AgentStack
After one bind, the agent does not shop the catalog. Work Graph hands it the next step. Live edits stay on the safe circle: write a copy, pass the checks, then publish.
接入你的智能体
發布者自己的 URL。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
https://agentstack.tech/mcp上方的 Claude 按鈕會開啟 Claude,並填好名稱和 URL。你仍需在那裡確認。
claude mcp add --transport http io.github.agentstacktech-agentstack https://agentstack.tech/mcpRun in a terminal.
{ "mcpServers": { "io.github.agentstacktech-agentstack": { "command": "npx", "args": [ "-y", "mcp-remote", "https://agentstack.tech/mcp" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
One MCP tool, agentstack.execute. The server holds the plan. Each turn is one action. Idle is a valid answer. Blocked names the unblock.
Story: agentstack.tech/work-graph · Contract: docs/plugins/WORK_GRAPH.md · Safe circle: agentstack.tech/mcp-docs#safe-cycle
session → context.project_id → agents.work_next → packet.next_action → claim / execute → work_next
Recipe mcp_work_loop_v1. Prompt agentstack_closed_loop_autonomy.
flowchart LR
S[Session] --> B[Bind project]
B --> W[work_next]
W --> N[next_action]
N --> X[Claim and execute]
X --> W
When that step changes live data, the same project runs the safe circle:
connect → sandbox → review → promote
The agent writes a generation. Customers stay on the previous copy until the checks pass. The project’s own rule publishes it: at once, or in stages.
Local registry build. Not a production traffic sample. Not a provider tokenizer. Bytes ÷ 4 is an English size estimate.
The full catalog is 6,720× that example packet. A 20-row search page is 35.6× it. The public catalog you should quote is 714 actions — live GET /mcp/actions/summary. Do not add the byte ratio and the operator targets into one savings claim.
Those are steady-production goals, not a live counter. Method and scenarios: docs/plugins/WORK_GRAPH.md.
This repository is the public documentation (English, user- and integrator-facing): web product, MCP, plugins, REST, RAG, sandboxes, and examples.
If you use the website: docs/USER_FEATURES_GUIDE.md.
If you build a product: docs/BUILD_YOUR_PRODUCT.md — @agentstack/sdk, optional genetic-ai-starter.
If you run agents on a large codebase: docs/genetic-system/.
If you integrate: docs/MCP_AND_ECOSYSTEM.md — start with the loop, then the catalog (714 actions · docs/MCP_SCALE.md).
REST / OpenAPI: docs/OPENAPI.md — Swagger · openapi.json.
npm SDK: @agentstack/sdk · docs/sdk/
Full index: docs/README.md · What's new: docs/WHATS_NEW.md
Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).
{ "mcpServers": { "io.github.agentstacktech-agentstack": { "url": "https://agentstack.tech/mcp", "headers": {} } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 http 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
AgentStack (agentstack.tech) 透過 HTTP 存取。
上次檢查時間:2026-11-09。 Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).