Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging level (e.g. INFO, DEBUG)INFO
QDRANT_KEYYesQdrant API key
QDRANT_URLYesQdrant cluster URL
EMBEDDING_MODELNoEmbedding model to use (default: Snowflake/snowflake-arctic-embed-s)Snowflake/snowflake-arctic-embed-s
AUTO_CREATE_INDEXESNoWhether to automatically create payload indexes at startup (default: true)true
QDRANT_COLLECTION_NAMEYesCollection to search (e.g. papers_test)

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
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_papersA

Semantic search for ACL conference papers about NLP. Embeds the query with a Sentence-Transformers model (Snowflake arctic-embed-s, 384-dim, matching the collection index) and returns the most similar papers ranked by cosine similarity. USE THIS when the user has a research topic or question and wants to find relevant papers. Narrow results with structured filters: publication year (exact or range), venue/booktitle, collection acronym (e.g. ACL/EMNLP/NAACL), collection id, field of study, or author. Set vector_name to search within a specific summary dimension (overview/approach/challenge/outcome).

get_paperA

Fetch a single ACL conference NLP paper by its paper_uuid (the Qdrant point id). USE THIS to inspect a paper in full detail — abstract, summaries, method/task entities — when you already have its ID from a search_papers or list_papers result. Returns the complete paper payload.

list_papersA

Browse ACL conference NLP papers using structured filters only (no semantic query). USE THIS to list papers when you know the filters but have no search text — e.g. 'all ACL 2024 papers' or 'all papers by this author'. Supports year/venue/acronym/field_of_study/author filters and pagination via offset (the last paper_uuid from the previous batch).

get_collection_infoA

Discover the ACL NLP papers collection schema: vector dimensions, distance metrics, total paper count, and sampled distinct values for filterable fields (years, venue acronyms, booktitles, fields of study). USE THIS first when you need to know what venues, years, or fields exist before building search_papers or list_papers filters.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.7/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a distinct role: semantic search, ID-based retrieval, filter-based browsing, and schema discovery. There is no overlap in purpose; search_papers and list_papers differ meaningfully by query type.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with lowercase and underscores: search_papers, get_paper, list_papers, get_collection_info. This is predictable and easy to understand.

Tool Count5/5

Four tools is well-scoped for a read-only ACL paper search and retrieval server. Each tool covers a core capability without unnecessary bloat.

Completeness5/5

The tool surface covers the full read-only lifecycle: discover schema, search semantically, browse with filters, and retrieve a specific paper by ID. There are no obvious missing operations for the stated purpose.

Maintenance

ActivitySlowing
ResponsivenessNo issues