MCP Tools DirectoryAbout this integration
Shared, persistent memory for AI agents, with semantic recall and live updates.
- Transport
- stdio
- Authentication
- unknown
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.1.4
- Package
- montycat-mcp
- Last compatibility test
- Not independently tested
Connect your agent
montycat-mcpThe package can autostart a local engine; separately operated engines use a URI containing user/password credentials and optional TLS settings. Documentation and manifest were reviewed without starting an engine or executing the package.
Capabilities: Store and search persistent agent memory, Manage memory namespaces, Subscribe to shared-memory changes
Connected profiles
Additional details
io.github.MontyGovernance/montycat-mcp
Source ↗ · Checked 2026-09-171.1.4
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17montycat-mcp
Source ↗ · Checked 2026-09-191.1.5
Source ↗ · Checked 2026-09-19Publisher directs MCP clients to a stdio configuration using uvx.
Source ↗ · Checked 2026-09-19External engine connections use a username/password connection URI; scopes are documented as namespaces rather than security boundaries.
Source ↗ · Checked 2026-09-19Point the MCP client's stdio configuration at uvx montycat-mcp; MONTYCAT_URI overrides the autostarted local engine.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19