Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "editlens-mcp": {
      "command": "uvx",
      "args": [
        "editlens-mcp"
      ]
    }
  }
}

Or install with pip: pip install editlens-mcp

README Excerpt

Local estimates of AI editing magnitude, with a durable store for comparing and recovering drafts. Windows, macOS and Linux; Python 3.10 or newer. The default checkpoint is a four-bucket RoBERTa classifier. Independent MCP clients share one local inference worker per matching environment and configuration. Requests queue behind one model.

Tools (20)

EDITLENS_BACKENDEDITLENS_BASE_MODELEDITLENS_BATCH_SIZEEDITLENS_CHECKPOINTEDITLENS_DBEDITLENS_DEVICEEDITLENS_DTYPEEDITLENS_IDLE_UNLOADEDITLENS_PREPROCESSEDITLENS_REQUEST_TIMEOUTEDITLENS_REVISIONEDITLENS_RUNTIME_DIREDITLENS_STARTUP_TIMEOUTEDITLENS_TRANSPORTEDITLENS_USE_CURRENT_PYTHONEDITLENS_WORKER_IDLEchain_assemblechain_createchain_deletechain_get_text

editlens-mcp

Quick Install

README Excerpt

Tools (20)

Related AI/LLM Servers