ContextWeaver MCP Server
by wchiway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RERANK_MODEL | Yes | Reranker model name | |
| RERANK_TOP_N | No | Rerank return count | 20 |
| CW_SEARCH_WLEX | No | Lexical weight | 0.4 |
| CW_SEARCH_WVEC | No | Vector weight (fusion stage) | 0.6 |
| RERANK_API_KEY | Yes | Reranker API key | |
| IGNORE_PATTERNS | No | Extra ignore patterns | |
| RERANK_BASE_URL | Yes | Reranker API URL | |
| EMBEDDINGS_MODEL | Yes | Embedding model name | |
| EMBEDDINGS_API_KEY | Yes | Embedding API key | |
| EMBEDDINGS_BASE_URL | Yes | Embedding API URL | |
| CW_SEARCH_SMART_MAX_K | No | Smart TopK hard upper bound | 8 |
| EMBEDDINGS_DIMENSIONS | No | Vector dimensions | 1024 |
| CW_SEARCH_RERANK_TOP_N | No | Results kept after rerank | 10 |
| CW_SEARCH_VECTOR_TOP_K | No | Vector recall candidates | 80 |
| CW_SEARCH_MAX_TOTAL_CHARS | No | Token budget in chars | 48000 |
| EMBEDDINGS_MAX_CONCURRENCY | No | Embedding concurrency | 10 |
| CW_SEARCH_IMPORT_FILES_PER_SEED | No | E3 import files per seed | 3 |
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
ActivityInactive
ResponsivenessNo issues