Today, we are excited to announce the release of the local Perses Model Context Protocol (MCP) Server in public beta. This MCP Server empowers AI Agents to understand, query and inteact with Perses APIs in a standardized and secure manner.
Imagine being able to prompt your favorite AI Agent to:
- "Show me the dashboards that are create in the last 10 days"
- "Can you tell me when 'Dashboard A' was last updated?"
- "What is the default Global Datasource"? s
This requires compl
The Model Context Protocol (MCP) is an open standard introduced by Anthropic that is rapidly gaining traction for connecting AI agents with diverse data sources. Its purpose is to allow LLMs to interact with the "outside world" beyond their training data, enabling real-time actions and information retrieval. It standardizes how context is brought into LLMs, allowing AI models to extend their functionality beyond their training data by accessing real-time information and executing specific tasks through standardized interfaces. Major players like Google, Microsoft, and OpenAI have already committed to supporting MCP.
As development progresses, more tools will be added to the MCP Server.
Getting Started with Perses MCP Server The Perses MCP Server, now available in public beta, is a powerful new addition to the observability toolkit. It is encouraged to explore its capabilities, integrate it with preferred LLM hosts, and experience the future of AI-powered observability firsthand.
Where to Find It: Perses MCP Server GitHub Repository: To delve into the code, review the full README.md, and begin with installation and configuration, visit:((https://github.com/perses/perses-mcp-server/blob/main/README.md)).
Perses Official Website: To learn more about the Perses observability application, its features, and documentation, visit: https://perses.dev/.
Perses CNCF Project Page: To understand Perses' role within the Cloud Native Computing Foundation ecosystem, visit: https://www.cncf.io/projects/perses/.
Model Context Protocol Servers Repository: To explore other reference and community-built MCP servers and grasp the full breadth of the protocol's capabilities, visit: https://github.com/modelcontextprotocol/servers.
Users can follow this guide to get started.