Secoda
Get Started
  • Getting Started with Secoda
    • Secoda as an Admin
      • Deployment options
      • Sign in options
      • Settings
      • Connect your data
        • Define Service Accounts
        • Choose which schemas to extract
      • Customize the workspace
      • Populate Questions with FAQs
      • Invite your teammates
        • Joining & Navigating between Multiple Workspaces
      • Onboard new users
        • Onboarding email templates
        • Onboarding Homepage template
        • Training session guide
      • User engagement and adoption
        • Tips & Tricks to share with new users
    • Secoda as an Editor
    • Secoda as a Viewer
      • Introduction guide
      • Requesting changes in Secoda
  • Best practices
    • Setting up your workspace
    • Integrating Secoda into existing workflows
    • Documentation best practices
    • Glossary best practices
    • Data governance
    • Data quality
    • Clean up your data
    • Tool migrations using Secoda
    • Slack <> Questions workflow
    • Defining resources workflow
    • Streamline data access: Private and public teams workflow
    • Exposing Secoda to external clients
  • Resource Management
    • Editing Properties
      • AI Description Editor
      • Bulk Editing
      • Propagation
      • Templates
    • Resource Sidesheet
    • Assigning Owners
    • Custom Properties
    • Tags
      • Custom Tags
      • PII Identifier
      • Verified Identifier
    • Import and Export Resources
    • Related Resources
  • User Management
    • Roles
    • Teams
    • Groups
  • Integrations
    • Integration Settings
    • Data Warehouses
      • BigQuery
        • BigQuery Metadata Extracted
      • Databricks
        • Databricks Metadata Extracted
      • Redshift
        • Redshift Metadata Extracted
      • Snowflake
        • Snowflake Metadata Extracted
        • Snowflake Costs
        • Snowflake Native App
      • Apache Hive
        • Apache Hive Metadata Extracted
      • Azure Synapse
        • Azure Synapse Metadata Extracted
      • MotherDuck
        • MotherDuck Metadata Extracted
      • ClickHouse
        • ClickHouse Metadata Extracted
    • Databases
      • Druid
        • Druid Metadata Extracted
      • MySQL
        • MySQL Metadata Extracted
      • Microsoft SQL Server
        • Page
        • Microsoft SQL Server Metadata Extracted
      • Oracle
        • Oracle Metadata Extracted
      • Salesforce
        • Salesforce Metadata Extracted
      • Postgres
        • Postgres Metadata Extracted
      • MongoDB
        • MongoDB Metadata Extracted
      • Azure Cosmos DB
        • Azure Cosmos DB Metadata Extracted
      • SingleStore
        • SingleStore Metadata Extracted
      • DynamoDB
        • DynamoDB Metadata Extracted
    • Data Visualization Tools
      • Amplitude
        • Amplitude Metadata Extracted
      • Looker
        • Looker Metadata Extracted
      • Looker Studio
        • Looker Studio Metadata Extracted
      • Metabase
        • Metabase Metadata Extracted
      • Mixpanel
        • Mixpanel Metadata Extracted
      • Mode
        • Mode Metadata Extracted
      • Power BI
        • Power BI Metadata Extracted
      • QuickSight
        • QuickSight Metadata Extracted
      • Retool
        • Retool Metadata Extracted
      • Redash
        • Redash Metadata Extracted
      • Sigma
        • Sigma Metadata Extracted
      • Tableau
        • Tableau Metadata Extracted
      • ThoughtSpot
        • ThoughtSpot Metadata Extracted
      • Cluvio
        • Cluvio Metadata Extracted
      • Hashboard
        • Hashboard Metadata Extracted
      • Lightdash
        • Lightdash Metadata Extracted
      • Preset
        • Preset Metadata Extracted
      • Superset
        • Superset Metadata Extracted
      • SQL Server Reporting Services
        • SQL Server Reporting Services Metadata Extracted
      • Hex
        • Hex Metadata Extracted
      • Omni
        • Omni Metadata Extracted
    • Data Pipeline Tools
      • Census
        • Census Metadata Extracted
      • Stitch
        • Stitch Metadata Extracted
      • Airflow
        • Airflow Metadata Extracted
      • Dagster
        • Dagster Metadata Extracted
      • Fivetran
        • Fivetran Metadata Extracted
      • Glue
        • Glue Metadata Extracted
      • Hightouch
        • Hightouch Metadata Extracted
      • Apache Kafka
        • Apache Kafka Metadata Extracted
      • Confluent Cloud
        • Confluent Cloud Metadata Extracted
      • Polytomic
        • Polytomic Metadata Extracted
      • Matillion
