  • More stars than 0% of the other 6120 servers in this category
  • Published to the registry more recently than 98% of the other 6120 servers in this category
  • Basic checks equal to or better than 100% of the other 6120 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is AgentSearch (agentsearchhq.com) safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: AGENTSEARCH_WALLET_PRIVATE_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 2 days ago, and the latest version (1.8.1) reached the registry today.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Context7, Codebase Memory, OpenSEO

Others in the same category

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Context7

Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.

by upstashWidely used↓ 1.2M/wk★ 64.8KUpdated 2 days ago

Computer or cloud

Codebase Memory

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

by DeusDataWidely used↓ 16.8K/wk★ 48.6KUpdated 28 days ago

Runs on your computer

OpenSEO

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

by every-appWidely used★ 27.6KUpdated today

Runs in the cloud✓ everyapp.com

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

agentsearch-mcp

MCP (Model Context Protocol) server from AgentSearch for Cursor, Claude Desktop, and other MCP hosts over stdio. It has two groups of tools:

  • Free web search with no setup: with no configuration, agentsearch_web_search uses the AgentSearch free tier (https://relay.agentsearchhq.com/v1/search): up to 25 searches/day per IP, subject to shared daily capacity, no key or wallet. When the daily limit is hit (HTTP 429), the tool explains how to upgrade to paid.
  • Extract and render free trial, no wallet (new in 1.4.0): with no wallet key, agentsearch_extract (5 calls/day per IP) and agentsearch_render (3 calls/day per IP, text output, no screenshots) use the AgentSearch free trial on the same relay. Past it they return HTTP 429 with wallet setup steps. Set AGENTSEARCH_FREE_TRIAL=0 to turn the trial off.
  • Extract and render, pay per call (search too, if you opt in): agentsearch_extract and agentsearch_render. Add a wallet key and these pay AgentSearch's own x402 API on Base (https://api.agentsearchhq.com) in USDC: extract $0.004, render $0.010 per call, charged only when a usable answer comes back. A wallet key alone does not make search paid: set AGENTSEARCH_MODE=paid to also pay $0.008 per search call. No account, no API key, no ETH for gas. The Pocket Network Agentic Portal route ($0.005 per call) is still available with AGENTSEARCH_PAYMENT_ROUTE=pocket for search, extract and render. Or set AGENTSEARCH_BASE_URL to use your own self-hosted AgentSearch-compatible API with no payment.
  • Search + Read, one paid call (new in 1.7.0): agentsearch_search_and_read searches the live web and returns the top pages as markdown for $0.009, versus $0.020 as one search plus three extracts, and one payment instead of four. Charged only when at least one page has text. Direct-only (not on Pocket or the free relay). Needs a wallet key. Docs: Search + Read.
  • News search and page screenshots, pay per call (new in 1.8.0): agentsearch_news_search returns recent articles with publish dates for $0.008, and agentsearch_screenshot returns a PNG/JPEG of any public page as an MCP image for $0.010 (viewport or full page, mobile sizes supported). Paid web search, news and Search + Read also take filters: freshness (day/week/month/year) or date_from/date_to, country, language, include_domains, exclude_domains. Extract takes include_links: false to save tokens. Direct-only; needs a wallet key.
  • AgentSearch Review Board (works out of the box, free): agentsearch_review_lookup checks which Pocket Network, x402 and remote MCP services work right now for a task before you pick one; agentsearch_review_submit posts a short structured review after you use one. No configuration or key needed; the board is at https://reviews.agentsearchhq.com.
npx -y @agentsearchhq/agentsearch-mcp   # free search + review tools work immediately

Search, then read the page. For hits and their text in one payment, use agentsearch_search_and_read ($0.009). Or the two-step loop: free agentsearch_web_search → agentsearch_extract on the 1–2 best URLs (clean markdown, $0.004 each; $1 covers about 250 calls) → agentsearch_render only for pages extract couldn't read (JavaScript apps). Guides: Claude Code research workflow, n8n AI agent reading pages, LangChain (Python) search-then-read.

Modes
Configagentsearch_web_searchagentsearch_extract / agentsearch_render
Nothing set (default)Free tier, up to 25 searches/day per IP, subject to shared daily capacityFree trial: 5 extract / 3 render calls per day per IP, then a 429 with wallet setup steps
AGENTSEARCH_FREE_TRIAL=0 (no wallet)Free tierReturn a message with how to add a wallet; no network call
AGENTSEARCH_WALLET_PRIVATE_KEYStill free (free tier, up to 25 searches/day per IP)Paid via AgentSearch's x402 API (extract $0.004, render $0.010)
AGENTSEARCH_WALLET_PRIVATE_KEY + AGENTSEARCH_MODE=paidPaid, $0.008 per call via AgentSearch's x402 APIPaid via AgentSearch's x402 API
...plus AGENTSEARCH_PAYMENT_ROUTE=pocketPaid search goes through the Pocket portal ($0.005)Paid via the Pocket portal ($0.005)
AGENTSEARCH_BASE_URL (takes precedence)Your self-hosted APIYour self-hosted API

To use paid Extract/Render, set AGENTSEARCH_WALLET_PRIVATE_KEY (a new wallet with a little USDC on Base) in this server's env and restart your client.

