English Français العربية

AgentStack (agentstack.tech)

Registre officiel Cloud et DevOps

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

Code source Site web Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http agentstack-agentstack-tech 'https://agentstack.tech/mcp'
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "agentstack-agentstack-tech": {
            "type": "http",
            "url": "https://agentstack.tech/mcp"
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. AgentStack
  2. The loop
  3. Measured on 2026-10-07
  4. Docs
  5. Open source kit
  6. Plugins
  7. Product

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.

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

The loop

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.

WhoWithout the loopWith Work Graph
Founder with open loopsEvery new chat re-reads the tool menuThe outcome is written once. The next chat takes the head of the queue
A person with more tasks than hoursThe agent invents a tool and spends the window choosingThe list says ready, blocked, or idle
A business that needs the work finishedThrash between catalog, guess, and retryClaim, execute, verify, on the same project as the site and the payments
Someone wiring an agentPaste the catalog into the promptagents.work_next, then packet.next_action

Measured on 2026-10-07

Local registry build. Not a production traffic sample. Not a provider tokenizer. Bytes ÷ 4 is an English size estimate.

PayloadUTF-8 bytesRough tokens
Example next_action plus two alternatives250~63
discovery.search, first 20 compact rows8,889~2,222
Handshake contract JSON, once11,297~2,824
Compact search, 50 rows (HTTP max)20,852~5,213
Full registry catalog JSON (795 actions in that build)1,680,071~420,018

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.

SignalTarget
Autonomous loops that follow packet.next_action≥ 90%
Catalog shopping while a packet is already present≤ 5%

Those are steady-production goals, not a live counter. Method and scenarios: docs/plugins/WORK_GRAPH.md.

Docs

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

Open source kit

RepoBranchNotes
genetic-ai-startermainMap-first install: npx @agentstack/genetic-ai-starter init. SoT lives in this repo under genetic-ai-starter/ when you have the monorepo.

Plugins

PluginNotes
cursor-pluginv0.4.18, gen3 — rules, skills, commands, agents, hooks; Plugin MCP Connect and OAuth 2.1 device code
claude-pluginClaude Desktop / API installers
gpt-pluginChatGPT / OpenAI ecosystem
vscode-pluginVS Code marketplace distribution

Product

Questions fréquentes

Qu'est-ce que AgentStack (agentstack.tech) ?

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

Comment installer AgentStack (agentstack.tech) ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http agentstack-agentstack-tech 'https://agentstack.tech/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour AgentStack (agentstack.tech) ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

AgentStack (agentstack.tech) est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient AgentStack (agentstack.tech) ?

Il est publié par agentstacktech. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.