Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"mcp-cerebra-legal-server": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
An enterprise-grade MCP server for legal reasoning and analysis based on the "think" tool concept from Anthropic's engineering blog.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in legal
87 tools for Korean law — statutes, precedents, ordinances, interpretations | MCP Server · CLI · npm
Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.
956k Swiss court decisions: full-text search, citation graph, statute lookup (DE/FR/IT)
AFIP — Argentine tax authority, electronic invoicing (Factura Electrónica)
MCP Security Weekly
Get CVE alerts and security updates for Mcp Cerebra Legal Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
An enterprise-grade MCP server for legal reasoning and analysis based on the "think" tool concept from Anthropic's engineering blog.
Cerebra Legal provides three powerful tools for legal reasoning and analysis:
The server automatically detects legal domains (ANSC contestation, consumer protection, contract analysis) and provides domain-specific guidance, templates, and feedback.
# Clone the repository
git clone https://github.com/yoda-digital/mcp-cerebra-legal-server.git
cd mcp-cerebra-legal-server
# Install dependencies
npm install
# Build the project
npm run build
npm start
The repository includes a test client that demonstrates how to interact with the server:
# Make the test client executable
chmod +x test-client.js
# Run the test client
./test-client.js
The test client will:
To add the server to Claude, update your MCP settings file with the following configuration:
Edit the file at ~/.config/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json:
{
"mcpServers": {
"cerebra-legal": {
"command": "node",
"args": ["/path/to/mcp-cerebra-legal-server/build/index.js"],
"disabled": false,
"alwaysAllow": []
}
}
}
Edit the file at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your platform:
{
"mcpServers": {
"cerebra-legal": {
"command": "node",
"args": ["/path/to/mcp-cerebra-legal-server/build/index.js"],
"disabled": false,
"alwaysAllow": []
}
}
}
Once the server is added to Claude, you can use the tools in your conversations:
For optimal AI interaction with these legal tools, it's essential to include proper guidance in the system prompt. These tools follow the same AI → Human interaction model as standard Cline tools but with domain-specific enhancements.
The system prompt should include detailed documentation for each tool:
## legal_think
Description: A structured legal reasoning tool that helps analyze complex legal issues with domain-specific guidance and templates. This tool enables step-by-step legal analysis with feedback on reasoning quality.
Parameters:
- thought: (required) The current legal reasoning step
- thoughtNumber: (required) Current thought number in sequence
- totalThoughts: (required) Estimated total thoughts needed
- nextThoughtNeeded: (required) Whether another thought step is needed
- category: (optional) Legal domain category (auto-detected if not provided)
- references: (optional) Array of legal references
- isRevision: (optional) Whether this revises previous
... [View full README on GitHub](https://github.com/yoda-digital/mcp-cerebra-legal-server#readme)