Supports configuration via the Claude Desktop MCP settings file located in the macOS Application Support directory.
Runs as a Node.js application that can be integrated with Claude Desktop through the MCP configuration.
Built with TypeScript for type safety and compiled to JavaScript for execution.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Online Kommentar MCP Server Search for commentaries about data protection in German"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides access to Swiss legal commentaries from onlinekommentar.ch. This server allows you to search and retrieve detailed legal commentaries on Swiss federal law through Claude Desktop or other MCP-compatible clients.
Search Commentaries: Full-text search across legal commentaries with filtering options
Retrieve Individual Commentaries: Get detailed content for specific legal articles
Multi-language Support: Search in English, German, French, and Italian
Advanced Filtering: Filter by legislative act, sort by title or date
Pagination Support: Navigate through large result sets
Related MCP server: German Legal MCP Server
Node.js (version 14 or higher)
npm or yarn package manager
Claude Desktop (for MCP integration)
Clone the repository:
git clone https://github.com/self-tech-labs/onlinekommentar-mcp.git
cd onlinekommentar-mcpInstall dependencies:
npm installBuild the project:
npm run buildAdd the following configuration to your Claude Desktop MCP settings file:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"online-kommentar": {
"command": "node",
"args": ["/path/to/onlinekommentar-mcp/build/index.js"]
}
}
}Replace /path/to/onlinekommentar-mcp with the actual path to your project directory.
After adding the configuration, restart Claude Desktop to load the MCP server.
Search for legal commentaries using various filters.
Parameters:
search (required): Full-text search query
language (optional): Content language (en, de, fr, it)
legislative_act (optional): Filter by legislative act ID
sort (optional): Sort order (title, -title, date, -date)
page (optional): Page number for pagination
Example queries:
"Search for commentaries about intellectual property"
"Find German commentaries about data protection"
"Search for articles related to criminal law, sorted by date"
Retrieve detailed information about a specific commentary using its ID.
Parameters:
id (required): The unique identifier of the commentary
Example:
"Get commentary details for ID: 6d8aee6b-86d0-43f2-8110-2d5b7360dd18"
Search for commentaries about "constitutional rights" in EnglishThis will return a list of relevant commentaries with their IDs, titles, publication dates, and URLs.
Get the full content of commentary ID: 7058f7a5-19d8-444e-a901-7bb635ded375This will return comprehensive information including:
Full title and publication details
Authors and editors
Legislative act information
Complete commentary content
Legal text being commented on
onlinekommentar-mcp/
├── src/
│ └── index.ts # Main MCP server implementation
├── build/ # Compiled JavaScript output
├── package.json # Project dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This filenpm run build: Compile TypeScript to JavaScript
npm start: Run the compiled server (for testing)
The server integrates with the onlinekommentar.ch API:
Base URL: https://onlinekommentar.ch/api
Endpoints:
/commentaries - Search commentaries
/commentaries/{id} - Get specific commentary
This server implements the Model Context Protocol specification, providing:
Tool registration for search and retrieval functions
Proper error handling and response formatting
JSON schema validation for parameters
Commentary objects include:
Unique identifiers
Multilingual titles and content
Author and editor information
Legislative act associations
Publication dates and metadata
Direct links to online versions
Server not appearing in Claude Desktop:
Check the configuration file path and syntax
Ensure the build directory exists and contains compiled JavaScript
Restart Claude Desktop after configuration changes
Build errors:
Verify Node.js version (14+ required)
Run npm install to ensure all dependencies are installed
Check for TypeScript compilation errors
API connection issues:
Verify internet connectivity
Check if onlinekommentar.ch is accessible
Review error messages in Claude Desktop logs
To debug the MCP server:
Check Claude Desktop logs for error messages
Test the API endpoints directly using curl:
curl "https://onlinekommentar.ch/api/commentaries?search=test"Verify the build output in the build/ directory
Fork the repository
Create a feature branch: git checkout -b feature-name
Make your changes and add tests
Commit your changes: git commit -am 'Add new feature'
Push to the branch: git push origin feature-name
Submit a pull request
This project is open source. Please refer to the license file for details.
