> For the complete documentation index, see [llms.txt](https://doc.api.tieto.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.api.tieto.com/features/mcp-services.md).

# MCP services

Our Model Context Protocol (MCP) services connect AI agents with platform documentation and authorized banking data. They help technical teams discover, integrate, and operate our Open Banking products from their preferred AI-enabled tools.

{% hint style="info" %}
MCP connects an AI client to defined tools and data sources. Access remains governed by the relevant authentication, consent, and entitlement controls.
{% endhint %}

## Documentation MCP server

The Documentation MCP server exposes our published developer documentation to MCP-compatible AI clients. It provides **read-only** access to the latest published documentation, including API Referecnces.

Our Documentation MCP allows to

* **Search documentation** — locate API guides, endpoint references, authentication requirements, and product-specific information.
* **Read published pages** — retrieve the relevant integration content as structured context for an AI conversation or workflow.
* **Navigate related documentation** — follow links between onboarding guides, API references, examples, and troubleshooting material.

#### Value for TPP integration teams

* **Faster API integration and onboarding** — agents can locate prerequisites, authentication flows, scopes, and request requirements quickly.
* **AI-assisted documentation search** — developers can ask focused technical questions across the published knowledge base.
* **Integration code generation** — agents can use retrieved API documentation to produce implementation scaffolding and request examples. Validate generated code before production use.
* **API error troubleshooting** — agents can match errors against documented response codes, validation rules, and recovery guidance.
* **Reduced support effort** — common integration questions can be resolved through self-service documentation access.
* **Better developer experience** — technical guidance remains available inside the tools developers already use.

{% hint style="warning" %}
Always validate generated requests, security controls, and error handling against the applicable API specification before deployment.
{% endhint %}

## Data Access MCP Service

Our **Data Access MCP Service** enables AI agents to securely access and work with financial data exposed through ASPSP Premium APIs using the Model Context Protocol (MCP). It allows corporate customers to connect the AI agents of their choice to their authorized banking data and use natural-language interactions for financial information retrieval, consolidation, analysis, and reporting.

#### Typical use cases

* **Consolidated financial information**\
  Bring together up-to-date financial data from multiple systems in a single view. Reduce the need to switch between systems or manually collect and consolidate information.
* **Cross-bank information retrieval**\
  Access financial information across multiple connected ASPSPs with a single request, instead of querying each bank or API integration separately.
* **Financial data analysis**\
  Analyze account and transaction data to identify trends, patterns, major cash movements, and changes over time. Use these insights to support liquidity monitoring, cash-flow forecasting, and treasury decision-making.
* **Automated financial reporting**\
  Generate account summaries, transaction reports, cash-position reports, and other management information directly from up-to-date financial data.
* **Financial monitoring and exception detection**\
  Identify significant balance changes, large or unusual transactions, unexpected cash movements, and other conditions requiring attention.
* **Natural-language financial queries**\
  Interact with financial data using everyday language. For example: *“What is our current EUR cash position across all connected banks?”*, *“What were our five largest outgoing transactions last week?”*, or *“Which accounts experienced the largest balance decrease this month?”*


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://doc.api.tieto.com/features/mcp-services.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.