> ## Documentation Index > Fetch the complete documentation index at: https://docs.tic.io/llms.txt > Use this file to discover all available pages before exploring further. # MCP Server > Use the TIC MCP (Model Context Protocol) server in AI applications — prompts, resources, and tools for Claude, OpenAI, and other LLMs. 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](https://mcp.tic.io). It accepts your TIC API key via either of two headers: * `x-api-key: ` — same scheme as our REST API * `Authorization: Bearer ` — for clients (such as the Anthropic Messages API connector) that only forward an OAuth-style bearer token Either form authenticates the same way against the same key. Pick whichever your MCP client supports. ## 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](https://platform.openai.com/docs/api-reference/responses). Endpoint: [https://api.openai.com/v1/responses](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. ```json theme={null} { "model": "gpt-5", "input": [ { "role": "developer", "content": [ { "type": "input_text", "text": "Talk like a chief financial officer" } ] }, { "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_company_by_company_id", "get_companies_by_sni_code", "get_financial_reports", "get_annual_reports", "get_risk_and_intelligence", "get_credit_score", "get_company_risk_summary", "get_company_debt_cases", "get_company_penalties", "get_company_lansstyrelsen_decisions", "get_company_kammarkollegiet_sanctions", "get_company_tax_deferrals", "get_company_business_mortgages", "get_company_payroll_history", "get_company_share_structure", "get_company_address_history", "get_company_name_history", "get_company_vehicles", "get_company_bankruptcies" ], "headers": { "x-api-key": "your_api_key" }, "require_approval": "never", "server_label": "TIC", "server_url": "https://mcp.tic.io" } ], "store": true, "include": ["reasoning.encrypted_content"] } ``` ## Example of using Anthropic Messages API Anthropic's Messages API can call remote MCP servers directly through its MCP connector. Full documentation is available [here](https://docs.claude.com/en/docs/agents-and-tools/mcp-connector). Endpoint: `https://api.anthropic.com/v1/messages` You need three headers on the request: * `x-api-key: ` — your Anthropic API key * `anthropic-version: 2023-06-01` * `anthropic-beta: mcp-client-2025-11-20` The `authorization_token` field on the MCP server entry is forwarded by Anthropic to our server as `Authorization: Bearer ` — pass your **TIC** API key there. An example request body: ```json theme={null} { "model": "claude-opus-4-7", "max_tokens": 1024, "messages": [ { "role": "user", "content": "Get company information for Bahnhof AB (publ)." } ], "mcp_servers": [ { "type": "url", "url": "https://mcp.tic.io", "name": "tic", "authorization_token": "your_tic_api_key" } ], "tools": [ { "type": "mcp_toolset", "mcp_server_name": "tic" } ] } ``` To restrict which TIC tools the model can see, use the `mcp_toolset` allowlist pattern — disable everything by default, then enable specific tools: ```json theme={null} { "tools": [ { "type": "mcp_toolset", "mcp_server_name": "tic", "default_config": { "enabled": false }, "configs": { "get_company_by_registration_number": { "enabled": true }, "get_company_risk_summary": { "enabled": true }, "get_company_debt_cases": { "enabled": true }, "get_company_penalties": { "enabled": true } } } ] } ``` ## 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: ```yaml librechat.yaml theme={null} 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 Prompts are user-invokable workflow templates that combine multiple tools into a single investigation flow with explicit framing and a named deliverable. Pick one from your MCP client's prompt menu to kick off an end-to-end analysis. All prompts take `registrationNumber` (Swedish organisationsnummer, e.g. `556519-9493`) and resolve identity to the internal companyId as their first step. | Prompt | Parameters | What it does | | -------------------------- | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | investigate\_company | `registrationNumber` | Full company workup: identity, risk, debts, penalties, addresses, naming, share structure. Deliverable: red-flag report grouped by category. | | liquidity\_stress\_check | `registrationNumber` | Combines credit risk, Skatteverket tax deferrals, Kronofogden debts, and payroll trend. Deliverable: stress score (Low/Medium/High/Critical) with evidence. | | due\_diligence\_check | `registrationNumber` | Know-Your-Business check. Resolves identity then runs the full workup. Deliverable: KYB verdict (Proceed / Conditions / Decline). | | shell\_company\_indicators | `registrationNumber` | Screens for shell-company / fraud signals: name churn, address intelligence, missing payroll, share-capital anomalies. Deliverable: shell likelihood + indicators. | ## Resources Resources are static reference data the model reads once into context — no tool call required. They decode the codes that appear in tool responses. | URI | What it contains | | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | | ormeo://reference/codes | Decoder for `LocalCompanyCode` (Swedish legal-form codes: AB, HB, KB, BRF, EK, SF, FL, …) and Kronofogden `KFM_DebtCaseType` (A vs E debt cases). | ## Tools Functions the model invokes to retrieve company, property, or vehicle data. Tools are grouped below by purpose. ### Company search & identity | Tool | Description | | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | | get\_company\_by\_name | Find a company by current or historical name | | get\_company\_by\_registration\_number | Find a company by Swedish registration number (organisationsnummer) | | get\_company\_by\_company\_id | Get the core company record by internal companyId | | get\_companies\_by\_sni\_code | List companies matching a 5-digit SNI industry code. Supports both SNI 2007 and SNI 2025 — pass `sniStandard="2007"` (default) or `"2025"`. | ### Company financials & risk | Tool | Description | | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | get\_financial\_reports | Income statement and balance sheet across all available periods (TKR, SEK) | | get\_annual\_reports | List of available annual reports in PDF with metadata and download URLs | | get\_credit\_score | Current credit score and the descriptions used as the basis of the calculation | | get\_company\_risk\_summary | Numeric risk scores: credit score, forward risk forecast/class, board score, beneficial-owners score, financial-discrepancy score, other-intelligence score, intelligence aggregates, and ORB network-risk aggregate counts. Scores only — no per-person details. 4-hour cache. | | get\_risk\_and\_intelligence | Raw company-intelligence records (flags and signals collected over time) | ### Company enforcement & compliance | Tool | Description | | ---------------------------------------- | -------------------------------------------------------------------------------------------------- | | get\_company\_debt\_cases | Kronofogden enforcement: debtor summary, debt summary, current cases, weekly aggregates | | get\_company\_penalties | Consolidated penalties (Skatteverket, Kammarkollegiet, Länsstyrelsen, Försäkringskassan, fees) | | get\_company\_lansstyrelsen\_decisions | Länsstyrelsen (County Administrative Board) decisions and penalty fees | | get\_company\_kammarkollegiet\_sanctions | Kammarkollegiet sanction cases grouped by diary number, with current balance and full case history | | get\_company\_tax\_deferrals | Skatteverket TF-ANST temporary tax-payment deferrals (liquidity-stress signal) | | get\_company\_bankruptcies | Bankruptcies initiated on a given date | ### Company structure & history | Tool | Description | | --------------------------------- | ---------------------------------------------------------------------------------------------- | | get\_company\_business\_mortgages | Bolagsverket-registered business mortgages (företagsinteckningar) — collateral encumbrance | | get\_company\_payroll\_history | Skatteverket MOMS-AG (VAT/employer tax) filings and aggregated CompanyPayroll2 history | | get\_company\_share\_structure | Registered share capital over time and share-class structure (A/B/C, …) from Bolagsverket | | get\_company\_address\_history | All addresses (visiting, mailing, registered) enriched with active AddressIntelligence signals | | get\_company\_name\_history | Current and historical legal names plus trade names (bifirma) | ### Vehicles | Tool | Description | | -------------------------------- | -------------------------------------------------------- | | get\_company\_vehicles | Vehicles owned or operated by a company | | get\_vehicle\_by\_license\_plate | Look up a vehicle by license plate | | get\_vehicle\_by\_vin | Look up a vehicle by VIN (vehicle identification number) | ### Property | Tool | Description | | ------------------------- | --------------------------------------------------------------------------- | | get\_property\_by\_label | Find a property by its label (property designation / fastighetsbeteckning) | | get\_orthophoto\_by\_year | Get an orthophoto for a property; leave year empty for the most recent year | We will continuously add new tools — check back here for new additions.