Response MCP Servers

ResponseCX ships two Model Context Protocol servers with different jobs.

Server	Transport	For
ResponseCX remote	Streamable HTTP at `POST /api/mcp`	An external agent building and tuning ResponseCX agents
Response analytics	Local stdio	Claude Desktop reading analytics and reporting data

Remote agent-building server

An external AI agent connects with its rcx_ API key as a Bearer token and gets a scope-filtered toolset for building ResponseCX agents.

POST /api/mcp
Authorization: Bearer rcx_...

The key is authenticated by the same guard as the REST v1 API. Scopes gate each individual tool, and tools/list advertises only the tools the key’s scopes permit — an unauthorized tool is never even visible.

The server is stateless: each JSON-RPC POST builds a fresh server and transport, so there is no cross-request session state to leak between tenants. Tool output is capped at 60,000 characters and truncated with a marker beyond that.

Tools

Discovery — so an agent can orient before it writes anything:

Tool	Purpose
`describe_workspace`	What exists in this workspace
`describe_vocabulary`	The legal terms for rule conditions — stops the model guessing at grammar

Building:

Tool	Purpose
`provision_agent`	Build a complete agent — settings, rules, functions, knowledge — in one atomic call
`build_support_agent`	Opinionated support-agent scaffold
`create_agent` / `update_agent` / `get_agent` / `list_agents`	Agent lifecycle
`configure_agent` / `get_agent_settings`	Model and behavior settings
`add_rule` / `update_rule` / `list_rules`	Rules
`add_function` / `update_function` / `list_functions`	Functions
`add_knowledge` / `search_knowledge`	Knowledge base

Verifying:

Tool	Purpose
`test_agent`	Exercise the agent — closes the build → verify loop
`audit_agent`	Review an agent’s configuration

Reading:

Tool	Purpose
`list_responses` / `get_response`	Response history
`analytics_summary`	Aggregate analytics

Resources

Re-readable context a client can attach without spending a tool call — notably vocabulary and workspace.

The build → verify loop

The intended flow for an agent building an agent:

describe_workspace and describe_vocabulary to orient.
provision_agent to create the whole thing atomically.
test_agent to exercise it.
audit_agent, then update_rule / update_function to correct.

Errors come back as safe, model-readable messages — internals are never leaked.

Local analytics server

A stdio MCP server that lets Claude Desktop call the Response analytics and reporting API through a small authenticated bridge.

Run it

RESPONSE_API_BASE_URL=http://localhost:3000 \
RESPONSE_API_TOKEN=<cli-token> \
RESPONSE_ORG_ID=<org-id> \
npm run mcp:response-api

Optional:

RESPONSE_INTERNAL_SECRET (or INTERNAL_API_SECRET) adds x-internal-secret for internal-only routes.
RESPONSE_MCP_MAX_RESPONSE_CHARS caps large tool responses. Default 60000.

Claude Desktop

{
  "mcpServers": {
    "response-analytics": {
      "command": "node",
      "args": ["/path/to/scripts/response-api-mcp-server.mjs"],
      "env": {
        "RESPONSE_API_BASE_URL": "https://your-response-host",
        "RESPONSE_API_TOKEN": "<cli-token>",
        "RESPONSE_ORG_ID": "<org-id>"
      }
    }
  }
}

Tools

Tool	Returns
`response_analytics_overview`	The comprehensive reporting payload: response volume, ratings, channels, AI resolution rate, widget activity, commerce signals, question themes, support performance, funnel steps, response times
`response_widget_analytics`	The widget/chat subset: conversations, messages, widget events, funnel, handoff/containment, response time, commerce activity
`response_dashboard_stats`	Compact dashboard stats
`response_responses_created`	Recently created responses, filterable by date range, channel, rating, function-call status, and search
`response_response_analytics_export`	Response rows for analytics and export
`response_response_count`	Total response count for the authenticated organization
`response_chat_conversations`	Chat/widget conversations with manager reporting fields — latest customer/agent messages, escalation and review state, status, counts, linked response signals
`response_chat_thread`	One conversation transcript with recent messages, counts, attachments, and response history
`response_cx_reporting_bundle`	The core CX reporting dataset in one call
`response_api_health`	Checks `/api/health`
`response_reporting_api_request`	Operator/debug escape hatch for allowlisted `/api/...` routes
`response_mcp_servers`	Available MCP integrations for the organization

CX reporting flow

For a broad report, start with response_cx_reporting_bundle. For deeper evidence, use response_responses_created to pull filtered response rows and response_chat_conversations to find relevant threads. Use response_chat_thread when you need the actual transcript.

The analytics server only accepts /api/... paths and never writes logs to stdout, so the MCP JSON-RPC channel stays clean.

Response Public API (v1)Response ChatGPT App Overview

Get started

Platform

StateSet One

StateSet Response

StateSet ResponseCX

Temporal Engine

StateSet iCommerce

StateSet Commerce

StateSet EDI

StateSet Mail

StateSet Voice

StateSet NSR

AI Agents

StateSet Sandbox

StateSet ACP

StateSet UCP

StateSet ICP

StateSet Sequencer

StateSet Set L2

StateSet Cloud

Tools

Response MCP Servers

Response MCP Servers

Remote agent-building server

Tools

Resources

The build → verify loop

Local analytics server

Run it

Claude Desktop

Tools

CX reporting flow

​Response MCP Servers

​Remote agent-building server

​Tools

​Resources

​The build → verify loop

​Local analytics server

​Run it

​Claude Desktop

​Tools

​CX reporting flow

​Related

Response MCP Servers

Remote agent-building server

Tools

Resources

The build → verify loop

Local analytics server

Run it

Claude Desktop

Tools

CX reporting flow

Related