Skip to main content
Glama
stevemurr

windex MCP server

by stevemurr

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WINDEX_DATA_ROOTNoBulk storage: downloads, parquet staging (point at a big disk)~/.windex/data
WINDEX_EMBED_DIMYesYour embedding dimension
WINDEX_EMBED_MODELYesYour embedding model name
WINDEX_EMBED_BACKENDYesYour embedding backend: http-openai, http-tei, or st
WINDEX_EMBED_ENDPOINTYesYour embedding endpoint URL
WINDEX_EMBED_BATCH_SIZENoBatch size for embedding32
WINDEX_EMBED_CONCURRENCYNoIndexing throughput vs. live-query latency10
WINDEX_EMBED_QUERY_TIMEOUTNoDeadline before hybrid search degrades to keyword5000
WINDEX_EMBED_THROTTLE_SECONDSNoThrottle seconds between batches0

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/stevemurr/windex'

If you have feedback or need assistance with the MCP directory API, please join our Discord server