AI MCP Workflows with TweekIT

Use TweekIT’s hosted MCP server to normalize any incoming file into AI‑ready formats inside your agents and automations. This prevents pipeline failures and removes manual pre‑processing.

Hosted endpoint: https://mcp.tweekit.io/mcp/

What's new in v1.5

• convert_url lets agents pull remote files over HTTP(S) without hand-encoding base64, including optional headers for authenticated sources.
• Automatic extension detection and richer error payloads (with TweekIT debug headers) make MCP troubleshooting quicker.
• The new config://tweekit-mcp-version resource exposes the deployed server build alongside the upstream API version.
• Ready-made JSON snippets now cover Cursor and Continue IDEs so teams can wire up the hosted server in minutes.

Common Workflows

• Image‑to‑Image: Convert any file (incl. first page of PDFs, PSD/AI, RAW) to PNG/JPG for model inputs.
• OCR Pipelines: Convert documents to high‑contrast PNGs for better text recognition.
• Office → PDF: Normalize Word/PowerPoint/Visio and legacy docs into standard PDFs for LLM ingestion.
• Pro Formats: Safely render Illustrator/complex PDFs into images when direct ingestion fails.
• Remote Assets: Use convert_url to fetch supplier PDFs or images directly from their source URLs before your agent processes them.

Quickstarts

Claude Desktop

{
  "mcpServers": {
    "tweekit": {
      "transport": { "type": "http", "url": "https://mcp.tweekit.io/mcp/" }
    }
  }
}

Call convert with base64 content (shortened):

{
  "name": "convert",
  "arguments": {
    "apiKey": "YOUR_KEY",
    "apiSecret": "YOUR_SECRET",
    "inext": "png",
    "outfmt": "webp",
    "blob": "<base64>",
    "width": 300,
    "height": 300
  }
}

ChatGPT MCP

{ "name": "search", "arguments": { "query": "tweekit", "max_results": 3 } }
{ "name": "fetch",  "arguments": { "url": "https://tweekit.io" } }

Cursor IDE

{
  "mcpServers": {
    "tweekit": {
      "type": "http",
      "url": "https://mcp.tweekit.io/mcp/",
      "headers": {
        "ApiKey": "${TWEEKIT_API_KEY}",
        "ApiSecret": "${TWEEKIT_API_SECRET}"
      }
    }
  }
}

1. Export TWEEKIT_API_KEY and TWEEKIT_API_SECRET (or replace the placeholders with literal values).
2. Restart Cursor and run “List tools” to confirm version, doctype, convert, and convert_url.
3. Optional: host the JSON internally and share an “Add to Cursor” link with your team.

Continue IDE

{
  "mcpServers": {
    "tweekit": {
      "type": "streamable-http",
      "url": "https://mcp.tweekit.io/mcp/",
      "headers": {
        "ApiKey": "${TWEEKIT_API_KEY}",
        "ApiSecret": "${TWEEKIT_API_SECRET}"
      }
    }
  }
}

1. Reload Continue so it picks up the new entry.
2. Invoke tools from the Continue panel—doctype, convert, and convert_url share the arguments shown above.
3. Document how your workspace manages secrets so teammates can connect quickly.

OpenAI TypeScript (MCP SDK)

import { Client } from "@modelcontextprotocol/sdk/client";
import { HttpClientTransport } from "@modelcontextprotocol/sdk/client/transport/http";

const transport = new HttpClientTransport(new URL("https://mcp.tweekit.io/mcp/"));
const client = new Client({ name: "tweekit-example", version: "1.0.0" }, { capabilities: {} }, transport);
await client.connect();
const tools = await client.listTools();
const res = await client.callTool({ name: "search", arguments: { query: "tweekit", max_results: 3 } });
// Need remote ingestion? call convert_url with { url, outfmt, fetchHeaders }.
console.log(res);

Python Quick Call

import asyncio
from fastmcp import Client

async def main():
    async with Client("https://mcp.tweekit.io/mcp/") as c:
        print(await c.list_tools())
        out = await c.call_tool("fetch", {"url": "https://tweekit.io"})
        print(out)

asyncio.run(main())

Need to bypass local uploads? convert_url pulls remote files straight into the pipeline:

{
  "method": "tools/call",
  "params": {
    "name": "convert_url",
    "arguments": {
      "apiKey": "{Your TweekIT API key}",
      "apiSecret": "{Your TweekIT API secret}",
      "url": "https://example.com/assets/catalog.pdf",
      "outfmt": "png",
      "width": 1200,
      "fetchHeaders": {
        "Authorization": "Bearer ${ACCESS_TOKEN}"
      }
    }
  },
  "jsonrpc": "2.0",
  "id": 7
}

Next Steps

• Read the full server guide: MCP Server
• Browse all docs: Documentation