Skip to content
ChatStack logo

ChatStack MCP server

Which MCP servers are ChatStack's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-29

← Back to ChatStack

Whose server it is
  • Registry nameapp.chatstack/app-cost-estimatorverified in the MCP registry

The registry name sits under chatstack.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools5
  • Server calls itselfchatstack-app-cost-estimator
  • Server version0.9.4
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 606 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: estimate total development cost for an app idea; generate a structured PRD with user stories.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "estimate total development cost for an app idea", the likely first call is start_session.
  • For "generate a structured PRD with user stories", the likely first call is start_session.
  • Keep approval on for send_turn, send_action: they delete, send or pay without saying so.
  • send_turn, send_action change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-30
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer627 ms
  • Space in an agent's context≈ 2,378 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsA · 97 of 100
  • Typed results5 of 5 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 5

What an agent can do with it

  • can do · estimate total development cost for an app idea
  • can do · generate a structured PRD with user stories
  • not sure · trim MVP scope by removing user stories

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that delete, send or pay, marked as not destructive: send_turn, send_action
  • Tools that change data, on a server that answers without a sign-in: send_turn, send_action

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers5 tools · read 2026-10-29
  • start_session

    Start a guided session to estimate app development cost, scope an MVP, and generate a software PRD. No portal account or personal access token is required. Call it with no arguments unless the user already named Review each step…

  • send_turn

    Continue an app cost estimate by sending the user's answers or requested changes to the MVP scope, user stories, requirements, or technical specification. Pass their exact words in input_as_text, even when next_tool is send_action…

  • send_action

    Submit the user's pending choice. Set action_type to a value from pending_gate_payload.allowed_actions. In Review each step, action_type is required; confirmed_by_user=true is preferred and is not a substitute for it. In Run it for me…

  • get_estimate_status

    Read the current app cost estimate without advancing it. Returns flow_stage, pending_gate, and pending_gate_payload. After submission it also returns post_submit_notice and post_submit_links: relay the notice verbatim, keep every URL, and…

  • submit_prd

    Submit the completed software PRD and app development estimate for email delivery and portal project creation. Call it only after user stories, requirements, tech specs, and the estimate exist. (flow_stage estimate). Run it for me stops…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "app-cost-estimator": {
      "type": "http",
      "url": "https://mcp.chatstack.app/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http chatstack https://mcp.chatstack.app/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.chatstack.app/mcp as a custom connector in the settings.

OpenAPI spec

6 paths, read 2026-10-29. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.