Dock for data analytics

Ad-hoc analytics asks stop drowning in Slack.

Requests, analyses, dashboards in one workspace. The SQL + reasoning + result lives next to the request, so the next similar question gets a 2-min copy-edit instead of a re-derivation.

Open in Dock Connect via MCP

Data · request queuevector/data-queue

2 analysts · 2 agents

RequestsAnalysesDashboardsDefinitions

Active requests

RequestRequesterStatus

Cohort retention by signup sourceLLexDrafting

ARR by plan tier — Q2 trendIndexerSQL drafted

Feature usage post-launchWriterSynthesizing

Churn root cause analysisDDevonReviewing

Analysis · Cohort retention

Question

SQL

Findings

writer drafting findings

Agent stack

The roles your agents fill. Bring whichever clients you already run.

Indexer

Reads new requests, finds prior analyses on similar questions, drafts SQL.

e.g. Claude Sonnet · Cursor

Writer

Drafts the analysis doc — question, SQL, findings, recommendation. The narrative around the data.

e.g. Claude Opus · GPT-5

What's in the workspace

4 surfaces, one workspace, same audit log.

Requests (table) — requester, urgency, ETA, owner.
Analyses (doc per request) — question + SQL + findings + recommendation.
Dashboards (table) — every dashboard with owner, last reviewed.
Definitions (doc) — metric definitions; the writer reads before answering.

Plug in over MCP

One server URL. Every MCP-speaking client.

Add the Dock MCP server to your client config and your agent gets typed access to the same workspace your team uses. No borrowed credentials — the agent gets its own API key, its own scopes, its own audit trail.

Claude Code · ~/.config/claude/mcp.jsonhttps://trydock.ai/api/mcp

// Add Dock to your client. Restart Claude Code; tools are typed
// against the surfaces in your workspace.
{
  "mcpServers": {
    "dock": {
      "url": "https://trydock.ai/api/mcp",
      "auth": "oauth"
    }
  }
}

// Once connected, your agent calls Dock tools by name:
//   list_rows("requests") → triage queue
//   create_row("analyses", { question, sql, findings })
//   append_doc_section("analyses/{slug}", findings_markdown)

Full docs: MCP server quickstart

Agent identity, audited

The log names the agent. Not its owner.

Every state-changing action lands in a per-workspace event stream with the actor named explicitly — human or agent. A real sample from a workspace just like yours:

08:14:08data-indexer matched request to prior analysis retention-q1

08:31:42data-writer drafted findings · 6 sections · 850 words

10:02:18LLex reviewed analysis · approved + shared to stakeholders

Start with a template

Data analytics request queue →

Run an analytics function where prior work always counts.

Dock is invite-only beta. Onboarding a small batch each week.