Treasure Data

Treasure Data CDP

Treasure Data pairs a remote documentation server with a local tdx server that can query tenant data, manage segments, and run workflows through CLI-backed tools.

Marketing automation, lifecycle & CDPSystem of engagementExtensible SaaS
An illustration of access surfaces surrounding a governed system.
System roleSystem of engagement
Access maturityExtensible SaaS
MCP supportOfficial MCP server
Reference updatedNot stated by publisher
BYO-UI reviewedJul 22, 2026

Concrete capability record

Data, retrieval, actions, identity, and operating limits

A field-by-field summary of what the reviewed first-party references actually support. Publisher update dates and BYO-UI review dates are shown separately below.

01 · Records and state owned

tdx command definitions, profiles and sites, databases, tables, schemas, SQL results, segments, workflow projects, runs and schedules, plus Treasure Data documentation.

02 · Data you can retrieve

Search the installed tdx command catalog, execute authorized query and inspection commands, list database or workflow state, and search API and product documentation.

03 · Actions and write paths

tdx_run can invoke any tdx CLI command except an explicit blocked set, including segment creation and workflow execution when the active credentials authorize them.

04 · Authentication and permissions

The local server inherits existing tdx authentication, optionally selected by TDX_PROFILE or TDX_API_KEY with TDX_SITE; resulting tenant privileges govern every command.

05 · Monitoring, approval, and recovery

Treat tdx_search as discovery and tdx_run as command execution; display the active profile, site, full command, arguments, target objects, and expected mutation before approval.

06 · Limits and caveats

Tenant operations require a locally installed tdx server; the remote server covers documentation. Each tdx_run command has a 15-minute timeout.

Agent access

MCP support

Official MCP serverTreasure Data tenant-data MCP plus docs MCPCurrent documented service

Support: Official MCP server

Read scope: Expose tdx command discovery, authorized tenant inspection and SQL results, segment or workflow state, and remote documentation while preserving profile, site, database, and command context.

Write scope: Assume any nonblocked tdx command can run under current credentials; distinguish query reads from segment, workflow, schedule, secret, or other state-changing commands before execution.

Authentication: Platform MCP runs locally and uses the tdx authentication chain, with optional profile or API-key and site environment overrides; documentation MCP is a separate remote endpoint.

Approval boundary: Require confirmation after command discovery and before tdx_run for segment changes, workflow runs or schedules, secret operations, and any command whose effects are not read-only.

Protocol does not erase product boundaries.

Confirm the current tool catalog, plan, region, scopes, rate limits, terms, and write behavior before implementation.

Editorial assessment

Access-maturity dimensions

A comparative architecture lens—not a quality score, market ranking, or buying recommendation. Scale: 1–5.

Data access4
Action access4
Event access1
Identity4
Governance4
Agent access4
UI extensibility4
Portability3
Observability3
Documentation2

Proposed customer-shaped experiences

What customers could create on top.

The output could be an export, report, graph, artifact, application, agent, workflow, or downstream feed. These proposals are derived from documented access—not claims that Treasure Data ships them.

Single-platform patterns

  • Enterprise audience, segment, and activation room
  • Lifecycle journey debugger
  • Audience activation workbench
  • Campaign QA and approval room
Use in the brief builder →

Multi-platform compositions

  • Treasure Data CDP + CRM or commerce system: lifecycle journey debugger
  • Treasure Data CDP + warehouse or CDP + content-production platform: cross-system decision workspace
Explore composition recipes →

Evidence and dates

First-party references, with publisher and review dates separated

“Publisher updated” is shown only when the page exposes an update date. “BYO-UI reviewed” records when this research checked the reference. A missing publisher date is reported as missing—not replaced with the review date.

4 recorded sources
MCP / agent-role validationRepresentative source
https://docs.treasure.ai/getting-started/ai ↗

Treasure Data provides tenant-data tooling through its CLI/ecosystem and a separate documentation-oriented server.

Publisher updated
Not stated by publisher
BYO-UI reviewed
Jul 12, 2026

Targeted first-party MCP/agent-role review; broader API inventory retained

APISource inventory
https://api-docs.treasuredata.com/ ↗

First-party API reference or API overview recorded for this platform.

Publisher updated
Not stated by publisher
BYO-UI reviewed
Jul 12, 2026

Full-profile first-party re-verification on 2026-07-12; see the private audit ledger.

Developer docsSource inventory
https://api-docs.treasuredata.com/en/tools/pytd/quickstart ↗

Reverified the named access facet exactly as bounded by the reviewed first-party record.

Publisher updated
Not stated by publisher
BYO-UI reviewed
Jul 12, 2026

Full-profile first-party re-verification on 2026-07-12; see the private audit ledger.

HomepageSource inventory
https://www.treasuredata.com/ ↗

First-party product homepage used to confirm product identity and current positioning.

Publisher updated
Not stated by publisher
BYO-UI reviewed
Jul 10, 2026

Inventory source: structurally normalized; content was not individually reopened in this pass.

Verified fact

Tied to cited first-party evidence reviewed for this profile.

Source inventory

Official links recorded for deeper research but not necessarily reopened endpoint by endpoint.

Editorial assessment

System role, maturity interpretation, and architectural boundary.

Proposed design

Interface patterns and compositions—not vendor product claims.