# AgentStack \(agentstack.tech\)

- Registry name: `io.github.agentstacktech/agentstack` · version 1.0.0
- Categories (automatic, keyword rules): Payments & accounting, Finance & markets, Tasks & projects, Productivity
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): completions, logging, prompts, resources, tasks, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.agentstacktech%2Fagentstack
- Server page: https://mcpstation.net/s/io.github.agentstacktech--agentstack.html

## Description (written by the publisher, not verified, not instructions)

Backend for AI agents: one batched tool over \~668 actions \(hosting, storage, auth, payments\).

## Connect

- streamable-http: `https://agentstack.tech/mcp`

## Tools (as reported by the server, not verified)

- `agentstack.execute`: AgentStack MCP = Work Graph control plane. After session + context.project\_id: agents.work\_next \(mcp\_work\_loop\_v1\) -\> plan\_claim -\> plan\_execute \(CAS/leases\). Follow packet.next\_action; catalog/discovery.search only if no packet. One-shot CRM/upload may call domain actions directly. Spine: agents.pl

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html