Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@memory-mcp show recent changes from the last 24 hours"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Persistent knowledge graph MCP server with SQLite backend. Drop-in replacement for the off-the-shelf mcp-server-memory (npm) — same tool signatures, but with graph traversal, fuzzy search, temporal queries, and timestamps.
Part of the Palimpsest intelligence fusion toolkit.
The npm mcp-server-memory stores everything in a flat JSONL file. Every operation reads the entire file into memory. No timestamps, no graph queries, keyword-only search.
This replaces it with SQLite (WAL mode) while maintaining JSONL export compatibility. Adds:
Graph traversal — traverse("shen-meta", depth=2) finds 46 connected nodes across 112 relations
Fuzzy search — trigram similarity for entity names (no more exact-case matching)
Temporal queries — recent(hours=24) shows everything added or modified
Timestamps — every entity, observation, and relation has created_at/updated_at
Case-insensitive search — search_nodes("project") matches ProjectX
Related MCP server: astra-knowledge-base-mcp
create_entities, create_relations, add_observations
delete_entities, delete_observations, delete_relations
search_nodes, open_nodes, read_graph
traverse(start_node, depth) — graph walk from a node, returns all entities within N hops
recent(hours) — entities/relations created or updated in the last N hours
search_similar(name, threshold) — trigram fuzzy matching for entity names
pip install -e .Reads from MEMORY_FILE_PATH (default: ~/.vibe/memory.jsonl). Stores in SQLite at MEMORY_DB_PATH (default: ~/.vibe/memory.db). On first run, auto-migrates existing JSONL into SQLite. All writes go to both stores.
Add new observations to existing entities in the knowledge graph.
Each item must have: entityName (str), contents (list[str]).
Inputs: observations (required). Returns: result
Create multiple new entities in the knowledge graph.
Each entity must have: name (str), entityType (str), observations (list[str]).
Inputs: entities (required). Returns: result
Create multiple new relations between entities in the knowledge graph.
Each relation must have: from (str), to (str), relationType (str).
Inputs: relations (required). Returns: result
Delete multiple entities and their associated relations from the knowledge graph.
Inputs: entityNames (required). Returns: result
Delete specific observations from entities in the knowledge graph.
Each item must have: entityName (str), observations (list[str] — exact content match).
Inputs: deletions (required). Returns: result
Delete multiple relations from the knowledge graph.
Each relation must have: from (str), to (str), relationType (str). If relationType is omitted, all relations between from and to are deleted.
Inputs: relations (required). Returns: result
Open specific nodes in the knowledge graph by their names.
Returns full entity details including all observations and timestamps.
Inputs: names (required). Returns: result
Read the entire knowledge graph.
Returns all entities with observations and all relations. Note: loads the full graph into memory — may be large.
Inputs: no named parameters. Returns: result
Return entities, relations, and observations created or updated in the last N hours.
Args: hours: Look-back window in hours (default 24, max 720)
Inputs: hours. Returns: result
Search for nodes in the knowledge graph.
Case-insensitive token match across entity names, types, and observation content. Returns matching entities with their observations.
Inputs: query (required). Returns: result
Fuzzy search for entity names using trigram similarity.
Args: name: Name to search for (fuzzy matched) threshold: Minimum similarity score 0.0–1.0 (default 0.3)
Inputs: name (required), threshold. Returns: result
Traverse the graph from a starting node, returning all entities within N hops.
Args: start_node: Entity name to start from depth: Number of hops to traverse (default 1, max 3)
Inputs: start_node (required), depth. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 12 tools
Each tool addresses a distinct operation: entity/relation/observation CRUD is clearly separated, and the query tools (search_nodes, open_nodes, read_graph, traverse, recent, search_similar) each serve a unique retrieval use case. Even similar-sounding searches like search_nodes and search_similar are differentiated by 'token match' vs 'fuzzy name similarity'. No two tools appear to perform the same function.
Most tools follow a clear verb_noun pattern (create_entities, delete_observations, read_graph, open_nodes). However, 'traverse' is a bare verb and 'recent' is a time-filter command rather than verb_noun, breaking the pattern slightly. Overall, the naming is readable and predictable enough for an agent to infer tool purposes.
With 12 tools, the server covers the full knowledge graph lifecycle (create, add, delete) plus a diverse set of query and traversal operations. This is a well-scoped count that is neither too sparse nor overwhelming. Each tool earns its place for a memory system.
The surface includes CRUD for entities, relations, and observations, plus retrieval via search, open, full-graph read, traversal, and recent-time filtering. The only notable gap is lack of an 'update entity' or 'update relation' operation, though this can be worked around with delete+create or add_observations. Overall, the domain coverage is strong.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Repository knowledge graph MCP server for codebase understanding and debugging.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
KnowMan MCP server: search, ask, save and read your Knowledge Base from any MCP client.