Finout MCP Integration

Overview

With the Finout MCP (Model Context Protocol), you can ask questions about your cloud cost spend, anomalies, waste, budgets, tag coverage, unit economics, and more - directly inside the AI tools you already use. The Finout MCP acts as a bridge to your live Finout data, letting you query and visualize cloud spend through natural language without switching tools or exporting data.

The Finout MCP is hosted and managed by Finout. There is nothing to install and no credentials to manage locally - authentication is handled via a standard OAuth flow, the same experience you use to log in to Finout.

MCP Clients

An MCP client is any AI assistant or agent that can communicate using the Model Context Protocol. The Finout MCP is compatible with any client that supports remote MCP with OAuth. Examples include:

• Claude (web and desktop)

• Cursor IDE

• Any other MCP-compatible AI tool

You can find a full list of clients in the MCP documentation.

What You Can Do

Once connected, ask questions like:

• "Show me the top 5 AWS services by cost last month"

• "Compare our cloud spend this quarter vs last quarter"

• "Which dimensions had the biggest cost increase this month?"

• "Are there any high-severity cost anomalies this week?"

• "What are our biggest waste and rightsizing opportunities?"

• "How are we tracking against our Q1 budget?"

• "What percentage of our spend is tagged with a team tag?"

Getting Connected

Step 1 - Download and Install an MCP Client

• Claude - Download Claude for Desktop or use Claude on the web.

• Cursor - Download Cursor for your operating system.

Other tools - Any MCP-compatible AI tool that supports remote connections via OAuth will work. Point it to https://mcp.finout.io/mcp.

Step 2 — Configure the Finout MCP Server

Claude

1. Open Settings → Connectors

2. Click Add Custom Connector

3. Enter the following details and click Add:

Field	Value
Name	Finout
URL	https://mcp.finout.io/mcp

Cursor

Other clients

Step 3 - Authorize the Finout MCP Server

After configuring the server, your browser will open an authorization screen.

1. Review the authorization details and click Allow Access

2. Log in to Finout with your existing credentials or via SSO

3. Once authorized, close the browser tab and return to your AI client

Tip: By default, most clients ask for approval before each tool call. For a smoother experience, set the permission to Always Allow in your connector settings.

Step 4 - Start Prompting

Open a new chat and start asking questions about your cloud costs. For example:

"Show me the top 5 AWS services by cost last month"

Your AI client will use the appropriate Finout MCP tool and return results from your live Finout data.

Data Access & Permissions

The Finout MCP respects your account's existing data access controls — no exceptions are granted simply because a request originates from an AI client.

When you connect the Finout MCP, authentication flows through a standard OAuth screen. The credentials you authorize with are the same credentials your Finout account uses. As a result, every query the MCP runs is scoped to exactly what your user is permitted to see — the same cost centers, filters, and data ranges available to you inside the Finout app.

This means:

• If your account is restricted to specific cost centers, the MCP cannot query outside them.

• If your organization has team-based access policies, those policies apply equally to MCP queries.

• There is no elevated or "read-all" mode available through the MCP.

The Finout MCP exposes 25 tools across five categories.

Discovery & Context

Tool	Description
get_account_context	Returns connected cost centers, available data ranges, and account configuration. Good first call when orienting to a new account.
search_filters	Finds filter metadata by name - required before calling query_costs or compare_costs.
get_filter_values	Returns available values for a specific filter (e.g., "what services do we use?").
list_available_filters	Lists all available filters by cost center. Use only when you need a full overview - prefer search_filters for targeted lookups.
debug_filters	Diagnostic tool for inspecting raw filter metadata. Use when a filter lookup returns unexpected results.
discover_context	Finds dashboards, saved views, and data explorers by name.
list_data_explorers	Lists all saved data explorer configurations in the account.
list_telemetry_centers	Lists custom metric sources available for unit economics calculations.

