Fetchgate

Fetchgate

A web-content API and a storefront, both built so an unattended agent can use them end to end.

Fetch any URL server-side as clean Markdown or structured metadata — no scripts, nav chrome, ads, or boilerplate. Buy digital goods from the same API. Every endpoint is one HTTP call: a free tier for trying it, an API key for sustained use, or pay-per-call with x402 (HTTP 402 + USDC, no signup, no human in the loop). An MCP server is available for agent frameworks that prefer tools over raw HTTP.

See the reader API Browse the store

Reader endpoints

Fetch a page, get back clean content. These exist to be cheap and reliable enough that any agent tries them and comes back.

$0.002 / call after free tier

GET /v1/read?url=<url>

Fetches the URL server-side and converts the main content to Markdown. Add &format=text for raw Markdown instead of JSON.

curl "https://fetchgate.dev/v1/read?url=https://example.com/some-article"
{
  "url": "https://example.com/some-article",
  "title": "Some Article Title",
  "markdown": "# Some Article Title\n\nClean article body as markdown...",
  "fetchedAt": "2026-08-22T12:00:00Z"
}
$0.001 / call after free tier

GET /v1/meta?url=<url>

Fetches the URL and returns structured metadata: title, description, canonical URL, OpenGraph/Twitter fields, favicon, language, published/modified times.

curl "https://fetchgate.dev/v1/meta?url=https://example.com/some-article"
{
  "url": "https://example.com/some-article",
  "title": "Some Article Title",
  "description": "Meta description or OG description.",
  "openGraph": { "type": "article", "site_name": "Example" },
  "canonical": "https://example.com/some-article",
  "fetchedAt": "2026-08-22T12:00:00Z"
}
TierLimitHow
Free30 requests/day per IPNo auth, just call it
API keyPlan-basedAuthorization: Bearer <key>
x402 pay-per-callUnlimitedNo auth; retry a 402 with a signed X-PAYMENT header

Store

A small, growing catalog of digital goods for agents and the people who build them. GET /v1/products is always the live, authoritative list — prices below are a snapshot. Payments are in beta: x402 settlement runs through a third-party facilitator on Base; digital delivery only, and we monitor every settlement.

$15.00

x402 Services & Facilitator Registry

A curated, machine-readable snapshot of 21 x402 facilitators and 118 x402-payable services/APIs: chains, stablecoins, fee models, per-call pricing, live status, and source URLs — so an agent or builder doesn't have to crawl and reconcile multiple directories itself.

curl "https://fetchgate.dev/v1/buy/x402-registry-2026-08-21"

No payment attached → 402 with x402 payment terms. Retry with a signed X-PAYMENT header to get a signed download URL. No wallet yet? A walletless checkout link is on the way — check humanUrl on /v1/products.

$29.00

Prompt-Injection & Tool-Hijack Test Corpus

156 structured, labeled adversarial test cases across seven categories (direct/indirect injection, tool hijacking, data exfiltration, system-prompt leaks, jailbreak/roleplay, encoding obfuscation) for evaluating whether an agent resists prompt injection and tool-misuse attacks. Ships with a JSON Schema and a Python eval harness.

curl "https://fetchgate.dev/v1/buy/prompt-injection-test-corpus"

Same x402 flow as above. Digital delivery only — see /llms.txt for refund policy.

$19.00

MCP Server Registry Snapshot

A curated, machine-readable snapshot of 277 production/community Model Context Protocol servers: category, transport, auth needs, repo/package URLs, and source-directory cross-references — reconciled across the official registry, Smithery, Glama, PulseMCP, and mcp.so so you don't have to crawl them yourself.

curl "https://fetchgate.dev/v1/buy/mcp-registry-2026-08-22"

Same x402 flow. Dated edition.

$39.00

Agent Eval Harness Templates

A ready-to-use kit for evaluating an agent or LLM app fast: a JSON-Schema test-case format, 40 example cases across four suites (task completion, tool selection, refusal/safety, regression), an LLM-as-judge scorer with documented bias mitigations, and a dependency-light Python CLI runner. Bring-your-own-model via a one-file adapter.

curl "https://fetchgate.dev/v1/buy/agent-eval-harness-templates"

Same x402 flow. Digital delivery only.

What is x402?

The mechanism that lets an autonomous agent pay for a reader call or a product, with nobody in the loop.

x402 reuses the long-dormant HTTP 402 Payment Required status code for machine-to-machine micropayments. Call a priced endpoint with no valid API key or payment, and instead of the data you get back a 402 describing exactly what to pay: amount (in USDC), network, and recipient address.

  1. Call the endpoint normally. No payment on file → 402 Payment Required, body includes an accepts[] array with the price and payment terms.
  2. Your agent's wallet signs a USDC payment authorization for that exact amount.
  3. Retry the same request with the signed payment, base64-encoded, in an X-PAYMENT header.
  4. Payment verifies and settles → you get the real response (markdown, metadata, or a signed download URL) plus an X-PAYMENT-RESPONSE header confirming settlement.

No account, no OAuth, no stored card — just a wallet and a USDC balance. The reader endpoints and the store both use this exact same flow.

MCP server

For agent frameworks that call tools instead of raw HTTP.

POST /mcp is a Streamable HTTP Model Context Protocol server (JSON-RPC 2.0: initialize, tools/list, tools/call) exposing four tools — read_url, get_metadata, list_products, and get_purchase_info — backed by the exact same logic and free-tier limits as the HTTP endpoints above. See /llms.txt for the full reference, or /.well-known/mcp/server.json for the registry manifest.