by arturborycki
Provides SQL query execution, schema exploration, and built‑in data‑analysis tools for Teradata databases through a Model Context Protocol server.
Teradata MCP Server offers a set of MCP‑compatible tools that let users run SELECT statements, explore databases and tables, and perform common data‑quality and statistical analyses directly against a Teradata instance.
Add the server configuration to claude_desktop_config.json
(or run it as a Docker container). The core command uses uv to start the MCP server and requires the DATABASE_URI
environment variable pointing to the Teradata connection string. For Docker, update docker‑compose.yml
with the same environment variables and launch with docker compose up
.
query
– execute arbitrary SELECT statements and receive results as JSON objects.list_db
, list_tables
, show_tables_details
– discover databases, list objects, and retrieve column metadata.list_missing_values
, list_negative_values
, list_distinct_values
, standard_deviation
– quick data‑quality checks and basic statistics.Q: Which command starts the server?
A: Use uv run teradata-mcp
(or the Docker compose workflow). The configuration expects a DATABASE_URI
like teradata://user:passwd@host
.
Q: Do I need to install anything manually?
A: Install the UV tool (pip install uv
) and ensure the Python environment can reach the Teradata driver. Docker users only need Docker.
Q: How is authentication handled?
A: Set KEYCLOAK_ENABLED=true
and provide the Keycloak server URL, realm, client ID, and secret as environment variables.
Q: Can I add custom tools?
A: Yes, MCP servers are extensible; additional Python modules can be added to the repository and referenced in the tools
directory.
Q: What output format do the tools return? A: All tools return JSON‑serializable structures (arrays of objects, simple lists, or key‑value maps).
A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through Teradata. This server enables running SQL queries, analyzing business data
The server offers six core tools:
query
query
(string): The SELECT SQL query to executelist_db
list_tables
db_name
(string): Database nameshow_tables_details
table_name
(string): Name of the tabledb_name
(string): Name of the databaselist_missing_values
list_negative_values
list_distinct_values
standard_deviation
# Add the server to your claude_desktop_config.json
{
"mcpServers": {
"teradata": {
"command": "uv",
"args": [
"--directory",
"/Users/MCP/mcp-teradata",
"run",
"teradata-mcp"
],
"env": {
"DATABASE_URI": "teradata://user:passwd@host"
}
}
}
}
Make sure to edit docker-compose.yml and update environment variable
docker compose build
docker compose up
UV:
uv build
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
KEYCLOAK_ENABLED=true
KEYCLOAK_SERVER_URL=https://your-keycloak-server.com
KEYCLOAK_REALM=mcp-realm
KEYCLOAK_CLIENT_ID=teradata-mcp-client
KEYCLOAK_CLIENT_SECRET=your-client-secret
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "teradata": { "command": "uv", "args": [ "--directory", "/path/to/mcp-teradata", "run", "teradata-mcp" ], "env": { "DATABASE_URI": "teradata://user:passwd@host", "KEYCLOAK_ENABLED": "true", "KEYCLOAK_SERVER_URL": "https://your-keycloak-server.com", "KEYCLOAK_REALM": "mcp-realm", "KEYCLOAK_CLIENT_ID": "teradata-mcp-client", "KEYCLOAK_CLIENT_SECRET": "your-client-secret" } } } }
Explore related MCPs that share similar capabilities and solve comparable challenges
by googleapis
An MCP server that streamlines database tool development by handling connection pooling, authentication, observability, and secure access, allowing agents to interact with databases via natural language.
by bytebase
Provides a universal gateway that lets MCP‑compatible clients explore and query MySQL, PostgreSQL, SQL Server, MariaDB, and SQLite databases through a single standardized interface.
by designcomputer
Enables secure interaction with MySQL databases via the Model Context Protocol, allowing AI applications to list tables, read contents, and execute queries safely.
by benborla
Provides read‑only access to MySQL databases for large language models, allowing schema inspection and safe execution of SQL queries.
by ClickHouse
Enables AI assistants to run read‑only ClickHouse queries, list databases and tables, and execute embedded chDB queries through an MCP interface.
by chroma-core
Offers an MCP server exposing Chroma's vector database capabilities for LLM applications, supporting collection and document management, multiple embedding functions, and flexible client types such as in‑memory, persistent, HTTP, and cloud.
by kiliczsh
Enables LLMs to interact with MongoDB databases via a standardized interface, offering schema inspection, query execution, aggregation, and write capabilities, with optional read‑only mode and smart ObjectId handling.
by domdomegg
Provides read and write access to Airtable bases for AI systems, enabling inspection of schemas and manipulation of records.
by XGenerationLab
A Model Context Protocol (MCP) server that enables natural language queries to databases