# Skeletable MCP server

> Allows AI agents to read, build, and propose changes to source-backed tables with verifiable citations and claim checks.

- Repository: https://github.com/eftpmc/skeletable
- Page: https://hostedmcp.org/servers/eftpmc/skeletable
- Transport: remote
- Stars: 0
- License: Apache-2.0
- Latest version: 1.0.0

## Install

### Claude Code

```sh
claude mcp add --transport http skeletable https://skeletable.com/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "skeletable": {
      "url": "https://skeletable.com/mcp"
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "skeletable": {
      "type": "http",
      "url": "https://skeletable.com/mcp"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"skeletable","type":"http","url":"https://skeletable.com/mcp"}'
```

### Codex

```sh
codex mcp add skeletable --url https://skeletable.com/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.skeletable]
url = "https://skeletable.com/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http skeletable https://skeletable.com/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "skeletable": {
      "url": "https://skeletable.com/mcp",
      "type": "http"
    }
  }
}
```

## FAQ

### Does reading tables require an account?

No, reading tables does not require an account, but proposing changes or building drafts requires a Bearer token from Settings.

### Can I use Skeletable to create datasets?

Yes, a table where proof is optional is considered a dataset, allowing values to record origins from pages, people, files, or models.

### How does the AI column functionality work?

AI columns use instructions to classify or process data; the agent provides answers through specific tools, and Skeletable records the model and prompt fingerprint used.
