Skip to main content
Glama
KodyDennon

Statly Docs MCP Server

by KodyDennon
README.md
# Statly Docs MCP Server

Model Context Protocol server for Statly documentation. Enables AI agents to search and retrieve Statly SDK and API documentation.

## Installation

```bash
npm install statly-docs-mcp
```

## Usage with Claude Desktop

Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "statly-docs": {
      "command": "npx",
      "args": ["statly-docs-mcp"]
    }
  }
}
```

## Usage with Claude Code

```bash
claude mcp add statly-docs -- npx statly-docs-mcp
```

## Available Tools

### search_docs

Search Statly documentation for a topic.

```
query: "express integration"
```

### get_sdk_reference

Get SDK API reference for a specific language.

```
language: "javascript" | "python" | "go"
```

### get_code_example

Get a code example for a specific use case.

```
language: "javascript" | "python" | "go"
topic: "installation" | "init" | "capture_error" | "user_context" | "breadcrumbs"
```

### get_api_reference

Get REST API reference information.

## Resources

The server provides access to the llms.txt documentation:

```
uri: statly://docs/llms.txt
```

## Development

```bash
pnpm install
pnpm build
pnpm start
```

TDQS

B3.4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: get_api_reference for REST API details, get_code_example for code snippets, get_sdk_reference for language-specific SDKs, and search_docs for general documentation search. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with 'get_' or 'search_' prefixes and snake_case formatting. This uniformity (get_api_reference, get_code_example, get_sdk_reference, search_docs) makes the set predictable and easy to navigate, with no deviations in style.

Tool Count4/5

With 4 tools, the count is appropriate for a documentation-focused server, covering key areas like API references, code examples, SDKs, and search. It is slightly lean but reasonable, as each tool serves a distinct and essential function without feeling bloated or incomplete.

Completeness4/5

The tool set covers the core documentation domain well, including references, examples, and search. A minor gap exists in lacking update or management tools (e.g., for documentation content), but this is acceptable for a read-only documentation server, and agents can still perform typical lookup tasks effectively.