        • Matillion Metadata Extracted
      • Airbyte
        • Airbyte Extracted Metadata
      • Informatica
        • Informatica Metadata Extracted
      • Azure Data Factory
        • Azure Data Factory Metadata Extracted
    • Data Transformation Tools
      • dbt
        • dbt Cloud
          • dbt Cloud Metadata Extracted
        • dbt Core
          • dbt Core Metadata Extracted
      • Coalesce
        • Coalesce Metadata Extracted
      • Dataform
        • Dataform Metadata Extracted
    • Data Quality Tools
      • Cyera
      • Dataplex
        • Dataplex Metadata Extracted
      • Great Expectations
        • Great Expectations Metadata Extracted
      • Monte Carlo
        • Monte Carlo Metadata Extracted
      • Soda
        • Soda Metadata Extracted
    • Data Lakes
      • Google Cloud Storage
        • GCS Metadata Extracted
      • AWS S3
        • S3 Metadata Extracted
    • Query Engines
      • Trino
        • Trino Metadata Extracted
    • Custom Integrations
      • File Upload
        • CSV File Format
        • JSONL File Format
        • Maintain your Resources
      • Marketplace
        • Secoda SDK
        • Upload and Connect your Marketplace Integration
        • Publish the Integration
        • Example Integrations
      • Secoda Fields Explained
    • Security
      • Connecting via Reverse SSH Tunnel
      • Connecting via SSH Tunnel
      • Connecting via VPC Peering
      • Connecting via AWS Cross Account Role
      • Connecting via AWS PrivateLink
        • Snowflake via AWS PrivateLink
        • AWS Service via AWS PrivateLink
      • Recommendations to Improve SSH Tunnel Concurrency on SSH Bastion
    • Push Metadata to Source
  • Extensions
    • Chrome
    • Confluence
      • Confluence Metadata Extracted
      • Confluence best practices
    • Git
    • GitHub
    • Jira
      • Jira Metadata Extracted
    • Linear
    • Microsoft Teams
    • PagerDuty
    • Slack
      • Slack user guide
  • Features
    • Access Requests
    • Activity Log
    • Analytics
    • Announcements
    • Audit Log
    • Automations
      • Automations Use Cases
    • Archive
    • Bookmarks
    • Catalog
    • Collections
    • Column Profiling
    • Data Previews
    • Data Quality Score
    • Documents
      • Comments
      • Embeddings
    • Filters
    • Glossary
    • Homepage
    • Inbox
    • Lineage
      • Manual Lineage
    • Metrics
    • Monitors
      • Monitoring Use Cases
    • Notifications
    • Policies
    • Popularity
    • Publishing
    • Queries
      • Query Blocks
        • Chart Blocks
      • Extracted Queries
    • Questions
    • Search
    • Secoda AI
      • Secoda AI User Guide
      • Secoda AI Use Cases
      • Secoda MCP Server
      • Secoda AI Capabilities
      • Secoda AI Security FAQs
    • Sharing
    • Views
  • Enterprise
    • SAML
      • Okta SAML
      • OneLogin SAML
      • Microsoft Azure AD SAML
      • Google SAML
      • SCIM
      • SAML Attributes
    • Self-Hosted
      • Additional Resources
        • Additional Environment Variables
          • PowerBI OAuth Application (on-premise)
          • Google OAuth Application (on-premise)
          • Github Application (on-premise)
          • OpenAI API Key Creation (on-premise)
          • AWS Bucket with Access Keys (on-premise)
        • TLS/SSL (Docker compose)
        • Automatic Updates (Docker compose)
        • Backups (Docker compose)
        • Outbound Connections
      • Self-Hosted Changelog
    • SIEM
      • Google Chronicle
  • API
    • Authentication
    • Reference
      • Getting Started
      • Helpful Information
      • Audit Logs
      • Charts
      • Collections
      • Columns
      • Custom Properties
      • Dashboards
      • Databases
      • Documents
      • Events
      • Groups
      • Integrations
      • Lineage
      • Monitors
      • Resources
      • Schemas
      • Tables
      • Tags
      • Teams
      • Users
      • Questions
      • Queries
      • Models
    • Examples
  • FAQ
  • Policies
    • Terms of Use
    • Secoda AI Terms
    • Master Subscription Agreement
    • Privacy Policy
    • Security Policy
    • Accessibility Statement
    • Data Processing Agreement
    • Subprocessors
    • Service Level Agreement
    • Bug Bounty Program
  • System Status
  • Changelog
Powered by GitBook
On this page
  • What is Model Context Protocol?
  • How MCP Works
  • Benefits of Using MCP
  • Available Tools
  • Setting things up
  • Secoda MCP
  • Features
  • Getting Started
  • Integration with Tools
  • Troubleshooting
  • License
  • Security
  • FAQ

