Koskamo

X1-BaaS MCP

An MCP server for the X1-BaaS API that enables AI agents to perform stealth browser automation, including scraping URLs into clean Markdown, extracting structured data via JSON schema or CSS selectors, crawling multi-page sites, and generating screenshots or PDFs. It supports x402 micropayments for access.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

X1-BaaS MCP logo, by TazpalVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Tazpal
You need:no account or API key needed — pay per request with USDC on Base + SolanaBearer token (request one at api@tazpal.com)
MCP endpoint (Streamable HTTP)
https://api.tazpal.com/mcp
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (3)

3 of 3 have a description · 3 of 3 declare behavior hints · 0 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to tazpal.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Scrape any URL into clean Markdown
  • Extract structured data using JSON schemas
  • Crawl multi-page sites via sitemap or patterns
  • Generate screenshots or PDFs of web pages

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.tazpal/x1-baas@1.0.0

Protocol and capabilities

Server
X1-BaaS 0.3.2
MCP protocol negotiated in check
2025-11-25
Tools
3 advertised
Resources
2 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Use the `scrape` tool to fetch and extract web content as clean Markdown. The engine handles JavaScript rendering, anti-bot bypass, and DOM cleaning automatically. The `scrape` tool is paid. If the request carries no API key (`Authorization: Bearer baas_live_*`) or x402 payment proof, the engine returns a 402 with x402 payment requirements (Base USDC and/or Solana), which are relayed to you so you can pay and retry. Use `get_pricing` to check current pricing before scraping. Use `server_status` to check engine health and availability.

Tools

3 advertised

scrape
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Scrape a URL and return content in your preferred format. Supported output formats: - markdown (default): Clean LLM-ready Markdown text - screenshot: PNG/JPEG image of the page - pdf: PDF document of the page - csv: Table data extracted as CSV - html: Sanitized HTML with scripts/ads removed This tool handles: - JavaScript rendering (SPA, dynamic content) - Anti-bot bypass (Cloudflare Turnstile, Datadome) - DOM cleaning (strips scripts, nav, footer, ads) - HTML-to-Markdown conversion (Mozilla Readability engine) - Automatic retry with escalating wait strategies - Domain cooldown to avoid rate-limiting - Response caching (5 min TTL) Args: url: The URL to scrape (must start with http:// or https://) output: Output format: "markdown" (default), "screenshot", "pdf", "csv", "html" wait_for_selector: Optional CSS selector to wait for before extraction (e.g., ".article-content") timeout_ms: Navigation timeout in milliseconds (default: 20000, max: 120000) block_media: Block images/fonts/video for faster loading (default: true) wait_strategy: Wait strategy: "default", "spa", "heavy", "cloudflare" (auto-detected if omitted) retry: Enable automatic retry on failure (default: true) bypass_cache: Skip cache, force fresh scrape (default: false) javascript: Custom JavaScript to execute after page load (e.g., "window.scrollTo(0, 1000)") Returns: Content in the requested format, or an error message.

scrape input schema
{
  "type": "object",
  "title": "scrapeArguments",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "title": "Url"
    },
    "retry": {
      "type": "boolean",
      "title": "Retry",
      "default": true
    },
    "output": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Output",
      "default": null
    },
    "javascript": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Javascript",
      "default": null
    },
    "timeout_ms": {
      "type": "integer",
      "title": "Timeout Ms",
      "default": 20000
    },
    "block_media": {
      "type": "boolean",
      "title": "Block Media",
      "default": true
    },
    "bypass_cache": {
      "type": "boolean",
      "title": "Bypass Cache",
      "default": false
    },
    "wait_strategy": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Wait Strategy",
      "default": null
    },
    "wait_for_selector": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Wait For Selector",
      "default": null
    }
  }
}
scrape output schema
{
  "type": "object",
  "title": "scrapeOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
scrape annotations
{
  "title": "Scrape Web Page",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
get_pricing
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check current pricing and payment requirements for the BaaS scrape engine. Returns pricing info, supported networks, and payment instructions. No authentication required. Returns: Current pricing details and payment instructions.

get_pricing input schema
{
  "type": "object",
  "title": "get_pricingArguments",
  "properties": {}
}
get_pricing output schema
{
  "type": "object",
  "title": "get_pricingOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
get_pricing annotations
{
  "title": "Get Pricing",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
server_status
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check the BaaS engine health and operational status. Returns browser status, uptime, x402 payment mode, and context count. Returns: Server health and diagnostic information.

server_status input schema
{
  "type": "object",
  "title": "server_statusArguments",
  "properties": {}
}
server_status output schema
{
  "type": "object",
  "title": "server_statusOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
server_status annotations
{
  "title": "Server Status",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

2 advertised

pricing_resource

Advertised by the server during the last successful anonymous check.

Current BaaS pricing and payment configuration.

pricing_resource URI
baas://pricing

MIME type: text/plain

status_resource

Advertised by the server during the last successful anonymous check.

Current BaaS engine status and diagnostics.

status_resource URI
baas://status

MIME type: text/plain

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
2514 ms
95th percentile latency
2514 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 2514 ms · metadata changed · 3 tool(s), 2 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http x1-baas-mcp https://api.tazpal.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add x1-baas-mcp --url https://api.tazpal.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable x1-baas-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "x1-baas-mcp": {
      "url": "https://api.tazpal.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "x1-baas-mcp": {
      "type": "streamableHttp",
      "url": "https://api.tazpal.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start x1-baas-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "x1-baas-mcp": {
      "type": "http",
      "url": "https://api.tazpal.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http x1-baas-mcp https://api.tazpal.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.tazpal.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "x1-baas-mcp": {
      "serverUrl": "https://api.tazpal.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like X1-BaaS MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,317

Do you run X1-BaaS MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing