# Clark MCP Server

> Use this tool when you need to enable personal agents to store and retrieve various types of memory, such as profile, factual, episodic, and procedural data. The Clark MCP Server provides a memory layer for MCP-compatible agents, solving problems related to knowledge retention and recall. It accepts input from agents and outputs stored memory data, ideal for use cases requiring persistent memory management in AI systems.

Canonical page: https://skillsregistry.net/skills/nomads-ai-lab-clark  
JSON: https://api.skillsregistry.net/v1/skills/nomads-ai-lab-clark

## Description

Provides a memory layer for personal agents, enabling MCP-compatible agents to store and query profile, factual, episodic, and procedural memory.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/il9yovdnjf)
- **Repository:** <https://github.com/NomadsResearch/clark>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "nomads-ai-lab-clark"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nomads-ai-lab-clark` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nomads-ai-lab-clark/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt