SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
A SQLite-backed MCP server for persistent memory storage, full-text retrieval, and relationship graph traversal.
Memory MCP provides a local, persistent memory layer for MCP-enabled assistants. It stores SHA-256-addressed memory items in SQLite with FTS5-powered full-text search, a directed relationship graph, BFS recall traversal, and token-budget-aware context retrieval β all accessible over stdio transport with no external dependencies.
retrieve_context) selects memories that fit a caller-specified token budget β no manual pagination needed.internal://instructions (Markdown guide) and memory://memories/{hash} URI template with hash auto-completion.SIGINT, SIGTERM) and no HTTP endpoints. |>=24.Use the npm package directly with npx β no installation required:
[!TIP] The server uses stdio transport only; no HTTP endpoint is exposed. Stdout must not be polluted by custom logging.
Or run with Docker:
claude_desktop_config.json:
CLI:
MCP config:
MCP client config:
src/ must update README.md and affected mcp/ mirror pages in the same PR.https://modelcontextprotocol.io/specification/2025-11-25/... links for protocol references; avoid latest and mixed legacy targets.src/server.ts.src/tools/index.ts, src/resources/index.ts, and src/prompts/index.ts.src/instructions.md match runtime behavior.npm run type-check, npm run test:fast, npm run build.| Tool | Category | Notes |
|---|---|---|
store_memory | Write | Idempotent by content+sorted tags hash |
store_memories | Write | Batch (1β50), transaction-wrapped |
get_memory | Read | Hash lookup |
update_memory | Write | Returns old_hash + new_hash |
delete_memory | Write | Cascades relationship deletion |
delete_memories | Write | Batch (1β50), transaction-wrapped |
search_memories | Read | FTS5 + importance/type filters + cursor |
create_relationship | Write | Idempotent directed edge creation |
delete_relationship | Write | Deletes exact directed edge |
get_relationships | Read | Direction filter + linked memory fields |
recall | Read | FTS5 seed + BFS traversal (depth 0β3) |
retrieve_context | Read | Token-budget-aware context retrieval |
memory_stats | Read | Store aggregates and type breakdown |
store_memoryStore a new memory with content, tags, and optional type/importance. Idempotent β storing the same content+tags returns the existing hash with created: false.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
content | string | Yes | β | Memory content (1β100000 chars) |
tags | string[] | Yes | β | 1β100 tags, each max 50 chars, no whitespace |
memory_type | enum | No | general | general, fact, plan, decision, reflection, lesson, error, gradient |
importance | integer | No | 0 | Priority 0β10 |
Returns: { hash, created }
store_memoriesStore multiple memories in one transaction (max 50 items).
| Name | Type | Required | Description |
|---|---|---|---|
items | Array<StoreMemoryItem> | Yes | 1β50 items, each with content, tags, optional memory_type, optional importance |
Returns: { items, succeeded, failed }
get_memoryRetrieve one memory by its SHA-256 hash.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/memory-mcp-server)<a href="https://allmcps.com/mcp/memory-mcp-server"><img src="https://allmcps.com/api/badge/memory-mcp-server?style=directory" alt="Memory MCP Server on AllMCPs" /></a>