# Basalt MCP

> Use this tool when you need to securely integrate AI models with Obsidian vaults, protecting your local filesystem from potential threats. Basalt MCP enables safe interaction through sandboxed file operations and todo tracking, with strict validation layers and resource limits. It is ideal for use cases requiring robust security and isolation, such as sensitive data processing or untrusted tool integration.

Canonical page: https://skillsregistry.net/skills/cmillstead-basalt-mcp  
JSON: https://api.skillsregistry.net/v1/skills/cmillstead-basalt-mcp

## Description

A security-hardened MCP server that enables AI models to safely interact with Obsidian vaults through sandboxed file operations and todo tracking. It implements strict validation layers and resource limits to protect the local filesystem from potentially hostile tool calls.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/blkhik3iu9)
- **Repository:** <https://github.com/cmillstead/basalt-mcp>

## 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": "cmillstead-basalt-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cmillstead-basalt-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cmillstead-basalt-mcp/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