Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYNoOpenAI API key for LLM-based query generation and quality assessment
ANTHROPIC_API_KEYNoAnthropic API key for LLM-based query generation and quality assessment
TWITTER_BEARER_TOKENNoTwitter/X API bearer token for authentication

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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
generate_search_queryC

Generate effective Twitter search queries for finding slander, roasts, jokes, and memes about a target character (real or fictional). Uses AI to produce creative, context-aware queries that capture character-specific slander.

fetch_postsA

Fetch posts from Twitter for a given query, looping until quality threshold is met. Uses AI to evaluate batch quality and stops early when sufficient roast content is found. Returns posts with engagement metrics.

rank_postsA

Rank fetched posts by engagement, separate text from media posts, and extract nicknames. Uses engagement formula: (likes * 1.0) + (retweets * 2.0) + (replies * 0.5). Retweets weighted highest because sharing is strong signal for humor.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose in the slander-finding workflow: generate_search_query creates queries, fetch_posts retrieves posts based on those queries, and rank_posts processes and ranks the fetched posts. There is no overlap or ambiguity between their functions.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (fetch_posts, generate_search_query, rank_posts) with clear, descriptive verbs that align with their actions. No deviations or mixed conventions are present.

Tool Count4/5

Three tools is a minimal but reasonable count for this server's purpose of finding and ranking slander content. It covers the core workflow (query generation, fetching, ranking) without being overly sparse, though a few additional tools (e.g., for filtering or exporting) could enhance completeness.

Completeness4/5

The tool set covers the essential steps for slander discovery: generating queries, fetching posts, and ranking them. Minor gaps exist, such as lacking tools for saving results or refining searches, but agents can work around these with the provided tools to achieve the server's goal.

Maintenance

ActivityInactive
ResponsivenessNo issues