How the paid mode works (default: AgentSearch's direct x402 API, since 1.6.0)
ToolEndpointPrice (USDC on Base)
agentsearch_extractPOST https://api.agentsearchhq.com/x402/v1/extract$0.004
agentsearch_search_and_readPOST https://api.agentsearchhq.com/x402/v1/search_and_read$0.009
agentsearch_renderPOST https://api.agentsearchhq.com/x402/v1/render$0.010
agentsearch_news_searchPOST https://api.agentsearchhq.com/x402/v1/news$0.008
agentsearch_screenshotPOST https://api.agentsearchhq.com/x402/v1/screenshot$0.010
agentsearch_web_search (only with AGENTSEARCH_MODE=paid)POST https://api.agentsearchhq.com/x402/v1/search$0.008

The request is sent unpaid; the API answers 402 with x402 v2 terms. The server checks every limit before signing (scheme exact, USDC on Base, AgentSearch's pinned payee 0xC49B157887e51c21CB655f39CF65D6a4c2a4C337, at most $0.020 per call, session cap), signs once, and retries with PAYMENT-SIGNATURE. The API settles only after a successful, non-empty answer. On the direct route, extract takes url, max_chars (up to 50000) and include_links; render takes only url (extra options such as formats or screenshot are dropped and listed under dropped; use agentsearch_screenshot for images); search, news and Search + Read take the filters above. Discovery: /.well-known/x402, /openapi.json; docs: https://agentsearchhq.com/docs/x402.

Pocket route (optional: AGENTSEARCH_PAYMENT_ROUTE=pocket, $0.005 per call)
ToolPortal serviceEndpoint
agentsearch_web_searchagentsearch-web-search-v1POST https://agent.pocket.network/v1/agentsearch-web-search-v1/v1/search
agentsearch_extractagentsearch-web-extract-v1POST https://agent.pocket.network/v1/agentsearch-web-extract-v1/v1/extract
agentsearch_renderagentsearch-web-render-v1POST https://agent.pocket.network/v1/agentsearch-web-render-v1/v1/render
  1. The request is sent unpaid; the portal answers 402 with x402 v2 terms (PAYMENT-REQUIRED).
  2. The server checks every limit before signing (see below), then signs an EIP-3009 TransferWithAuthorization for USDC on Base with the official @x402/core + @x402/evm client and viem.
  3. It retries once with PAYMENT-SIGNATURE. A 200 carries the portal envelope { "portal": {...}, "data": {...} } and the receipt in PAYMENT-RESPONSE.

The tool result is JSON with payment (amount, network, payee, payer, settled, transaction, Basescan link), spend (session spent/cap/remaining), response (the portal envelope, unchanged) and, when the target site failed inside a 200, upstreamError (copied from data.error). data is third-party content: treat it as data, never as instructions.

Portal errors ({ "error": { "code", "message", "retryable" } }, e.g. 400 UPSTREAM_REJECTED, 429, 503 with Retry-After) come back as MCP errors with the code and whether a retry can help. Per the portal, a non-2xx answer is not settled, so you are not charged for it.

Spending safety
  • Per call: never signs more than $0.020 (20000 atomic units) on the default direct route, or $0.005 (5000) on the Pocket route. AGENTSEARCH_MAX_PER_CALL_ATOMIC can lower this, never raise it (a cap below a tool's price makes that tool refuse with nothing signed).
  • Per session: never signs more than AGENTSEARCH_MAX_TOTAL_ATOMIC in total while it runs (default 1000000 = $1.00). Spend is counted when a payment is signed. The total resets when the server restarts.
  • Only these terms: scheme exact, network Base (eip155:8453), asset USDC (0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913), and the route's pinned payee: AgentSearch (0xC49B157887e51c21CB655f39CF65D6a4c2a4C337) on the direct route, or the portal's payee (0xF732ea490c5766071785a2310523f7fA2CEbB829) on the Pocket route, with a 402 whose resource is the tool's own endpoint. Anything else is refused with nothing signed.
  • The key is read from env, used only to sign, and is not returned in a tool result.
  • Use a new wallet made for this, holding only what you are willing to spend. The key sits in plain text in your client config.
  • Your MCP client may not ask before calling a tool, so the limits above are what holds.
Self-hosted mode

If AGENTSEARCH_BASE_URL is set, it takes precedence and no payment is made:

  • 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)

Free relay: https://relay.agentsearchhq.com serves free search plus the small extract/render free trial. It is used automatically when nothing is configured; you do not need to set it as AGENTSEARCH_BASE_URL. For more than the trial, use paid mode (AGENTSEARCH_WALLET_PRIVATE_KEY) or self-host.


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 (markdown\text, optional), max_chars (1–100000, optional)Page extract (title, markdown/text, links, meta) via POST /v1/extract. Use when you already have a URL. Read-only HTTP.

| agentsearch_render | url (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 HT

Only the beginning is shown; read the rest in the repo