[ Confirm upstream transport MCP ]

How to Use Neo4j Agent Memory MCP Server with Bifrost

Memory management for AI agents using Neo4j knowledge graphs

[ MCP SERVER SUMMARY ]

Neo4j Agent Memory MCP server summary

Memory management for AI agents using Neo4j knowledge graphs Connect Neo4j Agent Memory through Bifrost MCP Gateway to centralize access control, virtual keys, and tool-call observability for your AI assistants.

Property	Details
Company	Upstream maintainer
Connection type	Confirm upstream transport
Authentication	Varies by upstream server
Package or endpoint	See upstream documentation
Capabilities	Neo4j Agent Memory tools over MCP, AI assistant connectivity, Governed tool access through Bifrost
Official documentation	Neo4j Agent Memory MCP documentation

Before you start

Review the Neo4j Agent Memory upstream documentation for its installation requirements
Obtain any credentials required by the upstream service
A running Bifrost MCP Gateway instance

What you can do with Neo4j Agent Memory

Memory management for AI agents using Neo4j knowledge graphs
Expose Neo4j Agent Memory tools to Claude, Cursor, and other MCP clients through one endpoint
Apply virtual keys, tool allowlists, and audit logging at the gateway

MCP ServerIntegration

[ HOW TO CONNECT ]

Connect Neo4j Agent Memory to Bifrost in three steps

Install Bifrost

Start the gateway locally or deploy in your VPC.

npx -y @maximhq/bifrost

Add Neo4j Agent Memory in MCP Gateway

Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and select the transport documented by the upstream server. Or register via the API below.

• Confirm the transport, command or endpoint, and authentication requirements in the Neo4j Agent Memory upstream documentation.

• Replace every placeholder in the example before sending the request.

Point clients at Bifrost /mcp

Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to Neo4j Agent Memory.

{
  "mcpServers": {
    "bifrost": {
      "url": "http://localhost:8080/mcp",
      "headers": {
        "Authorization": "Bearer vk_your_virtual_key"
      }
    }
  }
}

[ EXAMPLE CONFIG ]

Register Neo4j Agent Memory via API

Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.

# For a remote HTTP or SSE server:
curl -X POST http://localhost:8080/api/mcp/client \
  -H "Content-Type: application/json" \
  -d '{
    "name": "neo4j-agent-memory",
    "connection_type": "<http|sse>",
    "connection_string": "<upstream MCP endpoint>",
    "tools_to_execute": ["*"]
  }'

# For a local STDIO server:
curl -X POST http://localhost:8080/api/mcp/client \
  -H "Content-Type: application/json" \
  -d '{
    "name": "neo4j-agent-memory",
    "connection_type": "stdio",
    "stdio_config": {
      "command": "<upstream command>",
      "args": ["<arg>"]
    },
    "tools_to_execute": ["*"]
  }'

[ WHY BIFROST ]

Run Neo4j Agent Memory through one governed gateway

Access control

Virtual keys, RBAC, and tool allowlists per team or agent.

Cost governance

Attribute MCP tool spend alongside LLM usage in one view.

Observability

Log every tool call with latency, server, and virtual key metadata.

Credential isolation

Upstream secrets stay in the gateway — not on every laptop.

[ FAQ ]

Common questions

What does the Neo4j Agent Memory MCP server do?

Memory management for AI agents using Neo4j knowledge graphs The exact tools available depend on the upstream server version and configuration.

How do I connect Neo4j Agent Memory to Bifrost?

Check the upstream documentation to determine whether Neo4j Agent Memory uses STDIO, Streamable HTTP, or SSE. Then add it as an MCP client in Bifrost using the corresponding command or endpoint.