Perigon MCP Server is an MCP server that connects AI assistants to the Perigon news API for real-time news search and media monitoring. Media analysts, researchers, journalists, and intelligence teams use it to retrieve structured information from thousands of global publications without manual web scraping. The server enables LLMs to query live news stories, inspect article metrics, track coverage across specific journalists, and look up entities such as companies, politicians, and topics. It also provides tools to calculate aggregated sentiment metrics, track publication volume over time, and evaluate coverage spikes against historical baselines. Furthermore, the integration allows users to review automated news monitors, read event summaries, and receive topic newsletters directly inside MCP client environments like Claude and Cursor. Through curated tool profiles, clients can restrict server capabilities to specific tasks like research, monitoring, or platform management, keeping context windows focused and reducing unnecessary token usage during active investigative sessions.
Category: Communication & Messaging
Tags: aggregation, journalism, media, news, real-time
json { "mcpServers": { "perigon_news_api": { "url": "https://mcp.perigon.io/v1/mcp", "type": "http", "headers": { "Authorization": "Bearer YOUR_PERIGON_API_KEY" } } } } 4. If using Claude Code CLI, run: bash claude mcp add --transport http perigon_news_api https://mcp.perigon.io/v1/mcp --header "Authorization: Bearer YOUR_PERIGON_API_KEY" 5. For clients lacking native HTTP transport support, use npx -y mcp-remote@latest https://mcp.perigon.io/v1/mcp as outlined in the project repository.Part of MCP Servers
Perigon MCP Server is an official integration developed by the Perigon engineering team that provides MCP-compatible AI assistants with direct access to the Perigon news API. It lets language models query live articles, retrieve aggregated sentiment and publication statistics, and manage automated media monitoring feeds.
Perigon MCP Server is hosted remotely at https://mcp.perigon.io/v1/mcp. You do not need to install local code packages. Simply configure your MCP client to connect via Streamable HTTP with an Authorization header containing your Perigon API key, or use mcp-remote for clients without native HTTP support.
The server includes tools for searching articles and stories, retrieving journalist and source details, computing sentiment and volume trends, and inspecting coverage spikes for people and companies. It also provides tools for checking organization watchlists, custom source groups, and managing Perigon monitors.
You can append a tools query parameter to the server URL, such as ?tools=search_news_articles,search_news_stories. You can also specify predefined tool profiles like research, monitoring, platform, or minimal to load curated subsets and keep LLM context sizes small.
The server works with any client supporting the Model Context Protocol, including Claude Code CLI, Cursor, and other editors or agents. Clients supporting Streamable HTTP connect natively, while other clients can connect using the mcp-remote proxy.