Skip to main content

MCP server exposing Z3rno memory operations as tools for Claude Desktop, Cursor, and other MCP clients.

Project description

z3rno-mcp

MCP (Model Context Protocol) server that exposes Z3rno memory operations as tools. Gives any MCP-compatible AI client (Claude Desktop, Cursor, Windsurf, etc.) the ability to store, recall, forget, and audit agent memories.

Tools

Tool Description
z3rno.store Store a memory (fact, preference, decision, etc.)
z3rno.recall Semantic search over stored memories
z3rno.forget Soft delete or GDPR-compliant hard delete
z3rno.audit Query the audit log of memory operations

Installation

# With uv (recommended)
uv pip install z3rno-mcp

# With pip
pip install z3rno-mcp

Configuration

Set environment variables:

Variable Required Default Description
Z3RNO_API_KEY Yes Your Z3rno API key
Z3RNO_BASE_URL No https://api.z3rno.dev Z3rno server URL
Z3RNO_AGENT_ID No Default agent ID (can be overridden per-call)

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "z3rno": {
      "command": "z3rno-mcp",
      "env": {
        "Z3RNO_API_KEY": "z3rno_sk_...",
        "Z3RNO_AGENT_ID": "my-agent"
      }
    }
  }
}

If installed via uv, use the full path:

{
  "mcpServers": {
    "z3rno": {
      "command": "uv",
      "args": ["run", "z3rno-mcp"],
      "env": {
        "Z3RNO_API_KEY": "z3rno_sk_...",
        "Z3RNO_AGENT_ID": "my-agent"
      }
    }
  }
}

Cursor

Add to your .cursor/mcp.json:

{
  "mcpServers": {
    "z3rno": {
      "command": "z3rno-mcp",
      "env": {
        "Z3RNO_API_KEY": "z3rno_sk_...",
        "Z3RNO_AGENT_ID": "my-agent"
      }
    }
  }
}

Claude Code

claude mcp add z3rno -- z3rno-mcp

Then set environment variables in your shell profile or .env.

Local Development

# Clone and install
git clone https://github.com/the-ai-project-co/z3rno-mcp.git
cd z3rno-mcp
uv sync --dev

# Run directly
Z3RNO_API_KEY=z3rno_sk_test Z3RNO_BASE_URL=http://localhost:8000 uv run z3rno-mcp

# Lint and format
uv run ruff check .
uv run ruff format .

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

z3rno_mcp-0.1.0.tar.gz (74.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

z3rno_mcp-0.1.0-py3-none-any.whl (8.3 kB view details)

Uploaded Python 3

File details

Details for the file z3rno_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: z3rno_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 74.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for z3rno_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dab7635159b1a26a9b31b2e4ea5fc58fe3cf5f0f63027d0d5f96bd13939f39d5
MD5 7faa647c5fcc5e5c331f5e51a429c587
BLAKE2b-256 94d2193835943dfc634eac6e5224e37f9e45b814cc17bd820d62ad53e01d22da

See more details on using hashes here.

File details

Details for the file z3rno_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: z3rno_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 8.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for z3rno_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7b29e40ee0199090dbb09fbef8f08dc70cffb8ef1630eb2dfe84630c581b25e3
MD5 45deebe99f1a7ee6896173ab93af10a9
BLAKE2b-256 ff1a8c04a786a33d915f19624b7984d449f5fe308f1120a7443f8cf9019ab0ce

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page