Delegate to Agent0 via MCP

The Dash0 MCP Server doesn't only expose individual read-only telemetry tools. It can also hand a whole investigation to Agent0 through the runTask tool, so Agent0 forms hypotheses, runs its own queries across metrics, logs, and traces, and reports back, instead of your AI assistant assembling those queries itself.

What It Is

• Delegation, not query assembly: runTask sends a question to Agent0 and lets it investigate, rather than requiring your assistant to work out which telemetry tools to call and in what order.
• Read-only over MCP: Agent0 investigates and reports. It does not apply changes through this path. It cannot create dashboards or check rules, open pull requests, or write to Dash0 or any connected system. Those capabilities exist in Chat and Automations, not over MCP.

When to Use It

• Open-ended or underspecified questions that span metrics, logs, and traces: incident investigation, "why is X slow or failing," impact analysis, anything that requires forming and testing a hypothesis. Agent0 works out the right queries instead of you or your assistant assembling them.
• A single, already-known value: use the matching direct telemetry tool instead. It's faster and consumes no credits.

Cost

Delegating to Agent0 consumes Agent0 credits, roughly 1-2 credits for a full investigation depending on how many steps it takes. See Pricing for the current credit rate.

The other Dash0 MCP tools, the direct telemetry queries like getMetricQuery, getLogRecords, or getFailedChecks, consume nothing. That's the tradeoff: delegation costs credits because Agent0 does the investigative work; calling a specific tool for a value you already know how to ask for doesn't.

An administrator controls whether Agent0 is available over MCP. See Disabling Agent0 delegation below.

Mechanics

Delegation uses two MCP tools together.

runTask

Starts or continues an Agent0 investigation.

• message and dataset are required. dataset is the dataset to query. Use the listDatasets tool to discover available datasets.
• timeoutSeconds (default 25, max 45): how long runTask waits inline for Agent0's answer. If Agent0 finishes within this window, you get the answer directly. If not, runTask hands back a thread link and Agent0 keeps working in the background rather than being cut off.
• threadIdOrUrl (optional): pass a previous thread's ID or URL to continue that conversation instead of starting a new one.
• networkLevel (default full): controls what the agent can reach on the network while it investigates. See below.
• modelClass (optional): how capable a model runs the task — light, standard, advanced, or premium. Omit to use the default configured for this connection. A level this deployment does not offer is rejected, naming the ones it does.
• reasoningEffort (optional): how deeply Agent0 reasons — low, medium, high, xhigh, or max. Omit to run at the level's own default depth. See Model Selection.

On connect, the server tells your assistant which level this connection runs unasked and which others it may ask for. That default comes from the MCP row in Settings → Agent0. A connection authenticated by a machine token has no person behind it, so it runs the Dash0 default instead.

waitForTask

Blocks until an in-flight runTask thread finishes, then returns its final answer.

• threadIdOrUrl and dataset are required, matching the thread runTask handed back.
• timeoutSeconds (default 300, max 600): how long to block waiting for the result.

If an investigation is still running after waitForTask's timeout, call it again with the same thread rather than starting over. getAgent0ThreadStatus and getAgent0ThreadContent can also inspect a backgrounded thread's progress without blocking, and listAgent0Threads finds threads by title if the link was lost.

networkLevel

The same egress concept as Agent0 Chat's network mode, exposed here as a per-call parameter:

• full (default): unrestricted outbound access.
• trusted_only: a curated allowlist of common package registries, source control, and cloud SDKs. See the full trusted hosts list.
• no_network: no outbound network access. Some connectors won't be available.

Disabling Agent0 delegation

Delegation can be switched off for a whole organization, or per client for a single user.

For the whole organization

An organization admin can turn off Agent0 via MCP under Settings → Agent0. With it off, Agent0's delegation tools (runTask, waitForTask, and the thread inspection tools) and the use-agent0 skill resource are removed from the Dash0 MCP Server for every member of the organization. The read-only telemetry tools stay available, so assistants keep working and stop consuming credits.

The setting is opt-out: if an admin never touches it, delegation stays on.

Use this when you want a billing guarantee rather than a per-developer convention, since it applies regardless of which client each person connects with.

For a single client

There is no per-user server-side setting. An individual who wants to keep delegation off in one editor, while the organization leaves it on, does so in the client connecting to the Dash0 MCP Server.

Claude Code

Deny the specific tools in permissions.deny, using the pattern mcp__<server>__<tool>, where <server> is whatever name you gave the Dash0 MCP server when you added it (check with claude mcp list if unsure):

12345678
{
  "permissions": {
    "deny": [
      "mcp__dash0__runTask",
      "mcp__dash0__waitForTask"
    ]
  }
}

The rest of the server's tools stay available. Denying the bare server name (mcp__dash0) removes the whole server instead.

Claude.ai connectors

Claude.ai doesn't have a settings.json equivalent. Individual tools are toggled from the conversation itself: open the Search and tools menu (the + button, or /, in the message composer) and turn off runTask and waitForTask under the Dash0 connector.

Cursor

Cursor has no config-file option for disabling individual tools; mcp.json only configures which servers connect. Disable specific tools from Settings → Tools & MCP, expand the Dash0 server, and toggle off runTask and waitForTask.

Further Reading

• About Agent0 — Overview of the AI layer built into Dash0
• Use AI in Dash0 — Connect external AI tools to Dash0 observability data
• Investigate & Analyze — How Agent0 investigates in Chat
• Use MCP in Chat and Automations — Connecting external MCP servers into Agent0, the opposite direction
• Key Concepts — Reference terminology and mental model