Overview
The Orca Security MCP Server brings your cloud security context directly into the AI tools your teams already use. Built on the Model Context Protocol (MCP), it lets security teams investigate, query, and act on their Orca environment through plain language conversation instead of custom integrations or hand built dashboards. Connect Orca to leading AI assistants and agents, including Claude Code, Claude Desktop, Cursor, and ChatGPT, using secure OAuth 2.0 or API token authentication over a remote HTTP endpoint.
With the Orca MCP Server, your teams can: get unified security context (access alerts, asset details, compliance data, and documentation in one place to simplify investigations and cut through noise); see the cloud in natural language (ask plain language questions about configurations, vulnerabilities, and posture through your LLM of choice); accelerate investigations (pivot from an alert to its related assets, risks, and documentation in seconds); and reduce risk proactively (surface hidden risks and compliance gaps before they become incidents).
Because MCP is an open standard, you can build and scale AI agents that work seamlessly against Orca, from continuous monitoring to automated triage, with every agent running against a consistent, secure interface. Orca supports a continually growing set of tools spanning alerts, assets, discovery, and documentation search.
Highlights
- Natural language cloud security: Ask plain language questions about alerts, assets, vulnerabilities, compliance, and posture, and act on them directly from AI assistants like Claude, Cursor, ChatGPT, and many others.
- Faster investigations, unified context: Pivot from an alert to its related assets, attack paths, risks, and documentation in seconds, with alerts, asset details, and compliance data in one interface.
- Open standard, agent ready: Built on the Anthropic backed Model Context Protocol with secure OAuth 2.0 and API token auth, so you can build and scale AI agents for continuous monitoring and automated triage.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
No Refund
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
MCP
GETTING STARTED / SETUP INSTRUCTIONS To get started using the Orca MCP server, follow the instructions below:
Available Tools This MCP server supports the following tools (examples — Orca adds more over time):
- discovery_search - Runs a natural-language search across your cloud environment and returns an app_url deep-link into Orca
- get_alert - Retrieves details for a specific alert
- update_alert_status - Updates an alert's status (open, in_progress, resolved)
- get_alert_attack_path_data - Returns attack-path data for an alert
- get_asset_by_id - Retrieves an asset by its ID
- get_aws_effective_permissions_policy_on_asset - Returns effective AWS permissions on an asset
- documentation_search - Answers questions from the Orca documentation
Prerequisites
- An Orca account and an Orca API token (create one in your Orca account settings)
- Install Node.js and npm (required for the mcp-remote bridge)
Authentication Orca supports OAuth 2.0 (recommended) via the central endpoint https://mcp.orcasecurity.io , and API token auth via your regional endpoint. For token auth, replace YOUR_ORCA_TOKEN with your actual key below. Orca uses the Token prefix (not Bearer).
Claude Desktop Edit the configuration file at:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json Add the below code: { "mcpServers": { "orca": { "command": "npx", "args": [ "mcp-remote", "https://api.orcasecurity.io/mcp ", "--header", "Authorization: Token <YOUR_ORCA_TOKEN>" ] } } }
Cline Cline stores MCP server configurations in a JSON file that can be modified. In the "Installed" tab, choose "Configure MCP Servers" to access the settings file. Add the following: { "mcpServers": { "orca": { "url": "https://api.orcasecurity.io/mcp ", "headers": { "Authorization": "Token <YOUR_ORCA_TOKEN>" }, "disabled": false, "autoApprove": ["discovery_search", "documentation_search"], "timeout": 30 } } }
Rate Limits
- Orca does not publish a fixed per-key request rate limit.
- AI discovery queries run through the MCP server consume Orca AI credits; see AI credits and plans for usage details.
Learn More MCP Docs: https://docs.orcasecurity.io/docs/orca-security-mcp-server
Support
Vendor support
For technical support, log in to your Orca platform and submit a request through the Support portal. For sales or general inquiries, visit
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.