Was this helpful?

  1. Features
  2. Secoda AI

Secoda MCP Server

Learn how to use the Model Context Protocol (MCP) to enable AI agents to securely access and interact with your Secoda data catalog, run SQL queries, and explore data lineage.

What is Model Context Protocol?

MCP is a protocol that enables AI tools and applications to connect with Secoda's data catalog and services in a secure, standardized way. It provides a structured method for AI models to:

  • Search and retrieve data assets (tables, columns, dashboards, documentation)

  • Execute SQL queries against your connected data warehouses

  • Access data lineage and relationships between entities

  • Retrieve business glossary terms and definitions

  • Access Secoda documentation and knowledge articles

How MCP Works

Secoda hosts the MCP server as part of your workspace that provides access to your data catalog through a secure, authenticated interface.

When an AI tool or application needs to access Secoda data:

  1. The tool connects to Secoda's MCP server endpoints

  2. Authentication verifies the user's workspace and AI permissions

  3. The tool can then access relevant Secoda data and functionality

  4. All operations respect your existing data governance and access controls

Benefits of Using MCP

  • Secure Access: All data access is authenticated and respects workspace permissions

  • Live Data Queries: Execute SQL queries directly against your data warehouses

  • Comprehensive Catalog Access: Search across all your data assets and documentation

  • Data Lineage: Understand upstream and downstream dependencies

  • Standardized Interface: Consistent interaction pattern across different AI tools

Available Tools

The Secoda MCP server provides the following tools:

Tool
Description

search_data_assets

Search for tables, columns, charts, and dashboards

search

General search across all Secoda resources including documentation

run_sql

Execute SQL queries against your connected data warehouses

retrieve_entity

Get detailed information about a specific data entity

entity_lineage

Explore upstream and downstream data dependencies

glossary

Access business terms and definitions from your glossary

get_secoda_docs

Retrieve Secoda documentation and knowledge articles

chart

Work with charts and visualizations

Setting things up

Secoda MCP

Secoda MCP is a custom server built with FastMCP that provides access to Secoda's data tools and functionalities.

Features

  • Access to Secoda's data assets search

  • Access to documentation search

  • Ability to run SQL queries directly

  • Integration with Secoda's data catalog

  • Entity lineage visualization

  • Glossary term retrieval

Getting Started

Prerequisites

  • Python 3.8 or higher

  • Access to Secoda's API

  • API token for authentication with the Secoda API (can be generated at https://app.secoda.co/settings/api if you're an admin)

Installation

  1. Clone the repository:

    git clone https://github.com/secoda/secoda-mcp.git
    cd secoda-mcp
  2. Install dependencies:

    # Install runtime dependencies
    python -m pip install -r requirements.txt

Environment Variables

Variable
Description
Default

API_TOKEN

Required token for API authentication

None (Required)

API_URL

URL of the Secoda API endpoint

https://app.secoda.co/api/v1/

Instance URL Note

If you're using a regional instance or self-hosted deployment of Secoda, replace app.secoda.co with your specific instance URL:

  • EU region: eu.secoda.co

  • APAC region: apac.secoda.co

  • Self-hosted: Your custom domain (e.g., secoda.yourcompany.com)

Integration with Tools

Using with Cursor

To integrate Secoda MCP with Cursor, add the following configuration to your ~/.cursor/mcp.json file:

{
    "mcpServers": {
        "secoda-mcp": {
            "command": "python",
            "args": [
                "/path/to/secoda-mcp/server.py"
            ],
            "env": {
                "API_TOKEN": "your-api-token",
                "API_URL": "https://app.secoda.co/api/v1/"
            }
        }
    }
}

Replace /path/to/secoda-mcp/server.py with the actual path to your server.py file, set your API token, and update the API_URL with your Secoda instance URL if not using app.secoda.co.

Using with Claude

To integrate Secoda MCP with Claude Desktop, add the following to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
    "mcpServers": {
        "secoda-mcp": {
            "command": "python",
            "args": [
                "/path/to/secoda-mcp/server.py"
            ],
            "env": {
                "API_TOKEN": "your-api-token",
                "API_URL": "https://app.secoda.co/api/v1/"
            }
        }
    }
}

Replace /path/to/secoda-mcp/server.py with the actual path to your server.py file, set your API token, and update the API_URL with your specific Secoda instance URL if not using app.secoda.co. To access the Claude Desktop configuration file, open the Claude menu, go to "Settings", click on "Developer" in the left-hand bar, and then click on "Edit Config".

After updating the configuration, restart Claude Desktop to apply the changes.

Using with Other Tools

Secoda MCP can be integrated with various other tools:

  • VS Code: Use the VS Code extension for MCP servers

  • JetBrains IDEs: Install the MCP plugin from the marketplace

  • Command Line: Access MCP functionalities directly via the CLI

  • Web Applications: Embed MCP capabilities in web apps through the REST API

Troubleshooting

  • If you encounter connection issues, ensure Secoda's API is running at the configured URL

  • If you get authorization errors, verify your API token is correct and properly set as an environment variable

  • For permission errors, check your authentication settings in your Secoda account

License

This project is licensed under the MIT License - see the LICENSE file for details.

Security

If you discover any security related issues, please email security@secoda.co instead of using the issue tracker.

FAQ

Why am I getting authentication errors? Ensure you have the correct permissions in your Secoda workspace and that MCP is enabled by your administrator.

I'm seeing connection timeouts MCP connections can be sensitive to network conditions. Try restarting your AI client or check with your network administrator about proxy settings.

Last updated 18 days ago

Was this helpful?