cowork-semantic-search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | Yes | The absolute path to the cowork-semantic-search directory, required for the Python interpreter to locate the server modules. |
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| index_folderA | Index or re-index all documents in a folder for semantic search. Scans the folder for supported document types (.txt, .md, .pdf, .docx, .pptx, .csv), extracts text, splits into chunks, computes embeddings, and stores them in a local vector database. Only processes files that have changed since the last indexing run. Safe to call multiple times — unchanged files are skipped automatically. |
| semantic_searchA | Search indexed documents using natural language. Finds the most relevant document chunks matching the query using semantic similarity. Returns ranked results with source file paths and relevance scores. Use mode='hybrid' to combine vector search with full-text search via Reciprocal Rank Fusion for better keyword + semantic matching. The folder must be indexed first with index_folder. |
| get_index_statusA | Get status information about the current search index. Returns total chunks, list of indexed files with chunk counts, and file type distribution. |
| reindex_fileA | Force re-index a single file, ignoring the content hash cache. Deletes existing chunks for this file, re-parses, re-chunks, re-embeds, and stores new chunks. Useful when you know a file has changed or when parsing was updated. |
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 4 tools
Tools cover distinct lifecycle stages: status check, folder indexing, querying, and forced single-file reindexing. The only mild overlap is between index_folder and reindex_file, but descriptions clarify bulk vs. targeted cache-bypassing use.
Three of four names follow verb_noun snake_case (get_index_status, index_folder, reindex_file). semantic_search is an adjective_noun outlier, but the overall pattern remains readable and consistent.
Four tools is a tight, well-scoped set for a focused semantic-search server. Each operation (index, query, status, targeted reindex) maps to a distinct user need without bloat.
Core index/search/reindex/status flows are covered, but there is no delete or remove-from-index operation. Deleted or moved files would leave stale chunks, creating a notable lifecycle gap.