getEntityDetails
Get comprehensive details about a specific entity including its information, tasks, and scorecards - we can use this to check operational readiness/health of an entity.
LABSCO SUMMARY
Ownership and readiness questions get answered from the catalog rather than from a wiki page.
Catalog, scorecard, initiative and team tools cover the structured questions, and queryData is the way out when a question has no endpoint shaped for it — arbitrary SQL against DX Data Cloud, the only tool here whose scope is not fixed by the API it wraps. reviewTasks is the sole tool that changes anything; everything else reads. getInitiativeDetails combines initiatives.info and initiatives.progressReport, so status and progress arrive together.
What it is
An MCP server for a DX instance — software catalog, scorecards, initiatives, teams, and a SQL endpoint onto DX Data Cloud
What you get
- Catalog reads: listEntities with a search term and type filter, getEntityDetails for one entity together with its tasks and scorecards.
- Scorecards — the active set, and one scorecard's levels and checks in full.
- reviewTasks resolves the outstanding DX tasks on an entity, which are its failing checks.
- Initiatives filtered by priority, tag and published state, and getInitiativeDetails, which returns the initiative record and its progress report from a single call.
- Team lookup by team_id, reference_id or member emails, where the email route returns name and members and the id route returns the fuller team structure.
- queryData executes SQL against the DX Data Cloud PostgreSQL database, with information_schema there when the table layout is unknown.
Requirements
A DX instance with a populated software catalog, plus access to its DX Data Cloud PostgreSQL database for queryData.
Setup effort
One command plus a key — pip install dx-mcp-server, then supply credentials
USE CASES
01
Deciding whether a service is ready to be on call for
Find the entity in the catalog, then read its record with the tasks and scorecards attached, and open the scorecard to see which checks it is judged on.
02
Clearing the failing checks on a service you own
List the active scorecards, pull the entity's outstanding tasks, and resolve the checks that have been dealt with.
03
Reporting on whether a migration is actually moving
List the initiatives by priority or tag, then read one back with its progress report in the same call.
04
Answering a question the catalog endpoints have no shape for
Go straight to the warehouse with SQL, reading information_schema first when the table layout is not known.
05
Tracking down who owns a service when all you have is an email
List the teams, then look one up by member email for its name and members, or by id for the fuller structure.
10 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
getInitiativeDetails
Get initiative details including both the initiative info and its progress report.
Note: This calls two endpoints:
- initiatives.info
- initiatives.progressReport
getScorecardInfo
Retrieve details about a specific scorecard, including its defined levels and checks. Args: id (str): The unique ID of the scorecard.
getTeamDetails
Retrieve details for an individual team. Note that searching by team_emails will return things like the team name and members, where the search by team_id/reference_id will return more detailed information about the team structure.
listEntities
List entities from the DX software catalog.
listInitiatives
Lists all initiatives with summary information.
listScorecards
List all active scorecards. Args: cursor (str, optional): Cursor for pagination. Get from response_metadata.next_cursor in prior requests. limit (int, optional): Limit the number of scorecards per page. Must be between 1 and 50.
listTeams
List all teams in DX.
queryData
Execute a SQL query against the DX Data Cloud PostgreSQL database. Always query from information_schema if you are uncertain about which tables and columns to look at. Args: sql (str): SQL query to execute
Returns: str: Formatted query results or error message
reviewTasks
Review/resolve/complete outstanding DX tasks (failing checks).
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools when we connected. WEB_API_TOKEN enables the catalog and entity tools, and DB_URL enables queries against your Data Cloud Postgres; the hosted server at ai.getdx.com/mcp takes only the token.
Requires
- WEB_API_TOKEN in your environment
- DB_URL in your environment
Where it runs
Of the 7 documented setups, 5 run the server on your machine and 2 connect to a hosted endpoint.
CONTEXT COST
Light Standing cost
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
pip
TERMINAL
pip install dx-mcp-serverHosted endpoint
ENDPOINT URL
https://ai.getdx.com/mcpCreate a DX API token in DX → Settings → Personal access tokens → Add personal access token, select the scopes you need, and use it as <YOUR_DX_API_TOKEN> in the client’s Authorization: Bearer request header.
MCP Clients
Claude Code — remote
CLAUDE CODE — REMOTE · TERMINAL
claude mcp add --transport http dx-mcp https://ai.getdx.com/mcp --header "Authorization: Bearer <YOUR_DX_API_TOKEN>"Cursor — remote
CURSOR — REMOTE · JSON
{
"mcpServers": {
"dx-mcp": {
"url": "https://ai.getdx.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_DX_API_TOKEN>"
}
}
}
}Claude Code — pip
CLAUDE CODE — PIP · TERMINAL
claude mcp add dx-mcp-server --env DB_URL=<YOUR_DB_URL> --env WEB_API_TOKEN=<YOUR_WEB_API_TOKEN> -- $(which dx-mcp-server)Claude Desktop — pip, Cursor — pip
JSON
{
"mcpServers": {
"dx-mcp": {
"command": "dx-mcp-server",
"args": [
"run"
],
"env": {
"DB_URL": "<YOUR_DB_URL>",
"WEB_API_TOKEN": "<YOUR_WEB_API_TOKEN>"
}
}
}
}Claude Desktop — local build, Cursor — local build
JSON
{
"mcpServers": {
"dx-mcp": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_DX_MCP_SERVER>",
"run",
"-m",
"dx_mcp_server",
"run"
],
"env": {
"DB_URL": "<YOUR_DB_URL>",
"WEB_API_TOKEN": "<YOUR_WEB_API_TOKEN>"
}
}
}
}
