AINative ZeroDB MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZERODB_API_URL | No | ZeroDB API endpoint | https://api.ainative.studio/api/v1 |
| ZERODB_PASSWORD | No | Authentication password | |
| ZERODB_USERNAME | No | Authentication username | |
| ZERODB_API_TOKEN | No | API token (if available) | |
| ZERODB_PROJECT_ID | No | Your project identifier | |
| MCP_CONTEXT_WINDOW | No | Context window size | 8192 |
| MCP_RETENTION_DAYS | No | Data retention period | 30 |
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 |
|---|---|
| zerodb_store_memoryC | Store agent memory in ZeroDB for persistent context |
| zerodb_search_memoryC | Search agent memory using semantic similarity |
| zerodb_get_contextC | Get agent context window for current session |
| zerodb_store_vectorC | Store vector embedding with metadata (must be exactly 1536 dimensions) |
| zerodb_search_vectorsC | Search vectors using semantic similarity |
| zerodb_renew_tokenC | Manually renew authentication token |
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 6 tools
Most tools have distinct purposes, but zerodb_search_memory and zerodb_search_vectors could be confusing as both involve semantic similarity searches. The descriptions clarify that one searches 'agent memory' and the other searches 'vectors', but the overlap in functionality might cause misselection without careful reading.
All tools follow a consistent zerodb_verb_noun naming pattern with snake_case throughout. The verbs (get, renew, search, store) are clear and predictable, making the tool set easy to navigate and understand at a glance.
With 6 tools, this server is well-scoped for managing agent context and memory in ZeroDB. Each tool serves a specific function (e.g., authentication, storage, retrieval), and there are no redundant or trivial tools, making the count appropriate for the domain.
The tool set covers core operations for agent context and memory management, including get, renew, search, and store functions. A minor gap exists in update or delete operations for stored memories or vectors, which agents might need for lifecycle management, but the current tools support basic workflows effectively.