About this integration
MCP server for persistent, semantic memory across AI sessions
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.2
- Package
- collective-memory
- Last compatibility test
- Not independently tested
Connect your agent
collective-memoryPublisher README and package manifest reviewed. The stdio command, required OpenAI API key, and executable are documented; the package and external embedding service were not executed or security-audited.
Capabilities: Store persistent project-scoped memories, Search memories by semantic similarity, Classify and deduplicate stored memories
Connected profiles
Additional details
io.github.Hustada/collective-memory
Source ↗ · Checked 2026-09-170.1.2
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17OPENAI_API_KEY
Source ↗ · Checked 2026-09-17collective-memory
Source ↗ · Checked 2026-09-190.1.2
Source ↗ · Checked 2026-09-19The publisher documents a local stdio MCP server with embedded local storage and no separate database server requirement.
Source ↗ · Checked 2026-09-19OPENAI_API_KEY is required for the embedding calls used by the server.
Source ↗ · Checked 2026-09-19Configure the MCP client to run npx collective-memory over stdio and pass OPENAI_API_KEY in the child environment.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19