ZeroDB Agent Memory MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZERODB_API_KEY | No | API key for authentication (preferred over username/password). | |
| ZERODB_API_URL | No | Base URL of the ZeroDB API. Defaults to http://localhost:8000 or auto-detected. | http://localhost:8000 |
| ZERODB_PASSWORD | No | Password for username/password authentication. | |
| ZERODB_USERNAME | No | Username for username/password authentication. | |
| ZERODB_PROJECT_ID | No | Your ZeroDB project ID. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| zerodb_store_memoryA | Store conversation context in agent memory with automatic importance scoring and embedding. Supports multi-session tracking and memory decay. |
| zerodb_search_memoryA | Search agent memory semantically using natural language queries. Supports cross-session search and filtering by tags, user, or time range. |
| zerodb_get_contextA | Get full conversation context window for a session with smart pruning. Automatically manages token limits, applies memory decay, and prioritizes important/recent memories. |
| zerodb_embed_textA | Generate vector embeddings for text using BAAI BGE models. Useful for manual vector operations or custom similarity calculations. |
| zerodb_semantic_searchB | Search memory by semantic similarity without needing a text query. Directly search using vector embeddings or similar memories. |
| zerodb_clear_sessionA | Clear all memories for a session. Use with caution - this permanently deletes conversation history. |
| zerodb_synthesize_contextA | Retrieve and LLM-synthesize relevant memories into a coherent context string. Searches memory for the query, retrieves top results, then uses Claude Haiku to synthesize a narrative, bullet list, or structured summary. Returns a ready-to-use context string for grounding AI responses. |
| zerodb_configure_auto_contextA | Configure ambient memory injection. When enabled, ZeroDB automatically retrieves relevant memories before each tool call and prepends them as context — agents get memory without calling recall() explicitly. |
| zerodb_get_auto_context_configA | Get the current auto-context configuration for an agent. |
| zerodb_slack_sendA | Send a Slack message using your stored Slack OAuth connection. No API key required — uses the token from your connected Slack account in ZeroDB. |
| zerodb_gmail_replyA | Reply to a Gmail thread using your stored Google OAuth connection. Sends from your connected Gmail account. |
| zerodb_calendar_createA | Create a Google Calendar event using your stored Google OAuth connection. |
| zerodb_github_create_issueB | Create a GitHub issue using your stored GitHub OAuth connection. |
| zerodb_notion_create_pageA | Create a Notion page using your stored Notion OAuth connection. |
| zerodb_plan_createA | Create a persistent plan, PRD, or task artifact in ZeroDB. Returns an artifact ID you can pass to zerodb_plan_get/update/history in future sessions. |
| zerodb_plan_getA | Retrieve a plan artifact by ID. Use this at session start to restore a plan from a previous session. |
| zerodb_plan_updateA | Update a plan artifact. Content changes are diffed and stored in version history automatically. |
| zerodb_plan_historyA | Get version history for a plan artifact. Returns list of diffs showing how the plan evolved. |
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 18 tools
Several memory retrieval tools (search_memory, semantic_search, synthesize_context) have overlapping objectives, differing mainly in input format and output granularity. The plan and external integration tools are clearly distinct, but the search variants create ambiguity for agents.
Most tools use a zerodb_ prefix, but the verb-noun pattern is inconsistent: store_memory is verb-first while plan_create and slack_send are noun-first. Semantic_search uses an adjective rather than a verb, further deviating from a consistent convention.
With 18 tools, the server offers a broad surface for memory management plus external integrations. While not excessive, the count is in the 16-25 borderline range and feels heavy for a memory-focused server.
Core memory operations (store, search, retrieve context, clear) are well covered, and plan artifacts include CRUD plus history. However, there is no plan delete or listing, no individual memory deletion, and external service integrations only expose a single action each, leaving notable gaps.