Koskamo

Engram MCP

Engram provides a universal memory layer for AI agents, enabling automatic extraction, consolidation, and bi-temporal recall of memories. It utilizes a local SQLite database with semantic vector search and a knowledge graph to offer superior recall accuracy and context awareness compared to flat file-based memory systems.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

Engram MCP logo, by tstockham96Community listingLocal stdioSource reviewed; not executedPublished by tstockham96
You need:npm install -g engram-sdkexport GEMINI_API_KEY=your-key-here
Vendor documentation

What you can do with it

  • Store and retrieve agent memories using semantic vector search
  • Consolidate memories automatically using LLM-powered extraction
  • Access bi-temporal versioning for historical context recall
  • Share memory vaults across multiple AI agents and projects

Source and maintenance

Community listingRegistry 0.5.1
mcp-registry: io.github.tstockham96/engram@0.5.1Source repository
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

engram-sdk 0.5.1

npm
engram-sdk package definition
{
  "version": "0.5.1",
  "transport": "stdio",
  "identifier": "engram-sdk",
  "registryType": "npm",
  "environmentVariables": [
    {
      "name": "GEMINI_API_KEY",
      "format": "string",
      "isRequired": true,
      "description": "Google Gemini API key for embeddings and LLM operations"
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "engram-mcp-engram-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "engram-sdk@0.5.1"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "engram-mcp-engram-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "engram-sdk@0.5.1"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "engram-mcp-engram-sdk": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "engram-sdk@0.5.1"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "engram-mcp-engram-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "engram-sdk@0.5.1"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}

Let your agent find its tools

Find servers like Engram MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,180