@houtini/seo-crawler-mcp 2.1.4 → 2.1.5

package/README.md

@@ -5,12 +5,21 @@
 [![Build Status](https://github.com/houtini-ai/seo-crawler-mcp/workflows/CI/badge.svg)](https://github.com/houtini-ai/seo-crawler-mcp/actions)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.3-blue?logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
 [![Type Definitions](https://img.shields.io/badge/types-included-blue)](https://www.npmjs.com/package/@houtini/seo-crawler-mcp)
-[![Known Vulnerabilities](https://snyk.io/test/github/houtini-ai/seo-crawler-mcp/badge.svg)](https://snyk.io/test/github/houtini-ai/seo-crawler-mcp)
 [![MCP Registry](https://img.shields.io/badge/MCP-Registry-blue?style=flat-square)](https://registry.modelcontextprotocol.io)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
 **Crawl and analyse your website for errors and issues that probably affect your site's SEO**
 
+<p align="center">
+  <a href="https://glama.ai/mcp/servers/@houtini-ai/seo-crawler-mcp">
+    <img width="380" height="200" src="https://glama.ai/mcp/servers/@houtini-ai/seo-crawler-mcp/badge" alt="SEO Crawler MCP server" />
+  </a>
+</p>
+
+> **Quick Navigation**
+>
+> [Installation](#installation) | [CLI mode](#cli-mode-terminal-usage) | [How to use](#how-to-use-this) | [What gets detected](#what-gets-detected) | [Data storage](#data-storage) | [Performance](#performance) | [Tools reference](#mcp-tools-reference) | [Available queries](#available-queries)
+
 I wanted to build on my experience working with the MCP protocol SDK to see just how far we can extend an AI assistant's capabilities. I decided that I'd quite like to build a crawler to check my site's "technical SEO" health and came across Crawlee - which seemed like the ideal library to base the crawl component of my MCP.
 
 What's interesting is that MCP usually indicates a server connection of some sort. This is not so with SEO Crawler MCP. The MCP protocol is probably more powerful than I realised - this is a self-contained application wrapped in the MCP SDK that handles everything locally:
@@ -69,6 +78,22 @@ Restart Claude Desktop. Four tools will be available:
 - `seo-crawler-mcp:query_seo_data`
 - `seo-crawler-mcp:list_seo_queries`
 
+### Claude Code (CLI)
+
+Claude Code uses a different registration mechanism -- it doesn't read `claude_desktop_config.json`. Use `claude mcp add` instead:
+
+```bash
+claude mcp add -e OUTPUT_DIR=/path/to/seo-audits -s user seo-crawler-mcp -- npx -y @houtini/seo-crawler-mcp
+```
+
+Verify with:
+
+```bash
+claude mcp get seo-crawler-mcp
+```
+
+You should see `Status: Connected`.
+
 ### Development Install
 
 ```bash

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@houtini/seo-crawler-mcp",
-  "version": "2.1.4",
+  "version": "2.1.5",
   "mcpName": "io.github.houtini-ai/seo-crawler-mcp",
   "description": "Crawl and analyse websites for SEO errors and issues using Crawlee with SQLite storage",
   "type": "module",

package/server.json

@@ -1,36 +1,36 @@
-{
-  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
-  "name": "io.github.houtini-ai/seo-crawler-mcp",
-  "description": "Crawl and analyse websites for SEO errors using Crawlee with SQLite storage",
-  "repository": {
-    "url": "https://github.com/houtini-ai/seo-crawler-mcp",
-    "source": "github"
-  },
-  "version": "2.1.3",
-  "packages": [
-    {
-      "registryType": "npm",
-      "identifier": "@houtini/seo-crawler-mcp",
-      "version": "2.1.3",
-      "transport": {
-        "type": "stdio"
-      },
-      "environmentVariables": [
-        {
-          "name": "OUTPUT_DIR",
-          "description": "Directory where crawl results are saved",
-          "isRequired": true,
-          "format": "string",
-          "isSecret": false
-        },
-        {
-          "name": "DEBUG",
-          "description": "Enable verbose debug logging (set to 'true' to enable)",
-          "isRequired": false,
-          "format": "string",
-          "isSecret": false
-        }
-      ]
-    }
-  ]
-}
+{
+  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
+  "name": "io.github.houtini-ai/seo-crawler-mcp",
+  "description": "Crawl and analyse websites for SEO errors using Crawlee with SQLite storage",
+  "repository": {
+    "url": "https://github.com/houtini-ai/seo-crawler-mcp",
+    "source": "github"
+  },
+  "version": "2.1.5",
+  "packages": [
+    {
+      "registryType": "npm",
+      "identifier": "@houtini/seo-crawler-mcp",
+      "version": "2.1.5",
+      "transport": {
+        "type": "stdio"
+      },
+      "environmentVariables": [
+        {
+          "name": "OUTPUT_DIR",
+          "description": "Directory where crawl results are saved",
+          "isRequired": true,
+          "format": "string",
+          "isSecret": false
+        },
+        {
+          "name": "DEBUG",
+          "description": "Enable verbose debug logging (set to 'true' to enable)",
+          "isRequired": false,
+          "format": "string",
+          "isSecret": false
+        }
+      ]
+    }
+  ]
+}