Skip to main content
You do not call Condense MCP tools yourself. You ask your AI tool in plain language, and it picks the tools it needs.

​
Name what you mean

Some tools need a name before they can answer.
  • Pipeline and connector tools take a workspace name.
  • Pod and job tools take a deployment or job name and its namespace.
  • Connector logs also take a duration in milliseconds.
Your AI tool finds your environments and workspaces with the Get-all-environments and Get-all-workspaces tools. You can use names, so you do not have to look up an ID first.

​
How one question becomes several tool calls

A single question often uses more than one tool. For example: You may see several calls go by before the answer arrives. That is your AI tool working through the question.

​
What to ask

Example requests. Replace the names with your own.

​
See what is running

  • “Show me the current pipeline in the fleet-tracking workspace.” Tool: Get-Current-Pipeline.
  • “Which environments have I connected?” Tool: Get-all-environments.
  • “Which workspaces do I have access to?” Tool: Get-all-workspaces.

​
Check a connector’s configuration

  • “Show the config of connector test-connector in current pipeline.” Tool: Get-Deployed-Connector-Configs.

​
Read connector logs

  • “Get the last 5000 ms of logs for config ID 872 in the fleet-tracking workspace.” Tool: Get-Connector-Logs.

​
Check utilization and workloads

  • “How much CPU is being used?” Tool: Get-CPU-Utilization.
  • “How busy are the nodes?” Tool: Get-Node-Utilization.
  • “What is the status of the deployment fleet-api in the namespace fleet-tracking?” Tool: Get-Pod-Status.
  • “Show the resource metrics for the deployment fleet-api in the namespace fleet-tracking.” Tool: Get-Pod-Metrics.
  • “Read the details of the job nightly-sync in the namespace fleet-tracking.” Tool: Read-Job.

​
Read metrics and alerts

  • “Which metrics are available?” Tool: List-Metrics.
  • “Run the PromQL query up and show me the result.” Tool: Execute-query.
  • “What was the latest alert?” Tool: Get-Latest-Alert.

​
Deploy a connector

  • “What do I need to configure to deploy the NATS to Apache Kafka output connector?” Tool: Get-Connector-Configs-To-Deploy.
  • “What config fields does my custom input connector Saas-Application need?” Tool: Get-Custom-Connector-Configs-To-Deploy.
  • “Deploy an NATS to MongoDB connector in fleet-tracking.” Tool: Deploy-connector.

​
Ask how something works

  • “How does RBAC work in Condense?” Tool: Query-docs.

​
Tips for better answers

  • Name the workspace, the deployment or the job. It saves a round of questions.
  • Give a log duration. Connector logs are collected for a duration in milliseconds, and the default is 200. Ask for what you need, for example “the last 5000 ms”.
  • Identify the connector for logs. Give its configuration ID, its connector ID or its name.
  • Find out what a connector needs before you deploy it. Ask for the configuration variables first, then deploy with those values.
  • Check before you deploy. Deploy-connector changes your environment. Read the configuration your AI tool is about to send before you approve it.
Connector configurations can include credentials such as broker addresses, usernames and passwords. Keep real secrets out of the chat where you can.

Tool reference

What each tool does, and which one changes your environment.

Scope and permissions

Why your AI tool can or cannot do something.