mcp-tool-builder
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_toolC | Create a new Python tool with specified functionality |
| list_available_toolsB | List all currently available tools |
| get_bitcoin_priceA | Gets current Bitcoin price in USD from CoinGecko API |
| get_weather_forecastC | Retrieves weather forecast for a given ZIP code using NWS API |
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
The tools have distinct purposes (tool creation, Bitcoin price, weather forecast, tool listing), but the domain is unclear—'create_tool' and 'list_available_tools' suggest a tool management server, while the other two are unrelated utilities. This mismatch could confuse agents about the server's scope, though individual tools are not directly overlapping.
Three tools follow a consistent verb_noun pattern (create_tool, get_bitcoin_price, get_weather_forecast), but 'list_available_tools' uses 'list' instead of 'get', breaking full consistency. Overall, naming is mostly predictable and readable with only minor deviation.
With 4 tools, the count is reasonable for a small utility set, but it feels thin for a 'tool-builder' server that might imply more comprehensive tool management. The inclusion of unrelated utilities (Bitcoin, weather) makes the scope ambiguous, affecting appropriateness.
If the domain is tool management, there are significant gaps: no update, delete, or test tools, and the unrelated utilities don't fit. If it's a general utility server, coverage is sparse and random. In either case, the surface is incomplete for coherent agent workflows.