Care MCP Server

Care Membrane MCP Server by MEOK AI Labs

Local serverstdioPython

What is the Care MCP server?

Care Membrane MCP Server by MEOK AI Labs. The care mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 8 defined tools rather than through you.

What it actually does

AI Safety evaluation toolkit: care scoring, threat detection, burnout analysis, relationship prediction, and care membrane probe framework.

Its toolset

Everything the assistant can do here goes through one of these:

  • validate_care — Score text against care-centered alignment principles (0-100)
  • detect_threats — Detect jailbreak attempts, prompt injection, and PII extraction
  • analyze_care_patterns — Detect burnout risk and relationship health imbalances
  • predict_relationship_evolution — Predict relationship evolution over the next 30 days
  • evaluate_care_membrane — Evaluate responses against the 16-probe Care Membrane framework
  • get_care_probes — List all 16 Care Membrane probes with categories
  • quick_check — Paste any AI response, get instant care score + threat detection. No API key needed.
  • what_is_care_membrane — Explains the 16-probe Care Membrane framework. No parameters needed.

Adding it to your client

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

When to reach for it

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Care's toolset — validate_care, detect_threats, analyze_care_patterns and 5 more — is a fair guide to whether it matches your workflow. It is maintained by CSOAI-ORG; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the care mcp server does with a few real requests.

Available tools

ToolWhat it does
validate_careScore text against care-centered alignment principles (0-100)
detect_threatsDetect jailbreak attempts, prompt injection, and PII extraction
analyze_care_patternsDetect burnout risk and relationship health imbalances
predict_relationship_evolutionPredict relationship evolution over the next 30 days
evaluate_care_membraneEvaluate responses against the 16-probe Care Membrane framework
get_care_probesList all 16 Care Membrane probes with categories
quick_checkPaste any AI response, get instant care score + threat detection. **No API key needed.**
what_is_care_membraneExplains the 16-probe Care Membrane framework. **No parameters needed.**

How to install the Care MCP server

## Claude Desktop Config

```json
{
  "mcpServers": {
    "care-membrane": {
      "command": "python",
      "args": ["server.py"],
      "cwd": "/path/to/care-membrane-mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Care to validate care.
  • Use Care to detect threats.
  • Use Care to analyze care patterns.

Frequently asked questions

It connects Care to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (validate_care, detect_threats, analyze_care_patterns, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Care directly.