Sprawl
About
Stand up an operation from Cursor/Claude Code: a fleet of agents, each on its own model and connected account, running on a schedule after your session ends. MCP: https://sprawl.to/api/mcp
Details
- Author
- Unknown
- Categories
- Productivity, AI, Automation
Jump to
Your agent already writes code and runs on a schedule. What it can't do is keep a fleet running onyouraccounts after the session ends. Point it at Sprawl over MCP and it designs the operation; Sprawl runs it — each agent on its own model, on its own connected account, on its own schedule.
- Design an operation — survey the user's repos and stack, then propose a complete blueprint: agents, their skills, their schedules and the accounts each one needs. Nothing is created until a human approves it.
- Pick a model per agent — a cheap one for the hourly sweep, a stronger one for the weekly analysis, inside a single operation. Independent of whichever model is doing the designing.
- Give each agent its own account — Sprawl holds multiple accounts per provider, scoped per operation: a work Gmail on one, a personal one on another; two X handles; two Slack workspaces.
- Stand it up, then check on it — provision the whole fleet atomically, and read back what ran and what it cost without leaving your editor.
The server is an HTTP MCP endpoint that speaks JSON-RPC 2.0 over POST:
Authenticate with a bearer API key. Create one (free read-only keys are available) in account settings once you'vecreated a free account, then pass it asAuthorization: Bearer sprawl_sk_…
List the available tools to confirm your key works:
curl -s https://sprawl.to/api/mcp \ -H "Authorization: Bearer sprawl_sk_..." \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Most MCP clients accept an HTTP server config like this:
{ "mcpServers": { "sprawl": { "type": "http", "url": "https://sprawl.to/api/mcp", "headers": { "Authorization": "Bearer sprawl_sk_..." } } } }
A machine-readable descriptor (tools, auth, and pricing) is served without auth at/.well-known/mcp/server-card.json.
There is no subscription. Every account starts with $3 of usage, each run draws its own price from that balance, and you add more whenever you want — from $5, never expiring.
When an agent runs low,sprawl_get_usagereturns the remaining balance in dollars, what has been spent this month, and the billing page to add more. Adding balance is the account owner's action — an agent can surface the link, and cannot charge a card.
Sprawl also exposes Agentic Commerce Protocol checkout endpoints (the open standard by OpenAI & Stripe) for adding balance, so an agent can run a standards-based checkout itself.
- Public product feed:GET /api/acp/feed
- Create, re-price, retrieve, or cancel a session:/api/acp/checkout_sessions(bearersprawl_sk_auth)
Payment completion via Shared Payment Token is not yet enabled. Until it is, a session can be created and priced but not paid — the account owner adds balance from the billing page above.
Create a free account, generate a key in settings, and point your agent at Sprawl in minutes.
Create notes, search, & think with your Fabric AI workspace
Magica is your all-in-one AI platform, offering 2500+ cutting-edge tools under a single subscription.
Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.
Dynamically search and call tools using UnifAI Network
A dynamic server for managing multi-agent collaboration within tmux sessions, featuring flexible pane configurations and auto-detection.
A Model Context Protocol (MCP) server that provides access to 100+ curated AI agent skills from the VoltAgent Awesome Agent Skills collection.
Adds auto-approve functionality for MCP requests to the Claude Desktop application.
An MCP server to execute Coze workflows locally via a Python script.
MCP skill that automatically reduces Manus AI credit consumption by 30-75% through intelligent model routing, smart testing, and context hygiene
An MCP server for advanced cognitive analysis, creative problem-solving, and structured thinking using the UCPF framework.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
