Precisely MCP server - Precisely Data Integrity Suite

Data Integrity Suite
Product
Spatial_Analytics
Data_Integration
Data_Enrichment
Data_Governance
Precisely_Data_Integrity_Suite
geo_addressing_1
Data_Observability
Data_Quality
dis_core_foundation
Services
Spatial Analytics
Data Integration
Data Enrichment
Data Governance
Geo Addressing
Data Observability
Data Quality
Core Foundation
ft:title
Data Integrity Suite
ft:locale
en-US
PublicationType
pt_product_guide
copyrightfirst
2000
copyrightlast
2026

The Precisely MCP Server is a Precisely‑hosted implementation of the Model Context Protocol (MCP) that enables AI agents and large language models (LLMs) to securely discover and invoke Precisely Data Integrity Suite capabilities through natural‑language interactions, without building custom integrations for each workflow.

MCP is an open, industry-standard protocol that allows AI clients to interact programmatically with tools, APIs, and data sources. Precisely uses this standard to expose its suite APIs as self‑describing, discoverable tools that AI agents can understand and use dynamically.

Limited Availability: This feature is currently available only in select workspaces and might be subject to change before general availability.

What the Precisely MCP Server does

The Precisely MCP Server acts as a secure adapter layer between AI agents (such as Microsoft Copilot, Claude, or IDE‑based agents) and the Data Integrity Suite APIs. Instead of users or developers manually calling APIs, the MCP Server allows AI agents to:
  • Interpret a users natural‑language intent
  • Discover relevant Precisely capabilities as tools
  • Implement the appropriate actions
  • Return results in clear, human‑readable responses

This removes the need for users to log into the Suite UI, write API calls, or switch contexts across tools.

How to access the DIS MCP server

  1. Enabling the DIS MCP Server in VS Code
    1. Install prerequisites
      • Download and install VS Code from https://code.visualstudio.com
      • Install the GitHub Copilot extension
        • Press Ctrl+Shift+X
        • Search GitHub Copilot
        • Click Install
      • Sign in to GitHub Copilot when prompted
    2. Create a workspace folder
      • Create a new folder called DIS MCP in your .c drive
      • Go to VSCode file > Open folder > DIS MCP
    3. Get your encoded API key
      • Log into your Data Integrity Suite workspace at https://cloud.precisely.com.
      • Click Account.
      • Click the API Keys tab.
      • Click Generate API Key or select an existing API key.
      • After the API Key is generated, it must be base64-encoded before use. The easiest way is to let Copilot do it for you:
        • Open Copilot Chat (Ctrl+Alt+I).
        • Make sure you are in Agent mode (use the dropdown at the bottom of the chat input).
        • Type the following message (replace the values with your real credentials)

          Encode my_api_key:my_api_secret in base64

        • Copilot will return the encoded string. Copy the encoded string as it will be required to setup the MCP server definition.
    4. Add the MCP configuration file
      • Inside your opened workspace folder, create a .github folder
      • Right click the .github folder, create a file named mcp.json.
      • Paste the following content
         {
  "servers": {
    "dis-mcp": {
      "type": "http",
      "url": "https://api.cloud.precisely.com/dis-mcp/mcp",
      "headers": {
        "Authorization": "Apikey base64(api_key:api_secret)"
      }
    }
  }
}
      • Replace <api_key> and <api_secret> with the encoded key:secret value generated in the previous step.
      • Save the file.
    5. Verify the connection
      • Press Ctrl+Shift+P and type MCP: List Servers
      • You should see DIS-MCP listed with status Running.
        Tip: If it shows an error, double-check that your encoded API key is correct (re-run the Copilot encoding step).
  2. Microsoft Copilot Studio
    Prerequisites
    • Access to Microsoft Copilot Studio with permission to create agents and tools
    • Generative orchestration enabled in your agent (required for MCP)
      1. Create a New Agent
        1. Open Microsoft Copilot Studio
        2. Select Agents from the left navigation
        3. Choose Create blank agent
        4. Provide:
          • Name (e.g., "DIS MCP Assistant")
          • Description (e.g., "An agent that searches, describes, and runs Precisely DIS actions via MCP")
          • Instructions - Example: "You help users discover and run Precisely data intelligence actions. Use the DIS MCP tools to search for available actions, describe their inputs and outputs, and run them on behalf of the user."
        5. Select your agent's model (e.g., GPT-4o or the default model available in your environment)
        6. Save the agent.
      2. Enable Generative Orchestration
        1. Open your agent
        2. Go to Settings
        3. Ensure Generative orchestration is turned On
      3. Add the DIS MCP server as a tool
        1. Open your agent
        2. Go to the Tools page
        3. Select Add a tool → Create New → Model Context Protocol.
        4. This launches the MCP onboarding wizard
      4. Configure the MCP server connection

        Provide the following details in the wizard:

        Field Value
        Server name 
        Precisely DIS MCP
        Description 
        Precisely DIS MCP server - search, describe, and execute data intelligence actions
        Server URL https://api.cloud.precisely.com/dis-mcp/mcp

        Authentication - Select API Key

        • Type: Header
        • Header name: Authorization

        Click Create. This will create the MCP connection.

      5. Connect to the DIS MCP server
        After the MCP tool is created, you must explicitly connect it before the agent can call its tools.
        1. On the Add Tools page, Connection shows Not connected
        2. Click the dropdown next to it and select Create new connection
        3. When prompted, enter your API Key value created above.
        4. Click Create
        5. The created connection should now be visible
        Click Add and Configure - the tool will appear on the Tools page.
      6. Verify DIS MCP tools are available

        After adding the MCP server, three core tools become automatically available to the agent:

        Tool Purpose
        precisely_actions_search Discover actions by natural language goal
        precisely_actions_describe Get full schema and examples for a specific action
        precisely_actions_execute Run an action with provided arguments

        Tool changes on the MCP server are dynamically reflected in Copilot Studio.

      7. Test the Agent via chat

        Open Test your agent in Copilot Studio and try a few sample queries. The agent will automatically select and call the appropriate DIS MCP tool based on what you ask.

      8. Publish and share
        1. Select Publish
        2. Choose a channel (e.g., Microsoft Teams, Microsoft 365)
        3. Configure visibility and submit for approval if required

Validating connectivity via chat

After publishing, put your Copilot chat instance into Agent mode, then validate connectivity via chat. Run the following queries to confirm the MCP server is connected and working correctly.
  1. Discovery: Search for actions related to geocoding an address

    You should see it invoke the precisely_actions_search tool and return a list of matching actions.

  2. Detail: Describe the geocode.address action

    You should see it invoke the precisely_actions_describe tool and return the action's schema and examples.

  3. Execution: What's the flood risk for 1600 Pennsylvania Ave NW, Washington, DC?

    You should see it invoke precisely_actions_execute and return a result. An authentication error means your API key is invalid or lacks permission to perform actions. Re-generate and re-encode it, then update your configuration.

For more information refer to API credential and authentication.