BusinessMCP

MCP resources & prompts, explained

5 min readLast updated September 21, 2026

Beyond tools, your BusinessMCP endpoint exposes MCP resources (a live business snapshot, SOPs, memory, brain search) and prebuilt prompts (weekly review, funnel audit, CRO, SEO, ad-waste, replay review) any MCP client can use.

Tools, resources & prompts

A first-class MCP server exposes three things. Tools are actions (covered in the data you can query). Resources are addressable, read-only context. Prompts are ready-made analyses. Your BusinessMCP endpoint advertises all three, plus server instructions describing how to use it — everything is scoped and redacted by your key's access policy.

Resources

Read these directly (no tool call) via resources/list then resources/read:

  • `businessmcp://snapshot` — a live 30-day analytics + funnel + pipeline snapshot, policy-scoped.
  • `businessmcp://sops` — your enabled standard operating procedures, each linking to businessmcp://sop/{id} for the full body.
  • `businessmcp://memory` — the compounding knowledge the analyst has learned about your business.
  • `businessmcp://brain/{query}` — hybrid search over your durable company knowledge, policy-filtered.

Prompts

Invoke by name via prompts/get. Each seeds a tool-chaining analysis:

  • `weekly-growth-review` — traffic, funnel, revenue, SEO and ads, this week vs last.
  • `funnel-audit` — find the biggest leak and what to fix first.
  • `conversion-optimization` — CRO ideas grounded in heatmaps + replays.
  • `seo-opportunities` — striking-distance keywords and quick wins.
  • `ad-waste-audit` — wasted spend + audiences to build.
  • `session-replay-review` — watch and summarise frustrated sessions.
  • `work-linkedin-queue` — hand the LinkedIn touches the engine is holding to the agent on your own machine. It is the one prompt that asks an agent to act rather than analyse: LinkedIn's API forbids automated cold outreach, so the send happens in your session while our caps and warm-up decide what reaches the queue. Needs full access — a read-only or no-send key cannot see its tools.

Using them from a client

Most MCP clients surface resources as attachable context and prompts as slash-commands or templates. In Claude Desktop, connected resources appear in the attachment menu and prompts appear as commands. Point your client at your endpoint (see Connect Claude, GPT & Gemini) and they show up automatically alongside your tools.

Frequently asked questions

What is the difference between a resource and a tool?

A tool is an action the model chooses to call with arguments. A resource is addressable, read-only context the client can attach without a tool call — like a live business snapshot or an SOP. Prompts are ready-made instructions that seed a task.

Keep going

Turn your company into one AI-ready data platform on a single hosted MCP endpoint.