At a Glance
| Type | Name | What it does | Who uses it |
|---|---|---|---|
| Tool | add_memory | Save context to long-term memory | Agent calls automatically when it learns something worth remembering |
| Tool | search_memory | Search past memories by meaning | Agent calls when past context would help its response |
| Tool | get_current_date | Get current date and time in a timezone | Agent calls before date-filtered memory search |
| Resource | membase://profile | Read-only user settings profile | Agent reads when stable profile context matters |
| Resource | membase://recent | Read-only recent memory timeline | Agent reads for latest updates and recency checks |
| Prompt | start | Guidance for memory workflow and safety | Agent can load at session start |
MCP Server
Membase runs a remote MCP server accessible at:| Property | Value |
|---|---|
| Transport | Streamable HTTP |
| Authentication | OAuth (browser-based) |
| Package | membase (npm) |
npx -y membase@latest --client <client> CLI command handles registration and auth automatically for supported clients. See the Agents guide for per-client setup.
Tools
Membase exposes 3 tools that agents can call during conversations:add_memory
add_memory
Stores long-term memory that persists across sessions. Agents use this proactively when the user shares durable context worth remembering: preferences, recurring habits, ongoing projects, goals, constraints, etc. Transient one-off information is skipped unless the user explicitly asks to save it.
| Parameter | Type | Required | Description |
|---|---|---|---|
content | string (max 50,000 chars) | Yes | The memory content to store |
metadata | object | No | Optional metadata for categorization (e.g., tags, source) |
search_memory
search_memory
Searches stored memories by semantic similarity. Agents use this when the user asks to recall something from a previous session, or proactively when past context would improve their response. Results are returned as episode-centric bundles with related context.
Each result includes a relevance score (0–1) indicating how closely it matches the query.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string (max 1,000 chars) | Yes | Natural-language search query. Use empty string to fetch recent memories. |
limit | integer (1-30) | No | Max results to return (default: 20) |
limit | integer (1-30) | No | Max results to return (default: 20) |
offset | integer | No | Pagination offset (default: 0) |
date_from | ISO date/datetime string | No | Inclusive lower bound for date filtering |
date_to | ISO date/datetime string | No | Inclusive upper bound for date filtering |
timezone | IANA timezone string | No | Date-only parsing timezone, for example America/Los_Angeles |
sources | array of strings | No | Filter by source (e.g. ["slack", "gmail", "google-calendar"]). If omitted, all sources are searched. |
get_current_date
get_current_date
Returns the current UTC timestamp. This helps agents resolve ambiguous expressions such as “today”, “this weekend”, or “next week” before building date filters.This tool takes no input parameters.
Resources
MCP resources provide read-only data that agents can pull into their context:| Resource | URI | Description |
|---|---|---|
| User Profile | membase://profile | User settings payload (display_name, role, interests, instructions, timezone) |
| Recent Memories | membase://recent | Top 10 recent memories sorted by captured_at (created_at) descending, with event_at (valid_at) when available |
Prompts
MCP prompts inject pre-built instructions and context into the agent’s system prompt:| Prompt | Description |
|---|---|
| start | Teaches the agent when to use search_memory, when to use resources, when to save memory, and what to avoid storing. |
start prompt can be used at session start to provide:
- Workflow guidance for memory retrieval and memory write behavior
- Safety guidance for secrets and transient information
- Resource usage guidance for profile versus recent timeline reads
Recommended Agent Behavior
Use these patterns for best results:- For personal recall questions, call
search_memoryfirst. - For stable user profile context, read
membase://profile. - For latest updates or “what changed” questions, read
membase://recent. - For date-filtered searches, call
get_current_dateand then pass explicit date filters tosearch_memory. - Save durable user context with
add_memory, and skip secrets or one-off transient data unless explicitly requested.
Connection Setup
For detailed setup instructions for each agent, see the Agents guide.Cursor
One-click install
Claude Desktop
CLI command
ChatGPT
Manual config
Next Steps
Dashboard
Explore and manage memories visually.
Memory Management
Learn how memories are created and updated.