MCP Server

Interact with Panther's API using conversational AI

Overview

The Panther Model Context Protocol (MCP) server enables natural language interactions with Panther in your MCP client of choice. Whether you're an analyst investigating alerts, a detection engineer writing rules in Cursor, or a CISO seeking metrics and quick insights, the MCP server lets you work with the Panther API using conversational AI.

The Panther MCP server democratizes Panther access to users across your organization—imagine not having to know how to program in Python to write a rule, or not needing a query language like SQL or PantherFlow to search data.

For example, you can use the Panther MCP server for:

• Detection engineering: Generate rules based on real logs in your data lake, using clients like Cursor.

  • In Cursor, "Create a rule to monitor when AWS admins are created in account 333333444444"

• Alert triage: Review and correlate many alerts generated within a given time period.

  • In Claude for Desktop, "Show me all medium+ alerts from the last 24 hours grouped by IP"

• Threat investigation: Query your security logs and investigate anomalies.

  • In Claude for Desktop, "Query AWS CloudTrail logs for failed login attempts in the last day."

• Panther operations: Expedite the resolution of operational issues end-to-end, such as rule errors or system errors.

  • In Claude for Desktop, "Generate a report of our top 10 rules by alert volume this month"

The Panther MCP server includes tools for working with a number of entities, like alerts, data, rules, data models, schemas, metrics, and Panther users. Learn more about these tools in the Available Tools section in the mcp-panther repository's README.

The Panther MCP server is open-source—see the contribution guidelines here. If you find a bug in the MCP server or need extra support while using it, please create an issue in the repository.

Use of Panther MCP features is subject to the AI disclaimer found on the Legal page.

Using the MCP workflow

1. Install the MCP server in your client of choice (e.g., Claude for Desktop).

   • You can install the Panther MCP server locally using docker or uvx. For full instructions, see the MCP Server Installation section of the README.

2. Ask a Panther-relevant question or provide a prompt (e.g., "Write a detection for suspicious S3 bucket access").

3. Your client uses mcp-panther's tools to interact with Panther's APIs and gather necessary data.

4. Your client uses the response from mcp-panther to answer your question or execute the action you requested.

Securing your MCP server

To safely use the Panther MCP server, it's strongly recommended to follow the guidelines in the Security Best Practices section in the mcp-panther repository's README.

The Panther MCP server vs. Panther AI

The Panther MCP server and Panther AI both allow you to interact with your Panther instance with AI using free-form prompts, but there are a few key differences:

	Panther MCP server	Panther AI
Primary use case	Detection engineering, cross-tool workflows, ad-hoc investigations, custom internal agent creation	Guided alert triage and incident response
Access method	MCP clients like Cursor, Claude for Desktop, and Goose	Panther Console (and API, for Cloud Connected customers)
Integration capability	Works alongside other MCP servers (e.g., GitHub, Slack, Notion, etc.)	Panther-specific workflows only
Best for	Complex, exploratory tasks requiring flexibility across Panther	Repeatable, consistent security operations workflows
AI model	Uses your MCP client's chosen model (e.g., GPT-4, Claude, LLama4, etc.)	Powered by Claude AI models by Anthropic through Amazon Bedrock