Skip to main content
Glama
norman-finance

Norman Finance MCP Server

Official

get_client

Retrieve detailed client information from the Norman Finance MCP server by providing a client ID. Designed to simplify financial workflows for entrepreneurs in Germany.

Instructions

Get detailed information about a specific client.

Args:
    client_id: ID of the client to retrieve
    
Returns:
    Detailed client information

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
client_idYes

Implementation Reference

  • The MCP tool handler for 'get_client'. This function executes the core logic of the tool, fetching detailed client information from the Norman Finance API using the provided client_id.
    @mcp.tool()
    async def get_client(
        ctx: Context,
        client_id: str
    ) -> Dict[str, Any]:
        """
        Get detailed information about a specific client.
        
        Args:
            client_id: ID of the client to retrieve
            
        Returns:
            Detailed client information
        """
        api = ctx.request_context.lifespan_context["api"]
        company_id = api.company_id
        
        if not company_id:
            return {"error": "No company available. Please authenticate first."}
        
        client_url = urljoin(
            config.api_base_url, 
            f"api/v1/companies/{company_id}/clients/{client_id}/"
        )
        
        return api._make_request("GET", client_url)
  • Tool registration section in the MCP server creation. The call to register_client_tools(server) registers the get_client tool (along with other client tools) with the FastMCP server instance.
    # Register all tools
    register_client_tools(server)
    register_invoice_tools(server)
    register_tax_tools(server)
    register_transaction_tools(server)
    register_document_tools(server)
    register_company_tools(server)
    register_prompts(server)
    register_resources(server)
  • Import of the register_client_tools function used to register client-related MCP tools including get_client.
    from norman_mcp.tools.clients import register_client_tools
    from norman_mcp.tools.invoices import register_invoice_tools
    from norman_mcp.tools.taxes import register_tax_tools
  • The register_client_tools function defines and registers all client-related tools, including the @mcp.tool()-decorated get_client handler.
    def register_client_tools(mcp):
        """Register all client-related tools with the MCP server."""
        
        @mcp.tool()
        async def list_clients(
            ctx: Context
        ) -> Dict[str, Any]:
            """
            Get a list of all clients for the company.
            
            Returns:
                List of clients with their details
            """
            api = ctx.request_context.lifespan_context["api"]
            company_id = api.company_id
            
            if not company_id:
                return {"error": "No company available. Please authenticate first."}
            
            clients_url = urljoin(
                config.api_base_url, 
                f"api/v1/companies/{company_id}/clients/"
            )
            
            return api._make_request("GET", clients_url)
    
        @mcp.tool()
        async def get_client(
            ctx: Context,
            client_id: str
        ) -> Dict[str, Any]:
            """
            Get detailed information about a specific client.
            
            Args:
                client_id: ID of the client to retrieve
                
            Returns:
                Detailed client information
            """
            api = ctx.request_context.lifespan_context["api"]
            company_id = api.company_id
            
            if not company_id:
                return {"error": "No company available. Please authenticate first."}
            
            client_url = urljoin(
                config.api_base_url, 
                f"api/v1/companies/{company_id}/clients/{client_id}/"
            )
            
            return api._make_request("GET", client_url)
    
        @mcp.tool()
        async def create_client(
            ctx: Context,
            name: str,
            client_type: str = "business",
            address: Optional[str] = None,
            zip_code: Optional[str] = None,
            email: Optional[str] = None,
            country: Optional[str] = None,
            vat_number: Optional[str] = None,
            city: Optional[str] = None,
            phone: Optional[str] = None
        ) -> Dict[str, Any]:
            """
            Create a new client.
            
            Args:
                name: Client name or business name
                client_type: Type of client (defaults to "business"), Options: "business", "private"
                address: Client physical address
                zip_code: Client postal/zip code
                email: Client email address
                country: Client country code (e.g. "DE")
                vat_number: Client VAT number
                city: Client city
                phone: Client phone number
                
