About ainative-memory-mcp
ainative-memory-mcp is a cloud-backed knowledge graph memory server for MCP clients. It adds semantic search and automatic ZeroDB provisioning to the server-memory tool set.
Key features
- 01Cloud-persisted knowledge graph
- 02Semantic vector search
- 03Entity and relation management
- 04Automatic ZeroDB provisioning
- 05Cross-device access with shared API key
Use cases
- 01Retaining project facts across devices
- 02Finding entities by meaning rather than exact wording
- 03Replacing local server-memory storage
- 04Starting memory storage without existing credentials
MCP support
It exposes knowledge-graph operations and semantic search as tools for MCP clients, including the nine server-memory tools and an additional semantic search tool.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
10Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| entities | array | Yes | Array of entities to create |
Details
From the project READMEainative-memory-mcp
Enhanced MCP knowledge graph memory server with cloud persistence and semantic search. Drop-in replacement for @modelcontextprotocol/server-memory.
Why this instead of server-memory?
| Feature | server-memory | ainative-memory-mcp |
|---|---|---|
| Storage | Local JSONL file | ZeroDB cloud |
| Persistence | Lost on machine wipe | Survives forever |
| Cross-device | No | Yes (same API key = same graph) |
| Semantic search | No (text match only) | Yes (vector similarity) |
| Setup | Manual file path | Auto-provisions on first run |
| Sharing | Copy files around | Share API key |
Quick Start
Claude Desktop / Claude Code
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "ainative-memory-mcp"],
"env": {
"ZERODB_API_KEY": "ak_your_key"
}
}
}
}
No API key? Just omit it — a free ZeroDB instance is auto-provisioned on first run.
Cursor / Windsurf / VS Code
Same config in your .mcp.json:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "ainative-memory-mcp"],
"env": {
"ZERODB_API_KEY": "ak_your_key"
}
}
}
}
Get an API Key
npx zerodb-cli init
Or sign up at ainative.studio.
Tools (10)
All 9 original server-memory tools plus semantic search:
Original Tools
| Tool | Description |
|---|---|
create_entities | Create new entities with name, type, and observations |
create_relations | Create directed relations between entities |
add_observations | Add observations to existing entities |
delete_entities | Delete entities and their cascading relations |
delete_observations | Remove specific observations from entities |
delete_relations | Delete specific relations |
read_graph | Read the entire knowledge graph |
search_nodes | Search by text match (name, type, observations) |
open_nodes | Fetch specific entities by name with their relations |
New Tool
| Tool | Description |
|---|---|
search_nodes_semantic | Vector similarity search — find entities by meaning, not just exact text |
Semantic Search Example
The original search_nodes only finds exact text matches. search_nodes_semantic understands meaning:
search_nodes("ML frameworks") -> might find nothing
search_nodes_semantic("ML frameworks") -> finds "PyTorch", "TensorFlow", "JAX"
Environment Variables
| Variable | Required | Description |
|---|---|---|
ZERODB_API_KEY | No* | ZeroDB API key (auto-provisions if missing) |
ZERODB_PROJECT_ID | No | ZeroDB project ID |
ZERODB_API_URL | No | API URL (default: https://api.ainative.studio) |
*If no credentials are provided, a free instance is automatically provisioned on first run.
Auto-Provisioning
On first run without credentials:
- A free ZeroDB instance is provisioned automatically
- Credentials are saved to
.mcp.jsonand.envin your project - A claim URL is printed so you can take ownership of the instance
- Everything works immediately — no signup required
How It Works
Instead of writing to a local memory.jsonl file, this server:
- Entities are stored as rows in a ZeroDB NoSQL table (
kg_entities) - Relations are stored in a separate table (
kg_relations) - Vector embeddings are automatically generated for each entity via ZeroMemory, enabling semantic search
- All data persists in the cloud and is accessible from any device with the same API key
Migration from server-memory
- Replace
@modelcontextprotocol/server-memorywithainative-memory-mcpin your MCP config - Add
ZERODB_API_KEYto your env (or let it auto-provision) - Re-create your entities (one-time migration — your old JSONL data stays on disk)
License
MIT
Powered by ZeroDB + AINative
This package is part of the AINative ecosystem — the AI-native developer platform.
Why ZeroDB?
| Feature | ZeroDB | Others |
|---|---|---|
| Vector search | Built-in, free embeddings | Separate service (Pinecone, Qdrant) |
| Agent memory | Cognitive memory with decay + reflection | DIY or Mem0 ($$$) |
| File storage | S3-compatible, included | Separate S3 bucket |
| NoSQL tables | Instant, schema-free | MongoDB Atlas, DynamoDB |
| PostgreSQL | Managed, pgvector pre-installed | Neon, Supabase ($$$) |
| Serverless functions | DB-event triggered | Firebase/Supabase Edge |
| Pricing | Free tier, no credit card | Pay-per-query from day 1 |
Get Started Free
npx zerodb-cli init # Auto-configures your IDE
Or sign up at ainative.studio — free tier, no credit card required.
Zero-Config Auto-Provisioning
No account needed to start. On first run, this package automatically:
- Provisions a free ZeroDB instance (~800ms)
- Saves credentials locally (
.env,.mcp.json) - Prints a claim link in your terminal
The 72-Hour Window
Your auto-provisioned instance is free for 72 hours. To keep your data permanently, visit the claim URL printed in your terminal.
For AI Agents
If a coding agent (Claude Code, Cursor, Windsurf) installs this package:
- Auto-provisions without human intervention
- The claim URL appears in agent output — visit it to take ownership
.claude/CLAUDE.mdinstructs agents to surface the claim link to you- Check
.envor~/.ainative/config.jsonfor your project ID if you miss it
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.