Model Context Protocol (MCP) Setup & Integration Guide

## Model Context Protocol (MCP) Setup Guide The Model Context Protocol (MCP) is the open standard created by Anthropic that connects AI assistants to external tools and data sources. With ESER AI's MCP Server, you can give Claude, Cursor, and AI coding agents direct, authorized control over your social media publishing pipelines. --- ### Installation by Client #### 1. Claude Desktop Configuration Open your Claude Desktop configuration file: - **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows:** `%APPDATA%\Claude\claude_desktop_config.json` - **Linux:** `~/.config/Claude/claude_desktop_config.json` Add the following block under `mcpServers`: ```json { "mcpServers": { "eser-ai": { "command": "npx", "args": ["-y", "@eser-ai/mcp-server"], "env": { "ESER_AI_API_KEY": "eser_api_YOUR_COPIED_KEY_HERE" } } } } ``` Restart Claude Desktop. A hammer icon will appear in the bottom-right corner showing active ESER AI tools! #### 2. Cursor IDE Integration 1. Open Cursor Settings -> **Features** -> **MCP Servers**. 2. Click **Add New MCP Server**. 3. Name: `eser-ai` | Type: `command` | Command: `npx -y @eser-ai/mcp-server`. 4. Set Environment Variable: `ESER_AI_API_KEY=eser_api_YOUR_KEY`. #### 3. Claude Code CLI Integration Run the command: ```bash claude mcp add eser-ai npx -y @eser-ai/mcp-server --env ESER_AI_API_KEY=eser_api_YOUR_KEY ``` --- ### Available MCP Tools Exposed 1. `eser_list_social_accounts`: Returns all connected accounts, platform IDs, handles, and connection states. 2. `eser_create_post`: Composes a multi-platform post draft with custom platform text and optional media storage keys. 3. `eser_schedule_post`: Places a post draft into the next optimal queue slot or a specific datetime. 4. `eser_ingest_source`: Ingests an article URL, whitepaper, or text document and extracts thesis takeaways. 5. `eser_get_post_status`: Retrieves publishing receipts, platform live URLs, and error logs for any post ID. 6. `eser_get_analytics`: Fetches engagement metrics (views, likes, reposts, comments) for published posts.