random-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Bind address for http/sse | 127.0.0.1 |
| PORT | No | Bind port for http/sse | 8000 |
| APP_NAME | No | Name reported by server_info | random-mcp-server |
| RANDOM_SEED | No | Fixed seed for reproducible pools | |
| RANDOM_COUNT | No | Records generated per kind at start-up | 25 |
| MCP_TRANSPORT | No | Transport type: stdio, http, or sse | stdio |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| server_infoA | Health/status of the server (the REST server's |
| list_recordsA | Return the seeded pool of records for Pass |
| get_recordB | Return a single record from |
| count_recordsB | Return the number of records available for |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool serves a distinct purpose: server_info provides health, list_records returns multiple records, get_record fetches a single record by ID, and count_records returns a count. No overlapping functionality, so selection is unambiguous.
Three tools follow a clear verb_noun pattern (list_records, get_record, count_records), but server_info breaks the convention with a noun_noun style. Minor inconsistency, but overall readable.
Four tools are well-scoped for a read-only random data server; each provides a unique retrieval operation without redundancy.
The surface covers listing, getting, counting, and server status, but lacks a way to discover available 'kind' values and offers no filtering or pagination beyond a simple count cap. This could hinder an agent that doesn't already know valid kinds.