Cost Analysis

Tool	Description
query_costs	Core cost query tool. Returns totals, breakdowns, and trends for any combination of time period, filters, and grouping dimensions.
compare_costs	Compares cloud costs between two time periods.
get_top_movers	Identifies dimensions with the biggest cost changes between two periods.
get_unit_economics	Computes cost-per-unit metrics (e.g., cost per active user, cost per API request).
get_cost_statistics	Returns daily cost stats: mean, median, peak, trough, and volatility.
get_cost_patterns	Analyzes temporal patterns - hourly peaks, weekday vs. weekend splits, recurring cycles.
get_savings_coverage	Analyzes savings plan and reservation coverage, including commitment gaps.
get_usage_unit_types	Discovers available usage unit types for a cost center. Call before using usage_configuration in query_costs.

Anomalies & Waste

Tool	Description
get_anomalies	Retrieves cost anomalies and spikes detected by Finout. Filter by severity: high, medium, low.
get_waste_recommendations	Returns CostGuard waste detection results - idle resources, over-provisioned instances, and commitment gaps.

Governance & Allocation

Tool	Description
get_tag_coverage	Measures what percentage of spend is tagged by a given dimension.
get_financial_plans	Retrieves budgets and forecasts with actuals, run rate, and forecast per dimension.
analyze_virtual_tags	Deep-dives into virtual tag configuration, relationships, and allocation logic.
get_object_usages	Finds all places a named Finout object is referenced - useful before modifying anything.
check_delete_safety	Checks whether a Finout object is safe to delete without breaking downstream dependencies.

Presentation

Tool	Description
render_chart	Renders a bar, column, line, or pie chart directly in the AI assistant UI. Use after query_costs or compare_costs to visualize results in-context.

What the MCP Cannot Do

The Finout MCP is currently read-only. It can retrieve, analyze, and surface your cost data, but it cannot create, edit, or delete anything inside your Finout account.

Specifically, the MCP cannot:

• Create or modify Virtual Tags, Cost Centers, or Dashboards

• Update financial plans or budgets

• Change account settings or user permissions

• Trigger any action that would alter your Finout configuration

If your AI client generates a configuration — for example, a Virtual Tag definition — it will produce that output as text or JSON for you to review and apply manually inside the Finout app or through Finout API.

Prompting Best Practices

• Pair with the Finout Docs MCP: For questions that combine how-to guidance with live account data, connect both the Finout MCP and the Finout Docs MCP at the same time. This lets your AI client retrieve documentation and query your actual cost data in a single conversation. Example: "What does the documentation say about Reserved Instance coverage, and what does our actual RI coverage look like this month?"

• Add context to your prompts. Mention the provider, time period, service, or tag dimension when relevant. For example: "Break down EC2 costs by environment tag for the last 30 days"

• Be specific about the time period. The default is the last 30 days - saying "last quarter" or "March 2026" ensures you get exactly the window you intend.

• Ask one thing at a time. Stacking unrelated questions can cause your AI client to conflate results. Ask them separately for cleaner answers.

• Specify the output format. If you want a chart, table, or summary, say so. For example: "Show me monthly EC2 spend by region for Q1 as a bar chart"

Validating Responses

Because the MCP relies on an LLM, responses are not always deterministic. To validate outputs:

• Cross-reference results against your existing Finout dashboards or saved data explorers

• Expand the tool calls in your AI client to inspect the underlying filters and groupings applied

• If a response looks off, note what you asked, what you received, and what you expected - and share it with us via the submit_feedback tool

Feedback

The Finout MCP includes a built-in submit_feedback tool. After any interaction, ask your AI client to submit feedback directly: "Please submit feedback: the get_top_movers tool returned data for the wrong time period when I asked about last quarter."

You can also reach your Finout contact directly or email [email protected]. The more specific your feedback, the faster we can act on it.

FAQs

Does the Finout MCP work with enterprise or internally-built AI tools?

Yes, in most cases. Any AI client that implements the MCP standard with OAuth support can connect to the Finout MCP at https://mcp.finout.io/mcp.

In some cases, custom in-house AI tools that use the MCP protocol but implement OAuth callback registration themselves might face some issues with the initial connections. If your internal tool encounters an authorization error during setup, contact your Finout support for assistance.