Skip to content
WhatShouldMyBotDo logo

WhatShouldMyBotDo MCP server

Which MCP servers are WhatShouldMyBotDo'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 2026-10-28

← Back to WhatShouldMyBotDo

Whose server it is
  • Registry namecom.whatshouldmybotdo/plannerverified in the MCP registry

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

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools3
  • Server calls itselfwhatshouldmybotdo
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 79 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

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: 8, the first on 2026-10-28
  • INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
  • Answered100% of days8 of 8 daily checks
  • Median first answer763 ms
  • Space in an agent's context≈ 1,191 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · Sort overnight email and draft replies for approval
  • cannot · Prepare a daily brief from calendar and task list
  • not sure · Follow up with leads after a quote goes out

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

None of the five warning signs in these definitions.

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 offers3 tools · read 2026-10-28
  • plan_first_agent

    Recommend the first AI agent (bot) a small business should set up, plus the next 3 jobs to add, from the same 5 questions and the same ranking as the free planner at whatshouldmybotdo.com/tools/what-should-my-bot-do. Read-only, no…

  • search_use_cases

    Search the WhatShouldMyBotDo library of AI agent use cases for small businesses by plain words. Read-only. Returns up to 8 matches with slug, title, one-line summary, schedule and a link to the guide. Use a slug from here with get_template.

  • get_template

    Get the copy-paste routine (instructions) for one WhatShouldMyBotDo use case, written for Grok Bot, ChatGPT, Claude or n8n. Read-only. Every routine is drafts-first: the user reviews before anything is sent or posted.

How to connect

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

{
  "mcpServers": {
    "planner": {
      "type": "http",
      "url": "https://whatshouldmybotdo.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http whatshouldmybotdo https://whatshouldmybotdo.com/api/mcp

Add to CursorAdd to VS Code

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

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.