About mcp-server-demo
mcp-server-demo is a demonstration of a multi-agent task flow for planning a business trip to Tokyo. The README describes agent discovery and task handoff, but provides little detail about implementation or intended users.
Key features
- 01Demonstrates specialist agent discovery
- 02Shows agent card retrieval
- 03Illustrates task initiation and handoff
- 04Shows immediate flight-result return
Use cases
- 01Explore a business-trip planning flow
- 02Review agent discovery and task handoff
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-server-demo
graph TD
A["User Request: \"Plan business trip to Tokyo\""] --> B[Discovery Phase]
B --> C[Client Agent identifies needed specialists: Flights, Hotels, Activities]
C --> D[Retrieve Agent Cards]
D --> E{Task Initiation}
E --> |POST /taskssend| F[Server: Flight Booking Agent]
F --> G{Processing}
G -->|Immediate Result| H[Return: Available Flights]
G -->|Need Input| I[State: Input-Required<br>"Preferred airline?"]
G -->|Long Process| J[State: Working<br>"Comparing rates..."]
I --> K[Client Response]
K --> G
J --> L[Status Updates]
L --> M[[Polling / SSE / Push Notifications]]
J --> N{Task Completion}
N -->|Success| O[Return: Final Flight Options]
N -->|Failure| P[Mark as Failed]
O --> Q[Main Agent combines results<br>with Hotel/Transport/Activity agents]
Q --> R[Present Comprehensive Itinerary]
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.