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 me recent entities added in 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: server-memory
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 targets a distinct operation: create/delete entities, add/delete observations, create/delete relations, search via token match vs fuzzy name match, open specific nodes vs read full graph vs traverse vs recent. The descriptions clearly differentiate similar-sounding tools like search_nodes and search_similar.
The naming predominantly follows a verb_noun snake_case pattern (create_entities, delete_relations, search_nodes). Minor deviations exist with 'recent' and 'traverse' which are single-word verbs, but they are still descriptive and do not disrupt overall consistency.
With 12 tools, the server is well-scoped for a knowledge graph memory system. Each tool serves a clear purpose, and the count is within the ideal range for a domain-specific MCP server.
The tool set provides comprehensive coverage for managing a knowledge graph: create/delete entities, add/delete observations, create/delete relations, multiple retrieval methods (specific, full graph, traversal, recent, search), and fuzzy search. Update operations are supported via add/delete observations and create/delete relations, covering the full lifecycle without dead ends.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
KnowMan MCP server: search, ask, save and read your Knowledge Base from any MCP client.