Skip to content
Fetchgate logo

Fetchgate MCP server

Which servers in the official MCP registry are Fetchgate's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to Fetchgate

Whose server it is
  • Registry namedev.fetchgate/fetchgateverified in the MCP registry

The registry name sits under fetchgate.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools10
  • Server calls itselffetchgate
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 33 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: screen web pages for prompt injection before an agent acts on them; check whether an x402 paid endpoint works before paying it; screen a token contract for risky owner or mint controls.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "screen web pages for prompt injection before an agent acts on them", the likely first call is scan_for_prompt_injection.
  • For "check whether an x402 paid endpoint works before paying it", the likely first call is check_x402_endpoint.
  • For "screen a token contract for risky owner or mint controls", the likely first call is check_base_token.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer211 ms
  • Space in an agent's context≈ 2,012 tokensthe definitions of all its tools (10), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 10 of 10

What an agent can do with it

  • can do · screen web pages for prompt injection before an agent acts on them
  • can do · check whether an x402 paid endpoint works before paying it
  • can do · screen a token contract for risky owner or mint controls

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers10 tools · read 2026-10-26
  • read_url

    Fetch a URL server-side and return its main content as clean Markdown, with scripts/styles/nav/ads/boilerplate stripped out. Wraps GET /v1/read. Free tier: 30 calls/day per caller; priced at $0.002/call via x402 once that's exhausted (see…

  • get_metadata

    Fetch a URL server-side and return structured metadata: title, description, canonical URL, OpenGraph/Twitter card fields, favicon URL, language, and published/modified timestamps when present. Wraps GET /v1/meta. Same free tier as…

  • list_products

    List Fetchgate's digital-goods catalog: id, name, description, priceUsd, currency, file format, size, sha256, and a walletless humanUrl checkout link for each product for sale. Wraps GET /v1/products. Free, no rate limit, no payment…

  • get_purchase_info

    Look up a product by id (from list_products) and explain exactly how to buy it: its price, and the x402 purchase flow step by step (the 402 challenge shape, the PAYMENT-SIGNATURE header, and the signed download URL you get back on…

  • get_agent_census

    Return the Agent Web Crawler Census: every named bot observed crawling a live, publicly-listed x402 + MCP endpoint over a 24-hour window, each with a case-insensitive regex `matcher` and a behavioural `category` (liveness-monitor…

  • scan_for_prompt_injection

    Check untrusted content BEFORE acting on it. Give a `url` to fetch and scan a web page (its visible text and, separately, text hidden in HTML comments, alt/title/aria attributes and meta tags), or give `text` to scan a tool result…

  • search_x402_services

    Search for a pay-per-call (x402) API that does what you need. Unlike a raw directory, results are limited to endpoints that answered a real x402 payment challenge AND had at least 5 settled calls from at least 2 distinct payers in the…

  • check_x402_endpoint

    Decide whether an unfamiliar pay-per-call (x402) endpoint is worth paying. Sends one unpaid GET to read its live payment challenge (format, price, network, signing domain), then adds its settled-call and unique-payer history, whether its…

  • check_base_token

    Screen a token contract on Base before an agent buys it. Reads the contract (ERC-20 metadata, owner, upgradeable proxy, and mint / pause / blacklist / fee selectors in its bytecode) and its DEX liquidity (WETH and USDC held by its Uniswap…

  • scan_mcp_server

    Connect to a remote Streamable HTTP MCP server, fetch its tools/list (sends only initialize, notifications/initialized and tools/list — never tools/call) and scan every tool name, description, parameter description and the server's…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "fetchgate": {
      "type": "http",
      "url": "https://fetchgate.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http fetchgate https://fetchgate.dev/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://fetchgate.dev/mcp as a custom connector in the settings.

OpenAPI spec

19 paths, read 2026-10-26. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.