StateSet API Docs

Start with the workflow trial or the platform MCP walkthrough for onboarding, accelerator status, and first-value checks. Manage a brand’s response-automation config from Claude. The MCP server is the already-running engine API — there is no separate process to deploy.


Server name	`stateset-engine`
HTTP endpoint	`POST https://api.workstream.stateset.com/v1/mcp`
stdio (local)	`engine-api mcp-stdio`
Protocol	MCP `2025-06-18`, JSON-RPC over Streamable HTTP
Auth	`Authorization: Bearer <api-key>`

The transport is POST-only; GET returns 405 and compliant clients fall back to POST. Auth supports per-brand API keys and configured OAuth access. Use a connection scoped to the intended tenant and operations; reserve global admin credentials for platform administration. Inspect the tools and input schemas exposed by your actual connection.

Tools

Tool	Purpose
`list_brands`	Brands visible to the caller — id, slug, status, config version
`get_brand_config`	Read a brand’s current `deterministic_config` and version
`get_brand_scorecard`	Closed-loop quality rates (approval, automation, escalation) so edits are grounded in real performance
`list_config_versions`	Published config history, for audit
`propose_config_patch`	Apply JSON-Pointer edits and return the result without saving
`validate_config`	Validate a proposed or current config
`apply_config`	Commit a new config through the audited, versioned pipeline
`get_config_version`	Read one published version in full, config snapshot included
`draft_config`	Draft a complete candidate config from raw material — brand voice, policies, macros
`simulate_skip_check`	Dry-run skip rules against real traffic before applying a change
`get_eval_cases`	Build eval cases from the brand’s most recent real tickets
`evaluate_config`	Replay those cases against a candidate config and score the outputs
`evaluate_golden`	Score a candidate against the brand’s standing golden set of human-corrected replies
`validate_brand`	Full readiness validation — config rules plus connector health
`activate_brand`	Activate the brand through the audited activation pipeline

apply_config requires a change_note and expected_config_version for optimistic concurrency — so two people editing the same brand can’t silently overwrite each other.

Onboarding and operating tools

Tool	Purpose
`list_bootstrap_templates` / `bootstrap_brand`	Select a supported starting configuration and create a brand
`connect_brand_connectors`	Connect providers for that brand
`run_onboarding_accelerator`	Discover, harvest, draft/apply, register webhooks, activate an eligible shadow brand, and queue replay
`get_onboarding_accelerator_status`	Inspect job progress and per-step failures or skips
`get_trial_report`	Inspect what ticket replays would have produced
`get_onboarding_funnel`	Identify the next incomplete milestone and observed timings
`list_brand_workflows` / `get_workflow_run`	Inspect actual workflow executions
`set_brand_routing_mode`	Change shadow/canary/live routing; distinct from activation

Use the HTTP transport for operations that delegate to REST handlers; those tools are not available through local mcp-stdio. Tool availability remains subject to authorization. For unattended config changes, set require_golden_pass: true on apply_config and stop on failed evaluations or version conflicts. Activating a shadow brand does not switch it to live routing. See the trial walkthrough. Follow Your First Workflow Configuration Change for candidate validation, evaluation, full-object apply, and independent read-back.

The natural loop

get_brand_config + get_brand_scorecard
        ↓
propose_config_patch      (nothing saved yet)
        ↓
validate_config
        ↓
apply_config              (audited, versioned)

get_brand_scorecard is what makes this more than a text editor. Reading approval and escalation rates before proposing a change means the model is tuning against observed behavior rather than guessing at a threshold.

1. Mint a per-brand API key

curl -X POST https://api.workstream.stateset.com/v1/brands/<BRAND_ID>/api-keys \
  -H "Authorization: Bearer <ADMIN_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"label":"claude-mcp"}'

The plaintext token is returned once. Store it securely — it cannot be retrieved later, only revoked and reissued.

2. Connect from Claude

Claude Code

claude mcp add stateset-config \
  --transport http https://api.workstream.stateset.com/v1/mcp \
  --header "Authorization: Bearer <BRAND_API_KEY>"

Then in a session:

List the brands I can access. For the brand I select, read its config, scorecard, and recent runs. Propose one improvement supported by that evidence; do not apply it or change routing.

Claude Desktop

Bridge the remote HTTP server to stdio:

{
  "mcpServers": {
    "stateset-config": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://api.workstream.stateset.com/v1/mcp",
        "--header", "Authorization: Bearer <BRAND_API_KEY>"
      ]
    }
  }
}

Scoping

Prefer a per-brand key over an admin key. The brand key confines every tool call to that brand’s tenant, so a mistaken apply_config cannot reach another customer’s configuration.

Control plane — the versioned config pipeline behind apply_config
Configuration — what lives in deterministic_config
Workflow Studio — the UI equivalent
All MCP servers

Last modified on September 20, 2026

Get started

Build your first integration

Operate and improve

Resources and support

Platform

Using the APIs

StateSet Response

StateSet ResponseCX

Temporal Engine

StateSet iCommerce Engine

StateSet iCommerce EDI Engine

StateSet Mail

StateSet iCommerce Voice Engine

StateSet iCommerce NSR Engine

AI Agents

StateSet Agents

StateSet iCommerce Sandbox Engine

StateSet ACP

StateSet UCP

StateSet ICP

StateSet Sequencer

StateSet Set L2

StateSet Cloud

Apps & Consoles

Tools

Workstream MCP

Tools

Onboarding and operating tools

The natural loop

1. Mint a per-brand API key

2. Connect from Claude

Claude Code

Claude Desktop

Scoping

​Tools

​Onboarding and operating tools

​The natural loop

​1. Mint a per-brand API key

​2. Connect from Claude

​Claude Code

​Claude Desktop

​Scoping

​Related

Tools

Onboarding and operating tools

The natural loop

1. Mint a per-brand API key

2. Connect from Claude

Claude Code

Claude Desktop

Scoping

Related