For issues and questions:
Open an issue on GitHub
Check the troubleshooting section above
Review the MCP protocol documentation
onlinekommentar.ch for providing the legal commentary API
Model Context Protocol for the integration framework
Swiss legal community for comprehensive commentary resources
Note: This tool provides access to Swiss legal commentaries for informational purposes. Always consult qualified legal professionals for legal advice.
Retrieves a specific commentary by its ID.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the commentary to retrieve. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a retrieval operation, implying read-only behavior, but doesn't address permissions, error conditions, rate limits, or what happens if the ID doesn't exist. Significant behavioral context is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a simple retrieval tool and gets straight to the point without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a retrieval tool with no annotations and no output schema, the description is insufficient. It doesn't explain what a 'commentary' is, what format it returns, error handling, or how this differs from the sibling search tool. More context is needed for proper agent understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents the single 'id' parameter. The description doesn't add any additional parameter semantics beyond what's in the schema, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('retrieves') and resource ('a specific commentary'), making the purpose unambiguous. However, it doesn't explicitly differentiate from the sibling 'search_commentaries' tool, which would be needed for a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus the sibling 'search_commentaries' tool. The description doesn't mention prerequisites, alternatives, or contextual constraints, leaving the agent without usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Searches for legal commentaries based on a query and filters.
| Name | Required | Description | Default |
|---|---|---|---|
| search | Yes | The full-text search query. | |
| language | No | Content language. | |
| legislative_act | No | Filter by legislative act ID. | |
| sort | No | Sort order. | |
| page | No | Page number for pagination. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'searches' but doesn't clarify if this is a read-only operation, what the expected response format is, whether there are rate limits, authentication requirements, or pagination behavior beyond the 'page' parameter. This leaves significant gaps in understanding how the tool behaves in practice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded with the core action and resource, making it easy to parse quickly. Every part of the sentence contributes to understanding the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a search tool with 5 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what a 'legal commentary' is, the search scope, result format, or behavioral aspects like error handling. This leaves the agent with insufficient context to use the tool effectively beyond basic parameter input.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value by mentioning 'filters' generically, but doesn't elaborate on specific parameters like 'legislative_act' or 'sort' beyond what the schema provides. This meets the baseline for high schema coverage, but doesn't enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('searches for') and resource ('legal commentaries'), making the purpose understandable. It distinguishes from the sibling tool 'get_commentary_by_id' by indicating this is a search operation rather than retrieval by specific ID. However, it doesn't specify what constitutes a 'legal commentary' or the search scope beyond 'based on a query and filters,' which keeps it from being fully specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It mentions 'filters' but doesn't specify which filters are available or when to apply them. There's no mention of prerequisites, limitations, or comparison to the sibling tool 'get_commentary_by_id,' leaving the agent without clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
get_commentary_by_idsearch_commentariesThe two tools have clearly distinct purposes: one retrieves a specific commentary by ID, while the other searches for commentaries based on queries and filters. There is no overlap or ambiguity between them.
Both tools follow a consistent verb_noun pattern with snake_case naming: get_commentary_by_id and search_commentaries. The naming is predictable and readable throughout.
With only two tools, the server feels thin for a legal commentary domain. It lacks essential operations like creating, updating, or deleting commentaries, which limits its utility and scope.
The tool surface is severely incomplete for a legal commentary server. It only provides retrieval and search capabilities, missing core CRUD operations (create, update, delete) and other lifecycle management tools, leading to significant gaps in functionality.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Resolve, search and verify legal citations against the official sources, with provenance.
Swiss federal law (Fedlex) and political data (LINDAS) for agents, every answer with sources
MCP for CanLII: Canadian case law and legislation metadata (federal, provincial, territorial).
Search Swiss federal legislation: laws, articles, amendments via the Fedlex SPARQL endpoint.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/self-tech-labs/onlinekommentar-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
