MCP Server MCP

Perenna

By github 👁 1 views ▲ 0 votes

A lightweight, Git-backed permanent memory for AI agents.

Homepage Verified source GitHub

Install

uvx perenna

Configuration Example

{
  "remotes": [],
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "perenna",
      "version": "0.2.0",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "packageArguments": [
        {
          "description": "Run the local MCP server over stdio",
          "value": "mcp",
          "type": "positional"
        },
        {
          "description": "Perenna data directory; defaults to ~/.perenna",
          "format": "filepath",
          "type": "named",
          "name": "--home"
        }
      ],
      "environmentVariables": [
        {
          "description": "Git remote name used for optional synchronization (for example, origin); leave unset for local-only operation",
          "name": "PERENNA_GIT_REMOTE"
        },
        {
          "description": "Embedding provider API key (optional; overrides a stored key; providers can also be configured via `vexor init`)",
          "isSecret": true,
          "name": "VEXOR_API_KEY"
        },
        {
          "description": "Remote reranker API key (optional; overrides a stored key; only needed when rerank is set to remote)",
          "isSecret": true,
          "name": "VEXOR_REMOTE_RERANK_API_KEY"
        },
        {
          "description": "Non-secret Vexor config as a JSON object, e.g. {\"provider\": \"gemini\", \"rerank\": \"bm25\"} (optional; merged over ~/.vexor/config.json; credential fields are rejected, use the dedicated variables)",
          "name": "VEXOR_CONFIG_JSON"
        }
      ]
    }
  ]
}

mcp model-context-protocol pypi