windex MCP server
by stevemurr
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WINDEX_DATA_ROOT | No | Bulk storage: downloads, parquet staging (point at a big disk) | ~/.windex/data |
| WINDEX_EMBED_DIM | Yes | Your embedding dimension | |
| WINDEX_EMBED_MODEL | Yes | Your embedding model name | |
| WINDEX_EMBED_BACKEND | Yes | Your embedding backend: http-openai, http-tei, or st | |
| WINDEX_EMBED_ENDPOINT | Yes | Your embedding endpoint URL | |
| WINDEX_EMBED_BATCH_SIZE | No | Batch size for embedding | 32 |
| WINDEX_EMBED_CONCURRENCY | No | Indexing throughput vs. live-query latency | 10 |
| WINDEX_EMBED_QUERY_TIMEOUT | No | Deadline before hybrid search degrades to keyword | 5000 |
| WINDEX_EMBED_THROTTLE_SECONDS | No | Throttle seconds between batches | 0 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues