Skip to main content
Glama

Tollkit MCP server

Pay-per-call tools for AI agents, as one remote MCP server:

https://api.tollkit.dev/mcp

No account and no API key. Each paid tool costs a fixed amount of USDC, paid per call with x402 on Base or Solana. A call that fails is never charged.

Listed in the official MCP Registry as io.github.UltraStarz/x402-extract.

Connect

Add the URL above as a remote (Streamable HTTP) MCP server in Claude, Cursor or any MCP client. In clients that take a JSON config:

{
  "mcpServers": {
    "tollkit": { "url": "https://api.tollkit.dev/mcp" }
  }
}

Paying: MCP has no 402 status, so a paid tool called without its payment argument returns the price quote as its result. Sign that quote with your x402 wallet and call the tool again with payment set. Two tools are free: try_it_free (a real sample result) and get_service_info.

Related MCP server: x402-farm

Tools

Group

Tools

Price per call

Web pages & documents

read a page in a real browser, screenshot, summarize, page brief, PDF to text, web search + read top pages

$0.002 – $0.015

Public data

SEC filings, financials, company snapshot and due diligence; US weather (by address or point); FAA airport delays; US address geocoding; exchange rates; IP lookup

$0.002 – $0.03

On-chain (Base, Ethereum, Solana)

wallet balance and portfolio, token info, token price, token safety check, transaction lookup, pre-trade check

$0.002 – $0.01

x402 market data

best x402 tools for a task, seller lookup, full market dataset

$0.01 – $0.10

Product data

price, stock, brand, SKU and images from a store page; compare up to 5

$0.01 – $0.04

Proof

signed, timestamped record of what a page said

$0.25

Live prices: /health · every tool with its URL and body: llms.txt · tollkit.dev/tools

Without MCP

Every tool is also a plain HTTP endpoint: POST the JSON body, get HTTP 402 with the price, pay with any x402 client (for example @x402/fetch), repeat the request. OpenAPI per hostname, e.g. https://data.tollkit.dev/openapi.json.

This repo

server.json is the MCP Registry entry. src/ holds an older stdio client (the x402-extract-mcp npm package) that only wraps product extraction and is no longer maintained; use the remote server above instead.

More

MIT licensed.

Available Tools

1 tool
extract_productAInspect

Extract structured Product schema from any product page URL. Renders the page through a headless browser, then returns name, description, brand, price, currency, availability, and variants. Costs $0.01 USDC per call (paid automatically from the configured wallet on Base Sepolia). Use this whenever the user gives you a product URL and wants the structured fields, or when you need clean product data for shopping comparisons, price tracking, or catalog ingestion.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesAbsolute https:// URL of the product page to extract.

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description carries full burden and excels: discloses headless browser rendering, cost of $0.01 per call, automatic payment from configured wallet on Base Sepolia. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each earning its place: purpose, mechanism, cost/payment, usage guidance. No redundancy, front-loaded with main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, description lists returned fields, explains mechanism and cost, and provides usage guidance. For a simple tool with one parameter, it is fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds value by specifying URL must be absolute https:// and from a product page, and mentions headless rendering, which goes beyond schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool extracts a structured Product schema from a product page URL, listing specific fields returned. It uses a specific verb and resource, and despite no sibling tools, it defines its scope well.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use cases: when user gives a product URL or needs product data for comparisons, tracking, or catalog ingestion. Lacks explicit when-not-to-use or alternatives, but given no siblings, this is nearly complete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.2
    • First observedextract_product

TDQS

A4.3/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly defined.

Naming Consistency5/5

With a single tool, naming is consistent by default. The name 'extract_product' follows a clear verb_noun pattern.

Tool Count2/5

A single tool for extracting product data is very thin. While the tool is focused, the server would benefit from additional tools for related operations (e.g., listing recent extractions, managing config). Count feels too low for a robust toolset.

Completeness2/5

The tool only handles extraction from a product page URL. Missing any complementary operations like validation, history, batch processing, or error handling. The surface is incomplete for a full workflow.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    MCP server providing 10 pay-per-call APIs for web scraping, DNS, email validation, and French business data, with autonomous micropayments via the x402 protocol (USDC on Base).
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server that enables AI agents to fetch web content as clean, structured Markdown via NanoParse's hosted API, using x402 micropayments in USDC on Base.
    1
    22 npm
    MIT