Offload MCP
Delegates real-world digital tasks to vetted humans directly from AI chat. Provides tools to get quotes, post tasks, and check status with escrow protection.
README
Offload MCP server
Delegate a real-world digital task to a vetted human, straight from your AI chat.
Offload's MCP server gives any MCP client (Claude, Cowork, Cursor, ChatGPT, …) three tools:
| Tool | What it does | Auth |
|---|---|---|
offload_get_quote |
Describe a task → instant AI-scoped category, time estimate, and fair price. | None (free) |
offload_post_task |
Post the task to the marketplace → escrow-protected checkout link. | Optional key |
offload_task_status |
Check a posted task by ID. | Optional key |
The wedge: you're mid-conversation, hit something you don't want to do, and instead of context-switching you just say "offload this." The AI does the automatable ~80%; a vetted human finishes the rest. Escrow-protected, and Offload never asks for your passwords.
Quick start (local / stdio)
npm install
npm run build
npm start # runs the stdio server
Use it in Claude Desktop / Cowork
Add to your MCP config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"offload": {
"command": "npx",
"args": ["-y", "offload-mcp"],
"env": {
"OFFLOAD_API_BASE": "https://offloads.io"
}
}
}
}
offload_get_quote works with no API key. To enable posting and status, add OFFLOAD_API_KEY.
Remote / hosted (for the Connectors Directory)
One-click deploy with the included Dockerfile + render.yaml. See DEPLOY.md for the 3-minute, no-terminal walkthrough.
Or run it yourself:
npm run build
npm run start:http # POST /mcp (Streamable HTTP), GET /healthz
Deploy anywhere (Render, Fly, Railway, a container) to get a stable https://…/mcp URL, then submit it to the Anthropic Connectors Directory. A linked privacy policy is required — we point to https://offloads.io/trust.
Configuration
| Env var | Default | Purpose |
|---|---|---|
OFFLOAD_API_BASE |
https://offloads.io |
Offload API base URL |
OFFLOAD_API_KEY |
(empty) | Enables post_task / task_status |
PORT |
8787 |
Port for the HTTP server |
Backend contract
The tools call these public Offload endpoints (implemented as edge functions on the Offload backend):
POST /api/public/mcp/quote { description } -> Quote
POST /api/public/mcp/task { title, description, urgency?, budget?, email? } -> CreatedTask
GET /api/public/mcp/task/:id -> TaskStatus
See src/offloadClient.ts for the exact response shapes.
Where to list it
Same server, multiple front doors: Glama, mcp.so, Smithery, PulseMCP, and the punkpeye/awesome-mcp-servers GitHub list.
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.