CypherMonkeyAI omni-channel lab

A lifelong-learner lab on AI omni-channel agents, including voice and the contact center. Free to read. Nothing sold.

Model Context Protocol · L3 · 25 min

A notes server on paper

Learn in five minutes

  • The server offers two resources: list notes, read note.
  • It offers no send tool.
  • The host is a learning page, not a company product.
  • The client asks, the person allows read, the note is quoted.
  • If the note is missing, the host refuses.

This is the capstone's tool shape in miniature. You can implement it later with the Python labs. You do not need a public URL to understand it.

This section HTML

Visual

T6-R6 diagram

Diagram SVGDiagram PNGDiagram HTML

Flow SVGFlow PNGFlow HTML

Paper call

  1. Person asks: what does note A say about hours?
  2. Client lists tools and resources.
  3. Person allows read of note A.
  4. Server returns the sentence.
  5. Host quotes it and stops.

This section HTML

Quiz

Which tool does this paper server refuse to offer?

Send is a side effect left out on purpose.

What happens if the note is missing?

Missing notes are a refusal.

What is the host in the story?

The story stays inside the lab.

This section HTML

Ecosystem

Paper server
A design you can trace without running a public service.

Sisters: Plugins, Function calling, Language-server ideas.

A notes server can serve chat and a voice host if both speak the same protocol.

Treat the spec revision as something you pin, like a model id.

Config

  • Write the goal in one sentence.
  • Name the input and the allowed output.
  • Save the trace next to the result.

Troubleshooting

  • The answer looks fluent and is wrong. Check whether a source passage actually contains the claim.
  • The loop never stops. Set a step cap and stop when the tool result repeats.

This section HTML

Sources HTML

Sources and go deeper

sources.json