Skip to main content
We provide an MCP (Model Context Protocol) server with prompts, resources and tools that you can use for building AI-applications. The server uses streamable HTTP transport providing real-time communication with Server-Sent Events (SSE) streaming support.

​
Getting Started

Our MCP server is located at https://mcp.tic.io and uses same header authentication as for the REST API. This means we expect x-api-key header key to be present in all calls.

​
Example of using OpenAI Responses API

OpenAI Responses API is the most advanced interface for generating model responses. Full documentation for the API is available here. Endpoint: https://api.openai.com/v1/responses Note you need to include Bearer authentication for the OpenAI to work. An example of the request body follows below that is using flagship gpt-5 model. 
{
  "model": "gpt-5",
  "input": [
    {
      "role": "developer",
      "content": [
        {
          "type": "input_text",
          "text": "Talk like a chief financial officier"
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Get company information for Bahnhof AB (publ)."
        }
      ]
    }
  ],
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "reasoning": {
    "effort": "medium",
    "summary": "auto"
  },
  "tools": [
    {
      "type": "mcp",
      "allowed_tools": [
        "get_company_by_registration_number",
        "get_company_by_name",
        "get_financial_reports",
        "get_annual_reports",
        "get_risks_and_intelligence",
        "get_credit_score",
        "get_company_vehicles",
        "get_company_bankruptcies"
      ],
      "headers": {
        "x-api-key": "your_api_key"
      },
      "require_approval": "never",
      "server_description": null,
      "server_label": "TIC",
      "server_url": "https://mcp.tic.io"
    }
  ],
  "store": true,
  "include": ["reasoning.encrypted_content"]
}

​
Example of LibreChat configuration

If you wish to use our MCP in LibreChat you simply add a block inside mcpServers section in yaml configuration file:
librechat.yaml
mcpServers:
  tic:
    type: streamable-http
    url: https://mcp.tic.io
    headers:
      x-api-key: 'your_api_key'

​
Example of prompt and response

This shows an example of a user input prompt and the response. The request is using gpt-4.1. Clean page

​
Prompts

Exposes prompt templates for clients.

​
Resources

Resources representes structured data like documents and database entries that AI can access.

​
Tools

Functions or APIs that the AI can invoke to perform an action or retrieve information. We currentley serve the following tools:
ToolDescription
get_company_by_nameReturns information about a business
get_company_by_registration_numberReturns information about a business based on the registration number
get_company_by_company_idReturn information about a business based the unique id
get_financial_reportsReturn all available financial reports for a specific business
get_annual_reportsReturn all available annual reports in PDF format with meta data
get_risks_and_intelligenceReturn all available risk and intelligence on a specific business
get_credit_scoreReturn the current credit score and descriptions for basis on calculation on a specific business
get_company_vehiclesReturn the vehicles owned and operated by a specific business
get_company_bankruptciesReturn initiated bankruptcies on the specific date
get_companies_by_sni_codeReturns companies matching a specific 5 digit SNI code
get_property_by_labelReturn an overview of information about a specific property by it’s label
get_orthophoto_by_yearReturn a orthophoto by it’s year, leave empty for it’s most recent year
get_vehicle_by_license_plateReturn information about a vehicle based on it’s license plate
get_vehicle_by_vinReturn information about a vehicle based on it’s vin
We will continously add new tools so check page on this page for new additions.
⌘I