Scanorama
Scanorama is a command-line tool to perform static analysis of any MCP-based server (built with official MCP SDKs) and detect potential security issues.
What is Scanorama?
Scanorama is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to scanorama is a command-line tool to perform static analysis of any mcp-based server (built with official mcp sdks) and detect potential security issues.
Scanorama is a command-line tool to perform static analysis of any MCP-based server (built with official MCP SDKs) and detect potential security issues.
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Scanorama is a command-line tool to perform static analysis
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx scanoramaConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Scanorama
Scanorama is an open-source command-line static analysis tool from Telefonica that scans MCP server codebases for security vulnerabilities including prompt injection risks, path traversal flaws, and insecure tool definitions. It uses an LLM backend (Google Gemini, OpenAI, or Azure OpenAI) to analyze server source code and produces structured JSON security reports.
Prerequisites
- Node.js 18+ and npm or pnpm installed
- An LLM API key: Google AI Studio key (GOOGLE_API_KEY), OpenAI key (OPENAI_API_KEY), or Azure OpenAI credentials
- Git for cloning repositories to scan (optional)
- Access to the MCP server source code you want to analyze
Install Scanorama globally
Install Scanorama from npm as a global CLI tool, then verify the installation.
npm install -g @telefonica/scanorama
scanorama --versionConfigure your LLM API key
Create a .env file in your working directory or export the API key for your chosen provider. Google Gemini is the default and recommended provider.
# Google Gemini (recommended):
export GOOGLE_API_KEY="your-google-ai-studio-api-key"
# Or OpenAI:
export OPENAI_API_KEY="your-openai-api-key"
# Or Azure OpenAI:
export AZURE_OPENAI_API_KEY="your-azure-key"
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"
export AZURE_OPENAI_API_VERSION="2024-02-01"Scan a local MCP server directory
Point Scanorama at the root directory of an MCP server project to perform static analysis. Results are printed to stdout.
scanorama --path ./my-mcp-serverScan a remote GitHub repository
Use the --clone flag to have Scanorama clone and analyze a remote MCP server repository directly, without manual cloning.
scanorama --clone https://github.com/owner/mcp-server-repo.gitExport results to a JSON report
Save the analysis results to a JSON file for review, CI integration, or sharing with security teams.
scanorama --path ./my-mcp-server --output security-report.jsonCustomize provider and model
Override the default provider and model, or adjust the LLM temperature for more or less conservative analysis.
# Use OpenAI GPT-4o:
scanorama --path . --provider openai --model gpt-4o --output report.json
# Use Gemini Flash with low temperature for deterministic results:
scanorama --path . --provider google --model gemini-1.5-flash-latest --temperature 0.1
# List available models for a provider:
scanorama --list-modelsScanorama Examples
Client configuration
Scanorama is a CLI tool, not an MCP server. This example shows a typical CI/CD pipeline invocation scanning an MCP server and failing the build on findings.
{
"name": "Security scan MCP server",
"run": "npx @telefonica/scanorama --path . --provider google --output scan-results.json --yes",
"env": {
"GOOGLE_API_KEY": "${{ secrets.GOOGLE_API_KEY }}"
}
}Prompts to try
Example Scanorama CLI invocations for common security analysis scenarios.
- scanorama --path ./mcp-server --output report.json
- scanorama --clone https://github.com/example/mcp-server.git --provider openai
- scanorama --path . --provider google --model gemini-1.5-flash-latest --temperature 0.2
- scanorama --list-models
- scanorama --helpTroubleshooting Scanorama
API key not found or authentication error with the LLM provider
Ensure the API key environment variable is exported in your current shell session or placed in a .env file in the directory where you run scanorama. For Google, the variable must be GOOGLE_API_KEY (not GEMINI_API_KEY). Verify the key is active in the provider's console.
scanorama --clone fails with a Git authentication error
The --clone option clones public repositories without authentication. For private repositories, clone manually first using 'git clone' with your credentials, then use --path to point Scanorama at the local directory.
Analysis produces no findings or generic output
Try lowering the temperature with --temperature 0.1 for more deterministic results. If the server codebase is large, ensure the LLM model you are using supports sufficient context length. Try a different provider — GPT-4o or Gemini 1.5 Pro handle large codebases better than smaller models.
Frequently Asked Questions about Scanorama
What is Scanorama?
Scanorama is a Model Context Protocol (MCP) server that scanorama is a command-line tool to perform static analysis of any mcp-based server (built with official mcp sdks) and detect potential security issues. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Scanorama?
Follow the installation instructions on the Scanorama GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Scanorama?
Scanorama works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Scanorama free to use?
Yes, Scanorama is open source and available under the LGPL-3.0 license. You can use it freely in both personal and commercial projects.
Scanorama Alternatives — Similar Security Servers
Looking for alternatives to Scanorama? Here are other popular security servers you can use with Claude, Cursor, and VS Code.
Casdoor
★ 13.6kAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
ghidraMCP
★ 9.0kAn Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through
HexStrike AI
★ 8.9kHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b
IDA Pro MCP
★ 8.7kEnables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.
Anthropic Cybersecurity Skills
★ 6.6k754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform
Hooker
★ 5.1k🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u
Browse More Security MCP Servers
Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Scanorama in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Scanorama?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.