Engram Memory
Engram MCP provides AI agents with reliable memory capabilities through explainable retrieval mechanisms, built by Lumetra as a streamable HTTP service. The server connects to Lumetra's hosted Engram service at engram.lumetra.io using API key authentication, enabling agents to store and retrieve information with transparent reasoning about why specific memories were surfaced. This implementation is valuable for AI systems that need persistent memory across conversations, knowledge management workflows, or applications requiring auditable retrieval decisions where understanding the basis for recalled information is critical.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/lumetra-io/engram-memory-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Engram Memory from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.