Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "agentstack": {
      "type": "http",
      "url": "https://agentstack.tech/mcp"
    }
  }
}

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

[mcp_servers.agentstack]
url = "https://agentstack.tech/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentstack": {
      "type": "remote",
      "url": "https://agentstack.tech/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "agentstack": {
      "type": "http",
      "url": "https://agentstack.tech/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=agentstack&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnRzdGFjay50ZWNoL21jcCJ9"
}

{
  "servers": {
    "agentstack": {
      "type": "http",
      "url": "https://agentstack.tech/mcp"
    }
  }
}

{
  "mcpServers": {
    "agentstack": {
      "httpUrl": "https://agentstack.tech/mcp"
    }
  }
}

extensions:
  "agentstack":
    enabled: true
    name: "agentstack"
    type: streamable_http
    uri: "https://agentstack.tech/mcp"
    timeout: 300

Quality 84 / 100good

protocol100 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
pass
protocol.list_ttltool list is cacheable (ttlMs 3600000)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations1 of 1 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 615 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability25 · weight 15

warn
stability.changes23 tool changes in 30 days
fail
stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

1 tools, about 615 tokens to load them all · tool set 93e9a2314699 · tools last changed 2026-10-18 · checked 2026-10-19 10:20 UTC

Tool changes

2026-10-18agentstack.executechangeddescription, input schema
before
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. Context.project_id on every batch. Detail: prompts/get agentstack_session_setup and agentstack_execute_budget.
after · 96% of words in common
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. context.project_id on every batch. Prompts: agentstack_session_setup, agentstack_execute_budget.
2026-10-17agentstack.executechangedinput schema
2026-10-16agentstack.executechangeddescription, input schema, output schemameaning changed
before
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 batch: work_next, plan_get, plan_claim. One/sync: plan_propose, plan_apply_proposal, plan_recovery_scan, context.get. Skip catalog when packet.next_action is set. Session: auth.get_profile -> project -> context.project_id on every batch. Setup GET /mcp/prompts/get?name=agentstack_session_setup. Packs: GET /mcp/actions execute_budget.packs (session.v1, batch.v1). Sync mcp_batch 60000ms whole batch; one heavy step per execute (agents.run wait=true; agents.plan_apply_proposal, agents.plan_propose, agents.plan_recovery_scan, context.get). LLM lane ai_stream 180000ms. async=true then discovery.job_status (GET /mcp/jobs/{job_id}). Single tool agentstack.execute; catalog_actions_public from /mcp/actions/summary. Prefer logic.* and integrations.*; not rules.*; not webhooks.*. Do not pick tools from catalog when packet.next_action is present.
after · 49% of words in common
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. Context.project_id on every batch. Detail: prompts/get agentstack_session_setup and agentstack_execute_budget.
2026-10-16agentstack.executechangedinput schema
2026-10-15agentstack.executechangedtitle, description, input schema, annotations
before
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.*).
after · 62% of words in common
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 batch: work_next, plan_get, plan_claim. One/sync: plan_propose, plan_apply_proposal, plan_recovery_scan, context.get. Skip catalog when packet.next_action is set. Session: auth.get_profile -> project -> context.project_id on every batch. Setup GET /mcp/prompts/get?name=agentstack_session_setup. Packs: GET /mcp/actions execute_budget.packs (session.v1, batch.v1). Sync mcp_batch 60000ms whole batch; one heavy step per execute (agents.run wait=true; agents.plan_apply_proposal, agents.plan_propose, agents.plan_recovery_scan, context.get). LLM lane ai_stream 180000ms. async=true then discovery.job_status (GET /mcp/jobs/{job_id}). Single tool agentstack.execute; catalog_actions_public from /mcp/actions/summary. Prefer logic.* and integrations.*; not rules.*; not webhooks.*. Do not pick tools from catalog when packet.next_action is present.
2026-10-14agentstack.executechangedoutput schema
2026-10-14agentstack.executechangedoutput schema
2026-10-14agentstack.executechangedinput schema, output schema
2026-10-13agentstack.executeadded
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.*).
2026-10-13agentstack.executeremoved
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.*).

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 96 / 100

provenance90

liveness98

freshness100

hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-96% +updated-13d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://agentstack.tech/mcp` streamable-http	none	yes	96%	828 ms	2026-07-28, 2025-11-25, 2025-03-26, 2024-11-05	2026-10-19

Tools (1)

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.plan_get -> agents.work_next -> agents.plan_claim -> agents.plan_execute. context.project_id on every batch. Prompts: agentstack_session_setup, agentstack_execute_budget.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.agentstacktech/agentstack",
  "title": "AgentStack (agentstack.tech)",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://agentstack.tech/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/agentstacktech/AgentStack",
    "source": "github"
  },
  "websiteUrl": "https://agentstack.tech",
  "description": "Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments)."
}