Context Grove
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXT_GROVE_ROOT | Yes | Must point to your project folder, the one containing `.context-grove/`. Use absolute paths. |
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 |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| knowledge_healthB | Check whether the project's Context Grove knowledge source is available. / Verifique se a fonte de conhecimento Context Grove do projeto está disponível. |
| knowledge_catalogB | List knowledge areas and canonical project documents. / Liste as áreas de conhecimento e documentos canônicos do projeto. |
| knowledge_readC | Read a project knowledge document by its path relative to .context-grove. / Leia um documento de conhecimento pelo caminho relativo a .context-grove. |
| knowledge_searchC | Find matching text in project knowledge and return cited snippets. / Busque texto correspondente no conhecimento e retorne trechos com fontes. |
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
Each tool targets a clearly distinct operation: availability check, catalog listing, document reading, and text search. There is no meaningful overlap between health, catalog, read, and search in this read-only knowledge context.
All tool names follow the same predictable snake_case pattern with a shared knowledge_ prefix. The suffixes vary between resource and action words, but the overall convention is consistent and readable.
Four tools are well-scoped for a read-only project knowledge source. Each tool earns its place by covering a distinct part of the access lifecycle: availability, discovery, retrieval, and search.
The surface covers checking availability, listing canonical areas and documents, reading by path, and searching with cited snippets. For a read-only knowledge access interface, this is complete with no obvious dead ends.