jef-mcp
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jef_yes_noA | Answer a yes-or-no question with YES or NO and a confidence. Use this when the user wants a question settled and there is no correct answer, such as whether to go out, whether to send the message, or whether to deploy on a Friday. Do not use it for questions of fact, which it will answer confidently and wrongly. |
| jef_pickA | Pick one of 2 to 5 options and give a probability for each. Use this when the user is stuck between named choices and wants one chosen for them: dinner, which film, which of three plans. Jef can only ever return an option you passed in, so it cannot introduce an idea of its own. |
| jef_scoreA | Rate something from 1 to 10. Use this when the user wants a number put on something subjective, such as an outfit, a plan, or an excuse. The number is arbitrary and deterministic, so the same description always scores the same. |
| jef_rankA | Put 2 to 5 options in order, best first. Use this when the user wants a priority order decided for them, such as which chore to do first or which of several tasks to start with. Returns every option you passed, reordered, never a subset. |
| jef_flagA | Judge a described behaviour as RED FLAG, GREEN FLAG or BEIGE FLAG. Use this when the user describes something someone did and wants a verdict on it. Beige means neither good nor bad, merely odd. Anything describing harm, threats or abuse escalates instead of being judged. |
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 5 tools
Each tool produces a distinctly different output type: binary yes/no, a single pick with probabilities, a numeric score, an ordering, and a categorical flag. The descriptions explicitly map use cases to each response shape, so an agent should not confuse them.
All names share the jef_ prefix and use lowercase snake_case, which is consistent. The only slight deviation is jef_yes_no being named after its output while the others are verb-like commands (pick, score, rank, flag), but this is a minor inconsistency.
Five tools is a well-scoped size for a subjective-decision helper server. Each tool covers a different way a user might want an opinion, and none feel redundant or unnecessary.
The tool surface covers the main decision output types an agent would need: binary choices, selection among options, numerical ratings, ordering, and categorical verdicts. There are no obvious dead ends or missing operations for the stated purpose.