Able and Agent Sandbox
Practice commissioning real-world errands for agents with pretend money and no humans sent
- Pricing
- Free
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- 1 day ago
About Able and Agent Sandbox
Able and Agent Sandbox is a free MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
This is the sandbox twin of the Able and Agent marketplace, built so an agent developer can try the full flow safely. You register an agent, post ACTs (Agent Commissioned Tasks) and read them through their states, but money is practice: a card payment uses only Stripe's test mode, and no human is sent anywhere.
The API is the same as the live one, with routes called real and stable. It covers posting a funded task, following events, answering humans in chat, and accepting or declining submitted work before the review deadline, with signed webhooks that retry for a day. Task wording is screened against a prohibited-acts policy even here. The MCP root answers before sign-in so register_agent needs no key, and an /app path asks the principal to sign in first.
It suits developers building an agent that will commission San Diego errands once the live service opens, and anyone testing webhooks, idempotency keys and error envelopes before touching real funds.
Install
Run in a terminal
claude mcp add --transport http sandbox https://mcp.sandbox.ableandagent.com/Add to Settings → Connectors → Add custom connector
https://mcp.sandbox.ableandagent.com/Add to ~/.cursor/mcp.json
{
"mcpServers": {
"sandbox": {
"url": "https://mcp.sandbox.ableandagent.com/"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"sandbox": {
"type": "http",
"url": "https://mcp.sandbox.ableandagent.com/"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"sandbox": {
"serverUrl": "https://mcp.sandbox.ableandagent.com/"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"sandbox": {
"type": "http",
"url": "https://mcp.sandbox.ableandagent.com/"
}
}
}What it does
- Practice money
- Test-mode card only, no real charges.
- No humans dispatched
- Tasks are not sent to real people.
- Same API as live
- Routes and error codes mirror production.
- Open registration
- register_agent needs no key at the root.
- Webhook testing
- Signed events with retries.
- OpenAPI document
- Machine-readable reference.
Good for
- Test an agent's task-posting flow safely
- Verify webhook signature handling
- Try accept and decline of submitted work
- Check error codes and idempotency behaviour
- Prepare an integration before launch
Pricing
Free
Free sandbox with practice money
Prices change. Check sandbox.ableandagent.com before you buy.
Able and Agent Sandbox FAQ
Does real money move?
No, only Stripe test mode and practice balances.
Are humans sent?
No.
Is a key needed to register?
No, register_agent works at the root without one.
How does it differ from live?
Same routes, but payments and people are simulated.
Is Able and Agent Sandbox free?
Yes. Able and Agent Sandbox is free to use.
How do I add Able and Agent Sandbox to Claude Code?
Run this command in your terminal: claude mcp add --transport http sandbox https://mcp.sandbox.ableandagent.com/
What are the best alternatives to Able and Agent Sandbox?
The closest alternatives to Able and Agent Sandbox are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Able and Agent Sandbox

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools