AgentStack (agentstack.tech)
Server Details
Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- agentstacktech/AgentStack
- GitHub Stars
- 1
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
There is only one tool, so there is no cross-tool ambiguity, but the single tool is a catch-all whose description packs auth, planning, work-graph, discovery, and prompt operations into one opaque 'execute' verb. An agent cannot tell what the tool actually does or when to call it versus the many sub-operations (auth.get_profile, plan_get, plan_claim, work_next, discovery.search) that are named only inside the description.
A single namespaced name (agentstack.execute) is trivially consistent, and the namespace prefix is reasonable. However, 'execute' is a vague umbrella verb that hides the many distinct actions the tool performs, so there is no predictable verb_noun pattern to learn.
One tool is far too few for a platform that evidently spans authentication, projects, planning, work graph, discovery, and prompt management. The single mega-tool collapses an entire API surface into one call, making scoping and error recovery difficult.
The description alludes to many operations (auth choices, plan lifecycle, work_next, packet.next_action, session_setup) but exposes none of them as discrete, discoverable tools. Agents have no concrete surface for CRUD or lifecycle coverage and must rely on inferred internal routing.
Available Tools
1 toolagentstack.executeAgentStack executeCInspect
AUTH-FIRST: auth.get_profile before mutate. IDE: Connect MCP; no auth.login in chat. Unauth: auth_choices; skip discovery/work_next. Anon: create_project_anonymous; bind context.project_id. Spine: plan_get->work_next->plan_claim->plan_execute. Work Graph: work_next -> plan_claim -> plan_execute; packet.next_action first (discovery.search if empty). Prompts: session_setup, execute_budget.
Inputs: steps (required), context, options. Returns: result.v1 batch envelope.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
The agent-native cloud: database, functions, AI, storage, computers. 51 tools, one API key.
Backend for AI-built apps: database, auth, files, email, AI, payments, deploy, realtime. 170+ tools.
Managed database, auth, file storage, email, analytics, and deployment for coding agents.
Production backend for AI-built apps: storage, data, jobs, webhooks, email, metering and billing.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceEnables AI agents to run 700+ backend actions across data, auth and RBAC, payments and wallets, CRM, hosting, RAG, bots, scheduling, and automation through a single execute tool, remotely or via a stdio bridge.1MIT
@manybases/mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to create and run a backend with database, auth, file storage, server-side functions, and a site, all without opening a browser.22 npmMIT
Init MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables coding agents to turn plain-English descriptions into live, typed, versioned HTTPS backend endpoints with auth and secrets handled, then call them — with each endpoint able to combine LLM reasoning, web search, scraping, media and voice generation, email, databases, storage and scheduled jobs. Also lets agents create and edit projects, list and inspect generated resources and runtime packages, and apply local manifest files.334 npmMIT- AlicenseNot gradedqualityDmaintenanceTurns coding agents into full-stack builders by enabling backend features like auth, databases, file storage, serverless functions, and LLMs to be added to apps in seconds.12 npmApache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.