← Index

Tentra — Memory for AI Coding Agents

io.github.rdanieli/tentra·v1.3.2·Memory & RAG
Quality Score
90
/100

Memory for AI coding agents. Call graphs + refactor safety + persistent code context. 35 MCP tools.

§01  Install
Remote endpoint

Streamable HTTP / SSE endpoint. Add to any MCP client that supports remote servers.

https://trytentra.com/api/mcp
Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "tentra": {
      "command": "npx",
      "args": [
        "-y",
        "tentra-mcp"
      ],
      "env": {
        "TENTRA_API_KEY": "<your-tentra_api_key>"
      }
    }
  }
}
Cursor (.cursor/mcp.json)
{
  "mcpServers": {
    "tentra": {
      "command": "npx",
      "args": [
        "-y",
        "tentra-mcp"
      ],
      "env": {
        "TENTRA_API_KEY": "<your-tentra_api_key>"
      }
    }
  }
}
Cline (cline_mcp_settings.json)
npx -y tentra-mcp
§02  Environment variables
TENTRA_API_KEY
secret

Tentra API key (optional — device flow auth via GitHub is used by default)

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
10
§04  Alternatives in Memory & RAG