zettaquant-vslm-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZQ_API_KEY | Yes | Your ZettaQuant API key. Must have the vslm scope. | |
| ZQ_BASE_URL | No | Override for staging or a private gateway. | https://api.zettaquant.ai |
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 | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vslm_predictA | Filter a list of sentences to only those relevant to Use this BEFORE feeding noisy context (earnings-call transcripts, news articles, long reports, log lines) to an LLM; it typically cuts token spend without losing important context. Chain it with your own language model. Args: sentences: raw input sentences; ~2000 per call is comfortable. query: natural-language description of the topic to filter for (e.g. "AI capex plans", "rate cuts", "supply chain risk"). Returns: dict with: relevant_sentences: sentences that passed the filter, original order. total_sentences, relevant_count: counts to compute savings. topic_used: the topic string the model actually filtered against. topic_source: "zettaquant" (server-derived) or "caller" (you supplied). model_id: which V-SLM head handled the request. |
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 1 tool
Only one tool exists, so there is no possibility of selecting the wrong tool for a task. The tool's purpose is clearly defined as relevance filtering.
With a single tool, there is no internal naming pattern to violate. The name 'vslm_predict' is readable and action-oriented, though it uses noun-verb ordering rather than the more common verb-noun style.
One tool is below the usual 3-15 range, but it is a dedicated single-purpose utility specialized for sentence relevance filtering. The count feels slightly thin rather than excessive or trivial.
For the stated purpose of filtering noisy sentences before LLM ingestion, the tool provides the core operation plus useful metadata like counts and model info. There is no obvious missing operation within this narrow, well-defined domain.