Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_AI_API_KEY | Yes | Your Google AI API key used for generating embeddings (e.g., text-embedding-004). | |
| UPSTASH_VECTOR_REST_URL | Yes | The REST URL for your Upstash Vector Index. | |
| UPSTASH_VECTOR_REST_TOKEN | Yes | The REST Token for your Upstash Vector Index. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_context | Add a piece of context/knowledge to the vector database. Use this to store information that can be retrieved later for relevant queries. |
| add_contexts_batch | Add multiple context entries to the vector database in a single operation. More efficient for bulk indexing. |
| query_context | Search for relevant context based on a natural language query. Returns the most semantically similar stored contexts. |
| delete_context | Delete a specific context entry by its ID |
| delete_contexts_batch | Delete multiple context entries by their IDs |
| get_stats | Get statistics about the vector database (number of stored contexts, dimensions) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Context Database Statistics | Current statistics about the context vector database |