            Returns:
                Newly created client record
            """
            api = ctx.request_context.lifespan_context["api"]
            company_id = api.company_id
            
            if not company_id:
                return {"error": "No company available. Please authenticate first."}
            
            if client_type not in ["business", "private"]:
                return {"error": "client_type must be either 'business' or 'private'"}
            
            clients_url = urljoin(
                config.api_base_url, 
                f"api/v1/companies/{company_id}/clients/"
            )
            
            client_data = {
                "name": name,
                "clientType": client_type
            }
        
            if email:
                client_data["email"] = email
            if phone:
                client_data["phone"] = phone
            if vat_number:
                client_data["vatNumber"] = vat_number
            if address:
                client_data["address"] = address
            if zip_code:
                client_data["zipCode"] = zip_code
            if country:
                client_data["country"] = country
            if city:
                client_data["city"] = city
                
            return api._make_request("POST", clients_url, json_data=client_data)
    
        @mcp.tool()
        async def update_client(
            ctx: Context,
            client_id: str,
            name: Optional[str] = None,
            client_type: Optional[str] = None,
            address: Optional[str] = None,
            zip_code: Optional[str] = None,
            email: Optional[str] = None,
            country: Optional[str] = None,
            vat_number: Optional[str] = None,
            city: Optional[str] = None,
            phone: Optional[str] = None
        ) -> Dict[str, Any]:
            """
            Update an existing client.
            
            Args:
                client_id: ID of the client to update
                name: Updated client name
                client_type: Updated client type ("business" or "private")
                address: Updated client physical address
                zip_code: Updated client postal/zip code
                email: Updated client email address
                country: Updated client country code (e.g. "DE")
                vat_number: Updated client VAT number
                city: Updated client city
                phone: Updated client phone number
                
            Returns:
                Updated client record
            """
            api = ctx.request_context.lifespan_context["api"]
            company_id = api.company_id
            
            if not company_id:
                return {"error": "No company available. Please authenticate first."}
            
            if client_type and client_type not in ["business", "private"]:
                return {"error": "client_type must be either 'business' or 'private'"}
            
            client_url = urljoin(
                config.api_base_url, 
                f"api/v1/companies/{company_id}/clients/{client_id}/"
            )
            
            # Get current client data
            current_data = api._make_request("GET", client_url)
            
            # Update only provided fields
            update_data = {}
            if name:
                update_data["name"] = name
            if client_type:
                update_data["clientType"] = client_type
            if email:
                update_data["email"] = email
            if phone:
                update_data["phone"] = phone
            if vat_number:
                update_data["vatNumber"] = vat_number
            if address:
                update_data["address"] = address
            if zip_code:
                update_data["zipCode"] = zip_code
            if country:
                update_data["country"] = country
            if city:
                update_data["city"] = city
            
            # If no fields provided, return current data
            if not update_data:
                return {"message": "No fields provided for update.", "client": current_data}
            
            return api._make_request("PATCH", client_url, json_data=update_data)
    
        @mcp.tool()
        async def delete_client(
            ctx: Context,
            client_id: str
        ) -> Dict[str, Any]:
            """
            Delete a client.
            
            Args:
                client_id: ID of the client to delete
                
            Returns:
                Confirmation of deletion
            """
            api = ctx.request_context.lifespan_context["api"]
            company_id = api.company_id
            
            if not company_id:
                return {"error": "No company available. Please authenticate first."}
            
            client_url = urljoin(
                config.api_base_url, 
                f"api/v1/companies/{company_id}/clients/{client_id}/"
            )
            
            api._make_request("DELETE", client_url)
            return {"message": "Client deleted successfully"} 
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states it retrieves detailed information. It lacks behavioral details such as required permissions, error handling (e.g., invalid client_id), response format, or whether it's a read-only operation, which is critical for a tool with no structured safety hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise and well-structured with clear sections for Args and Returns, using minimal sentences that each serve a purpose without redundancy. It's front-loaded with the core purpose, making it efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain what 'detailed client information' includes, error cases, or behavioral traits, leaving significant gaps for a tool that interacts with client data in a financial context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, but the description adds basic semantics by explaining 'client_id' as 'ID of the client to retrieve'. This compensates partially, though it doesn't specify format (e.g., numeric, string) or constraints, keeping it at a baseline level of adequacy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('detailed information about a specific client'), making the purpose unambiguous. However, it doesn't differentiate from sibling tools like 'list_clients' or 'update_client', which would require explicit scope clarification 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.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'list_clients' for multiple clients or 'update_client' for modifications. The description only states what it does, not when it's appropriate, leaving the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/norman-finance/norman-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server