Senzing MCP Prompts
Senzing offers 31 prompts. A prompt is one you invoke yourself, rather than a tool the model calls on your behalf — each has its own page with the configuration for every client that can run it.
-
analyze-data-qualityanalyze data quality
-
architect-cloud-deploymentarchitect cloud deployment
-
build-a-demobuild a demo
-
build-entity-explorer-uibuild entity explorer ui
-
build-reporting-dashboardbuild reporting dashboard
-
build-robust-error-handlingbuild robust error handling
-
build-scalable-loaderbuild scalable loader
-
build-sdk-integrationbuild sdk integration
-
choose-a-databasechoose a database
-
delete-and-erasedelete and erase
-
deployment-optionsdeployment options
-
design-er-pipelinedesign er pipeline
-
evaluate-er-resultsevaluate er results
-
explain-entity-resolutionexplain entity resolution
-
how-would-senzing-fithow would senzing fit
-
install-senzinginstall senzing
-
manage-redo-queuemanage redo queue
-
map-data-sourcemap data source
-
migrate-v3-to-v4migrate v3 to v4
-
plan-a-pocplan a poc
-
plan-replication-and-haplan replication and ha
-
platform-integrationplatform integration
-
realtime-integrationrealtime integration
-
request-eval-licenserequest eval license
-
resolve-and-searchresolve and search
-
run-entity-resolutionrun entity resolution
-
senzing-roisenzing roi
-
show-me-er-in-actionshow me er in action
-
steward-entitiessteward entities
-
troubleshoot-errortroubleshoot error
-
why-senzingwhy senzing
Senzing also offers 2 resources — data you attach as context, where a prompt is something you run.
Read from the server itself, by connecting to it and calling prompts/list on 24 September 2026.
A listing does not declare its prompts, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each prompt's arguments.