MCP.Market

Ainative Memory MCP server

by AINative-Studio·io.github.AINative-Studio/ainative-memory-mcp·v1.0.1
No reviews yet

Cloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed by ZeroDB.

A89/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

0 stars269 downloads/wk

Reviews

Write one

Nobody has reviewed Ainative Memory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Ainative Memory tools (10, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_observations

    Add new observations to existing entities in the knowledge graph.

  • create_entitieswrite action

    Create multiple new entities in the knowledge graph. Entities are the fundamental nodes with a name, type, and list of observations. Stored in ZeroDB cloud — persists across sessions and devices.

  • create_relationswrite action

    Create multiple new relations between entities in the knowledge graph. Relations should be in active voice.

  • delete_entitieswrite action

    Delete multiple entities and their associated relations from the knowledge graph.

  • delete_observationswrite action

    Delete specific observations from entities in the knowledge graph.

  • delete_relationswrite action

    Delete multiple relations from the knowledge graph.

  • open_nodes

    Open specific nodes in the knowledge graph by their names.

  • read_graph

    Read the entire knowledge graph from ZeroDB cloud storage.

  • search_nodes

    Search for nodes in the knowledge graph based on a text query. Matches against entity names, types, and observation content (case-insensitive substring match).

  • search_nodes_semantic

    Search for nodes in the knowledge graph using semantic vector similarity. Unlike search_nodes which does exact text matching, this finds entities by meaning — e.g., searching "machine learning frameworks" would find entities about "PyTorch" or "TensorFlow" even without those exact words.

Public scan report

scanner v0.1.10 · 2026-11-05 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 41 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Ainative Memory compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 85% of 3,443 Web search servers
Tools
10
the typical Web search server has 5
Tools that change things
50%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
269
more than 74% of 994 Web search servers with a package

What its tools let an agent do: 3 read · 4 create · 3 delete

Install Ainative Memory in Claude Code, Cursor or VS Code

Runs npx -y ainative-memory-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add ainative-memory-mcp -- npx -y ainative-memory-mcp
Add to Cursor

What the publisher says

From the Ainative Memory repository's README, as published. We do not edit it. Read it on GitHub

ainative-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?

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

New Tool

Semantic Search Example

The original searchnodes only finds exact text matches. searchnodes_semantic understands meaning:

search_nodes("ML frameworks")        -> might find nothing
search_nodes_semantic("ML frameworks") -> finds "PyTorch", "TensorFlow", "JAX"

Environment Variables

*If no credentials are provided, a free instance is automatically provisioned on first run.

Auto-Provisioning

On first run without credentials:

  1. A free ZeroDB instance is provisioned automatically
  2. Credentials are saved to .mcp.json and .env in your project
  3. A claim URL is printed so you can take ownership of the instance
  4. Everything works immediately — no signup required

How It Works

Instead of writing to a local memory.jsonl file, this server:

  1. Entities are stored as rows in a ZeroDB NoSQL table (kg_entities)
  2. Relations are stored in a separate table (kg_relations)
  3. Vector embeddings are automatically generated for each entity via ZeroMemory, enabling semantic search
  4. All data persists in the cloud and is accessible from any device with the same API key

Migration from server-memory

  1. Replace @modelcontextprotocol/server-memory with ainative-memory-mcp in your MCP config
  2. Add ZERODBAPIKEY to your env (or let it auto-provision)
  3. Re-create your entities (one-time migration — your old JSONL data stays on disk)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Ainative Memory: common questions

Is Ainative Memory MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Ainative Memory safety report
How do I install Ainative Memory?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Ainative Memory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Ainative Memory maintained?
The last commit was 52 days ago (2026-09-25). The latest release is v1.0.1.
What can I use instead of Ainative Memory?
Servers from other publishers that do the same job: Octobrain MCP server, Marm MCP server and Shodh Memory MCP server.
How does Ainative Memory compare with other Web search MCP servers?
safety score 89/100 (higher than 85% of 3,443 Web search servers); tools 10 (the typical Web search server has 5); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Ainative Memory

Same job from other publishers: the closest match first, then the best rated.

  • Octobrain
    Persistent memory for AI assistants with semantic search and knowledge graph relationships.
    More from Muvon →
    A
  • Marm
    Universal MCP Server with advanced AI memory capabilities and semantic search.
    A
  • Shodh Memory
    Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
    C
  • M3 Memory
    Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.
    A
  • Ori Memory
    Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.
    A

More from AINative-Studio →