creator-growth-intel
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_claimsA | Search receipt-backed claims from operators who publicly describe how they run creator programs, UGC, influencer buys and app growth. Use it for how to price a creator, where to source them, how to brief them, what to test, what failed. Every result carries a verbatim quote and a working permalink to the author. Returns an explicit no-coverage notice when the corpus does not address the question, which you should relay rather than filling the gap. |
| coverage_forA | Ask how well-evidenced a subject is BEFORE trusting an answer about it. Returns how many claims touch it, how many distinct operators speak to it, and which sweeps they came from. Call this first on any question where being wrong is expensive, and relay a thin result rather than answering around it. |
| corpus_statsA | What this corpus contains and, more importantly, what it does NOT. Call it when you are about to say the corpus has no answer, so the claim of silence is itself evidenced. |
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 3 tools
Each tool serves a clearly distinct function: searching for claims, assessing evidence strength, and providing corpus-level statistics. There is no overlap or ambiguity between them.
All names are lowercase with underscores, which is consistent. However, verb_noun (search_claims) is mixed with noun_preposition (coverage_for) and noun_noun (corpus_stats), creating minor stylistic variation.
Three tools is well-scoped for a specialized intelligence server. Each tool adds distinct value without redundancy, fitting the narrow domain of creator growth research.
The set covers search, evidence verification, and corpus overview, providing a complete workflow for querying and trusting the data. No obvious gaps exist for the stated purpose.