humor-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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_humorA | Full-text search the humor corpus. Returns lines with their credit attached. Filter by source pack, kind or minimum human score. |
| top_ratedB | The highest human-rated lines in the corpus. Single-word lexicon entries use a different scale and are excluded unless kind='word'. |
| taste_profileB | What this corpus's human rater actually liked versus disliked, with the score distribution. Use this to calibrate register before writing. |
| breakdownA | Structural breakdowns (mechanism, setup/turn, technique) for lines matching a query — how the joke is built, not just the text. |
| preference_pairsA | Chosen vs rejected pairs — what won head-to-head and what lost. Off-rubric packs are withheld by default and reported in |
| sourcesA | Every corpus pack loaded: who wrote it, under what license, whether it may be redistributed or used commercially, and how to cite it. |
| style_packC | A compact, paste-ready style brief: exemplars, liked/disliked calibration, and the attribution block that must travel with any output. |
| corpus_statsC | What is loaded: counts by pack and by kind, size on disk. |
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 8 tools
Most tools are clearly distinct: search_humor finds text, top_rated ranks by score, breakdown explains structure, preference_pairs shows pairwise comparisons, and sources/corpus_stats describe corpus metadata. However, taste_profile, style_pack, and preference_pairs have some overlap in that they all serve rater/calibration purposes and could cause misselection when an agent wants calibration guidance.
Names use a consistent snake_case convention throughout, mostly combining a noun subject with a descriptive suffix (search_humor, top_rated, taste_profile, corpus_stats, style_pack). Most are noun-headed which is descriptive though not strictly verb_noun; minor deviation like 'breakdown' and 'sources' being bare nouns breaks the pattern slightly.
8 tools is right in the sweet spot for a specialized domain server. Each tool addresses a distinct need: searching, ranking, calibration, structural analysis, pairwise comparison, attribution, and corpus statistics. Nothing feels redundant or frivolous.
The surface covers the main workflow: search for humor, understand quality via ratings, get structural breakdowns, see pairwise preferences, and obtain attribution/licensing. Minor gaps could include functionality to inspect individual lines by ID or to generate/write new humor, but for an analysis-oriented humor corpus, the coverage is strong.