# WhatShouldMyBotDo (remote · whatshouldmybotdo.com)

Pick the first AI agent for a small business. Read-only planner tools with links to setup guides.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `whatshouldmybotdo.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-whatshouldmybotdo-planner/api-mcp.md), [page](https://verifymcp.io/servers/com-whatshouldmybotdo-planner/api-mcp)

## Channel facts

- Endpoint: `https://whatshouldmybotdo.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 944 tokens (~314/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the WhatShouldMyBotDo MCP server?

WhatShouldMyBotDo is a hosted endpoint at https://whatshouldmybotdo.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-whatshouldmybotdo-planner 'https://whatshouldmybotdo.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-whatshouldmybotdo-planner": {
      "url": "https://whatshouldmybotdo.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-whatshouldmybotdo-planner": {
      "type": "http",
      "url": "https://whatshouldmybotdo.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-whatshouldmybotdo-planner]
url = "https://whatshouldmybotdo.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-whatshouldmybotdo-planner": {
      "type": "remote",
      "url": "https://whatshouldmybotdo.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-whatshouldmybotdo-planner --url 'https://whatshouldmybotdo.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-whatshouldmybotdo-planner:
    url: "https://whatshouldmybotdo.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-whatshouldmybotdo-planner": {
      "Transport": "http",
      "Url": "https://whatshouldmybotdo.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-whatshouldmybotdo-planner -t streamable-http -u 'https://whatshouldmybotdo.com/api/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 73, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-21 (score 72)

First indexed and scored.

## MCP tools (3)

### `plan_first_agent` (~594 tokens)

Plan my first AI 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 account, nothing is saved. Ask the user the 5 questions first; do not guess their answers. Returns titles, why it fits, estimated hours saved a week (estimates, not guarantees), schedule, and links to each guide and the full plan on the site.

Input parameters:

- `ai_tool` (string): Q4 "Which AI tool will run your bots?" One of: grok (Grok Bot), chatgpt (ChatGPT), claude (Claude), n8n (n8n). Default grok.
- `apps` (array): Q3 "Which apps does your business already use?" Up to 12 of: gmail (Gmail / email), calendar (Google Calendar), slack (Slack), notion (Notion), sheets (Google Sheets / Excel), crm (CRM (HubSpot, GHL……
- `business_type` (string, required): Q1 "What kind of business do you run?" One of: solo-founder (Solo founder), agency-owner (Agency owner (marketing, web, AI)), realtor (Real estate agent / team), medical-office (Dental / medical offi…
- `first_goal` (string): Q5 "What do you want first?" One of: customers (Win more customers), never-miss (Never miss a customer message), admin (Get admin and invoices off my plate), inbox (Get my inbox under control), conte…
- `time_drains` (array, required): Q2 "What eats most of your week?" 1 or 2 of: email (Email & inbox), leads (Finding & following up leads), content (Creating content), scheduling (Scheduling & bookings), support (Customer support / c…

### `search_use_cases` (~101 tokens)

Search AI agent 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.

Input parameters:

- `query` (string, required): Plain words for the job you want a bot to do, e.g. "follow up leads" or "invoice reminders". 2-100 characters.

### `get_template` (~139 tokens)

Get a copy-paste agent routine

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.

Input parameters:

- `ai_tool` (string): Which AI tool the routine is written for. One of: grok (Grok Bot), chatgpt (ChatGPT), claude (Claude), n8n (n8n). Default grok.
- `slug` (string, required): Use-case slug from search_use_cases or plan_first_agent, e.g. "lead-follow-up-sequences".

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-whatshouldmybotdo-planner/api-mcp#diagnostics

## Score history

- 2026-10-23: 73
- 2026-10-22: 73
- 2026-10-21: 72

## Common questions

### What is the WhatShouldMyBotDo MCP server?

WhatShouldMyBotDo is an MCP server listed in the public MCP registry as com.whatshouldmybotdo/planner. Pick the first AI agent for a small business. Read-only planner tools with links to setup guides. This page covers its hosted endpoint (https://whatshouldmybotdo.com/api/mcp).

### Is the WhatShouldMyBotDo MCP server safe to use?

WhatShouldMyBotDo scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the WhatShouldMyBotDo MCP server expose?

WhatShouldMyBotDo exposes 3 tools: plan_first_agent, search_use_cases, get_template. Their descriptions and schemas cost roughly 834 tokens of context every time the server is loaded.

### Does the WhatShouldMyBotDo MCP server require authentication?

No. We connected to WhatShouldMyBotDo without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the WhatShouldMyBotDo MCP server still maintained?

WhatShouldMyBotDo is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://whatshouldmybotdo.com/api/mcp
- Website: https://whatshouldmybotdo.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-whatshouldmybotdo-planner/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-whatshouldmybotdo-planner/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-whatshouldmybotdo-planner/api-mcp