canlii-mcp
Provides access to the CanLII API for searching and retrieving Canadian legal information, including court decisions, legislation, and citations.
README
CanLII MCP Server
A Model Context Protocol (MCP) server that provides access to the CanLII (Canadian Legal Information Institute) API. This server allows AI assistants to search and retrieve Canadian legal information including court decisions, legislation, and legal citations.
Prerequisites
- A CanLII API key (obtain from CanLII API)
- Node.js and npm
- Cloudflare Workers account (for deployment)
Setup
1. Clone and Install Dependencies
git clone <repository-url>
cd canlii-mcp
npm install
2. Configure Environment Variables
Create a .env file or configure your Cloudflare Workers environment with:
CANLII_API=your_canlii_api_key_here
For Cloudflare Workers deployment, set the environment variable using:
wrangler secret put CANLII_API
3. Local Development
npm run dev
This will start the server locally at http://localhost:8787
4. Deploy to Cloudflare Workers
npm run deploy
Available Tools
1. get_courts_and_tribunals
Retrieves a list of available courts and tribunals databases.
Parameters:
language(required): "en" or "fr"- Optional date filters:
publishedBefore,publishedAfter,modifiedBefore,modifiedAfter,changedBefore,changedAfter,decisionDateBefore,decisionDateAfter
2. get_legislation_databases
Gets available legislation databases (statutes, regulations, etc.).
Parameters:
language(required): "en" or "fr"- Optional date filters (same as above)
3. browse_legislation
Browse legislation within a specific database.
Parameters:
language(required): "en" or "fr"databaseId(required): Database code (e.g., "cas" for Canada Statutes, "car" for Canada Regulations)- Optional date filters
4. get_legislation_regulation_metadata
Get detailed metadata for a specific piece of legislation.
Parameters:
language(required): "en" or "fr"databaseId(required): Database identifierlegislationId(required): Specific legislation ID
5. get_case_law_decisions
Retrieve case law decisions from a specific database.
Parameters:
language(required): "en" or "fr"databaseId(required): Database identifieroffset(required): Starting record numberresultCount(required): Number of results (max 10,000)- Optional date filters
6. get_case_metadata
Get detailed metadata for a specific court case.
Parameters:
language(required): "en" or "fr"databaseId(required): Database identifiercaseId(required): Case identifier- Optional date filters
7. get_case_citator
Get citation information for cases (what cases cite this case, what this case cites, etc.).
Parameters:
language(required): "en" or "fr"databaseId(required): Database identifiercaseId(required): Case identifiermetadataType(required): "citedCases", "citingCases", or "citedLegislations"- Optional date filters
Connecting to Claude Desktop
-
Install the mcp-remote proxy:
npm install -g mcp-remote -
In Claude Desktop, go to Settings > Developer > Edit Config and add:
{
"mcpServers": {
"canlii": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:8787/sse"]
}
}
}
For deployed servers, replace the URL with your Cloudflare Workers URL:
https://your-worker-name.your-account.workers.dev/sse
- Restart Claude Desktop
Connecting to Cloudflare AI Playground
- Go to https://playground.ai.cloudflare.com/
- Enter your MCP server URL:
https://your-worker-name.your-account.workers.dev/sse - The CanLII tools will be available in the playground
Usage Examples
Finding Court Decisions
// Get available courts and tribunals
await get_courts_and_tribunals({
language: "en",
});
// Browse recent decisions from Supreme Court of Canada
await get_case_law_decisions({
language: "en",
databaseId: "scc-csc",
offset: 0,
resultCount: 10,
});
Searching Legislation
// Get legislation databases
await get_legislation_databases({
language: "en",
});
// Browse federal statutes
await browse_legislation({
language: "en",
databaseId: "cas",
});
// Get specific act metadata
await get_legislation_regulation_metadata({
language: "en",
databaseId: "cas",
legislationId: "criminal-code",
});
Case Citations
// Get case metadata
await get_case_metadata({
language: "en",
databaseId: "scc-csc",
caseId: "2023scc1",
});
// Find cases that cite this case
await get_case_citator({
language: "en",
databaseId: "scc-csc",
caseId: "2023scc1",
metadataType: "citingCases",
});
Development
Scripts
npm run dev- Start local development servernpm run deploy- Deploy to Cloudflare Workersnpm run format- Format code with Biomenpm run lint:fix- Fix linting issuesnpm run type-check- Run TypeScript type checking
Project Structure
src/
├── index.ts # Main MCP server implementation
├── schema.ts # Zod schemas for API responses
└── worker-configuration.d.ts # TypeScript declarations
API Rate Limits
Be aware of CanLII API rate limits and usage terms. The API is intended for research and educational purposes.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Run tests and linting
- Submit a pull request
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
