Orca Security MCP Server

This integration connects Orca Security's AI Sonar and data serving capabilities to MCP (Model Control Protocol), allowing you to ask natural language questions about your cloud infrastructure security posture directly in Cursor, Claude or other AI tools.

Configure Claude Desktop

Install uv if you don't have it already:
```
pip install uv
```
Open Claude Desktop, Go to Settings->Developers->Edit Config

Change the configuration file to the following (replacing <TOKEN> with your actual Orca token):

{
  "mcpServers": {
    "orca": {
      "command": "uvx",
      "args": ["orca-mcp-server"],
      "env": {
        "ORCA_AUTH_TOKEN": "<TOKEN>"
      }
    }
  }
}

Restart Claude Desktop for the changes to take effect

Environment Variables

Variable	Description	Default
`ORCA_API_HOST`	Orca Security API host	https://api.orcasecurity.io
`ORCA_AUTH_TOKEN`	Your Orca API authentication token	TOKEN (Required)
`ORCA_REQUEST_TIMEOUT`	API request timeout in seconds	30.0

Using the Integration

Once running, you can query the Orca Security data using natural language:

Example queries:

"Show me all critical vulnerabilities in my AWS environment"
"What EC2 instances are missing security patches?"
"Which S3 buckets are publicly accessible?"

Troubleshooting

If you encounter issues:

Check the log output for error messages
Verify your Orca authentication token is valid
Ensure your network allows connections to the Orca API endpoint

Development Status
- 3 - Alpha
Intended Audience
- Developers
License
- OSI Approved :: MIT License
Programming Language
- Python :: 3.10

Metadata

Development Status
- 3 - Alpha
Intended Audience
- Developers
License
- OSI Approved :: MIT License
Programming Language
- Python :: 3.10

Release files for orca-mcp-server 1.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for orca-mcp-server 1.0.2
File	Size	Uploaded	Provenance
orca_mcp_server-1.0.2.tar.gz	4.4 kB	May 19, 2025	With provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for orca-mcp-server 1.0.2
File	Interpreter	ABI	Platform	Reset
orca_mcp_server-1.0.2-py3-none-any.whl 4.4 kB May 19, 2025 With provenance	Python 3	none	any	Details

Total release size: 8.8 kB

Release files / orca_mcp_server-1.0.2.tar.gz

Download URL	orca_mcp_server-1.0.2.tar.gz
Size	4.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`310e28188d17a9a1a6e62915b5c39f027aa395fc6fbf7f48cc2e5f30a8b296b6`
BLAKE2b-256 checksum How to use checksums	`6f99ccc78e96c06427928adec97ac03d160fc8056c16af2c6fe2e56865b52ecc`
Upload date	May 19, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/orcasecurity/orca-mcp-server
Publishing commit: github.com/orcasecurity/orca-mcp-server/tree/8e4b42199973387bd2bf972aa91d29b04a759843

Workflow

Publishing configuration: github.com/orcasecurity/orca-mcp-server/blob/8e4b42199973387bd2bf972aa91d29b04a759843/.github/workflows/python-publish.yml
Publishing logs: github.com/orcasecurity/orca-mcp-server/actions/runs/15110548863/attempts/1

Artifact

Subject: orca_mcp_server-1.0.2.tar.gz
SHA-256 checksum: 310e28188d17a9a1a6e62915b5c39f027aa395fc6fbf7f48cc2e5f30a8b296b6 Verifying attestations

Release files / orca_mcp_server-1.0.2-py3-none-any.whl

Download URL	orca_mcp_server-1.0.2-py3-none-any.whl
Size	4.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`a3562fac3efe2da30ee5b4b25442a7867ced438f7dd7590dc5a8c70c65a2fcb9`
BLAKE2b-256 checksum How to use checksums	`1b46d2da54324f375ccc665bc2606b32b04e85463a834dff3880fafb406de689`
Upload date	May 19, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/orcasecurity/orca-mcp-server
Publishing commit: github.com/orcasecurity/orca-mcp-server/tree/8e4b42199973387bd2bf972aa91d29b04a759843

Workflow

Publishing configuration: github.com/orcasecurity/orca-mcp-server/blob/8e4b42199973387bd2bf972aa91d29b04a759843/.github/workflows/python-publish.yml
Publishing logs: github.com/orcasecurity/orca-mcp-server/actions/runs/15110548863/attempts/1

Artifact

Subject: orca_mcp_server-1.0.2-py3-none-any.whl
SHA-256 checksum: a3562fac3efe2da30ee5b4b25442a7867ced438f7dd7590dc5a8c70c65a2fcb9 Verifying attestations

Security for orca-mcp-server 1.0.2

Report project as malware

Provenance

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Attestation for orca_mcp_server-1.0.2.tar.gz

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/orcasecurity/orca-mcp-server
Publishing commit: github.com/orcasecurity/orca-mcp-server/tree/8e4b42199973387bd2bf972aa91d29b04a759843

Workflow

Publishing configuration: github.com/orcasecurity/orca-mcp-server/blob/8e4b42199973387bd2bf972aa91d29b04a759843/.github/workflows/python-publish.yml
Publishing logs: github.com/orcasecurity/orca-mcp-server/actions/runs/15110548863/attempts/1

Artifact

Subject: orca_mcp_server-1.0.2.tar.gz
SHA-256 checksum: 310e28188d17a9a1a6e62915b5c39f027aa395fc6fbf7f48cc2e5f30a8b296b6 Verifying attestations

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.