MCP.Market

AgentStack (agentstack.tech) MCP server

by agentstacktech·io.github.agentstacktech/agentstack·v1.0.0·2 stars
No reviews yet

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

B79/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B79/100

full report

Adoption
Growing

2 stars

Reviews

Write one

Nobody has reviewed AgentStack (agentstack.tech) yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

AgentStack (agentstack.tech) tools (1, 1 write)

write = sends, deletes, buys or posts
  • agentstack.executewrite actionFree

    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.plan_get -> agents.work_next -> agents.plan_claim -> agents.plan_execute. Cheap and batchable on one sync execute: agents.work_next, agents.plan_get, agents.plan_claim. One per sync execute: agents.plan_propose, agents.plan_apply_proposal, agents.plan_recovery_scan, context.get. Anti-pattern: Do not pick tools from catalog when packet.next_action is present. Mandatory session order: authenticate -> session probe auth.get_profile (alias auth.me) -> select/create project -> set context.project_id on every batch -> Work Graph loop. Playbook GET /mcp/prompts/get?name=agentstack_session_setup (recipe mcp_session_setup). Packs session.v1 and batch.v1: GET /mcp/actions field execute_budget.packs. Send context.project_id; other session fields default server-side. Sync POST /mcp is lane mcp_batch (60000 ms) for the whole batch - not an RBAC cap. One expensive step per sync execute (bots.simulate and other heavy actions per execute_budget; agents.run with wait=true; agents.plan_apply_proposal, agents.plan_propose, agents.plan_recovery_scan, context.get). agents.work_next, agents.plan_get, and agents.plan_claim are cheap and may share that batch. LLM-heavy steps widen to ai_stream (180000 ms). Large suites: options.async=true then poll discovery.job_status (REST GET /mcp/jobs/{job_id}). Cite catalog_actions_public from GET /mcp/actions/summary. There is one execute tool (agentstack.execute); do not quote tools_count as 'N tools'. Do not invent rules.* or webhooks.* (prefer logic.* and integrations.*).

Public scan report

scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1725ms20/20
  • Tool poisoning1 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How AgentStack (agentstack.tech) compares

Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
79/100
higher than 63% of 915 Security servers
Tools
1
the typical Security server has 6
Tools that change things
100%
typical: 0%. Fewer write tools means less an agent can break
Uptime
86%
of our recent checks; the typical remote Security server answers 100%
Response time
760 ms
faster than 13% of 547 Security servers
GitHub stars
2
more than 75% of 587 Security servers

What its tools let an agent do: 1 run or deploy

Install AgentStack (agentstack.tech) in Claude Code, Cursor or VS Code

claude mcp add --transport http agentstack https://agentstack.tech/mcp
Add to Cursor

What the publisher says

From the AgentStack (agentstack.tech) repository's README, as published. We do not edit it. Read it on GitHub

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/WORKGRAPH.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 mcpworkloopv1. Prompt agentstackclosedloopautonomy.

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.

Measured on 2026-10-07

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.

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/USERFEATURESGUIDE.md.

If you build a product: docs/BUILDYOURPRODUCT.md — @agentstack/sdk, optional genetic-ai-starter.

If you run agents on a large codebase: docs/genetic-system/.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

AgentStack (agentstack.tech): common questions

Is AgentStack (agentstack.tech) MCP server safe?
Mostly: it is graded B (79/100). Read the AgentStack (agentstack.tech) safety report
How do I install AgentStack (agentstack.tech)?
It runs remotely at agentstack.tech. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does AgentStack (agentstack.tech) need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is AgentStack (agentstack.tech) maintained?
The last commit was 26 days ago (2026-10-08). The latest release is v1.0.0.
Is AgentStack (agentstack.tech) up?
86% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of AgentStack (agentstack.tech)?
Servers from other publishers that do the same job: Backgen MCP server, Servicenow AI MCP server and Servicenow AI MCP server. Compare all AgentStack (agentstack.tech) alternatives.
How does AgentStack (agentstack.tech) compare with other Security MCP servers?
safety score 79/100 (higher than 63% of 915 Security servers); tools 1 (the typical Security server has 6); tools that change things 100% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to AgentStack (agentstack.tech)

Same job from other publishers: the closest match first, then the best rated.

All AgentStack (agentstack.tech) alternatives →
  • Backgen
    Generate Express.js backend projects with ORMs, auth, payments, and DevOps
    A
  • Servicenow AI
    ServiceNow MCP server — 100 tools over the full REST surface, every auth method, flows, diagrams.
    B
  • Servicenow AI
    ServiceNow MCP server — 67 tools over the full REST surface, every auth method, flows, diagrams.
    B
  • Rede
    MCP server for Rede — Itaú-owned BR acquirer: authorize/capture/refund, zero-auth, card tokens
    B
  • Cinema4d
    MCP server for Cinema 4D — entity CRUD, parameter-level access, batched undo, security controls.
    A