Connect your AI tools directly to your UserGuiding project through the MCP Server. Once connected, tools like Claude, Cursor, OpenAI Codex, or any MCP-compatible assistant can look up users, search by attributes or events, track events, manage companies, manage Knowledge Base articles, and more — all through natural language.

MCP is available on all UserGuiding plans and takes about two minutes to set up. No developer help needed.

How It Works

The MCP (Model Context Protocol) is an open standard released by Anthropic in 2024 that lets AI tools call external services in a structured, authenticated way — similar to how a developer calls an API, but mediated by the AI model. Instead of pasting data into a chat window or hooking up ad-hoc integrations, the AI tool connects once to an MCP server and gets a well-defined set of tools it can invoke on your behalf.

The UserGuiding MCP Server exposes your project's user data as a set of tools the AI can invoke on your behalf.

   AI Tools (Claude, Cursor, OpenAI Codex, etc.)
        │
        │  SSE connection + JSON-RPC messages
        ▼
   UserGuiding MCP Server
        │
        │  Authenticated via your API key
        ▼
   Your UserGuiding Project Data

Claude (Desktop and Claude.ai), Cursor, and OpenAI Codex support MCP natively. Any other tool that adopts MCP as a transport will be able to connect to the UserGuiding server without additional setup.

What You Can Do With UserGuiding MCP

The MCP Server turns the product data you already track into something you can query conversationally. Five common use cases:

User research without SQL. Filter your users by any attribute or event, combine criteria, slice by cohort. No dashboard filter stack, no CSV export. The AI picks the right search tools automatically.

"Show me all users on the Pro plan who signed up in the last 30 days and triggered the export_csv event at least once."

Pre-call research for sales. Before a renewal call or prospect demo, pull everything the user has done in your product: plan, signup date, feature usage, which goals they hit, which events they triggered this week.

"Look up [email protected]. What's their plan, when did they sign up, and what have they done in the product this week?"

Support context. When a ticket comes in, pull the full user profile and recent interaction history in one prompt. Cuts the 2-3 back-and-forth messages that usually start with "what plan are you on?".

"Pull the full profile for [email protected] so I can see their plan, features used, and recent activity."

Activation and onboarding analysis. Compare cohorts, find differences in behavior, identify the onboarding steps that separate activated users from ones who churn.

"Show me users who completed our onboarding checklist vs. users who dropped off at step 3. What did the completers do that the others didn't?"

Expansion and churn signals. Find users whose usage patterns suggest they're ready to upgrade, or users on paid plans who are going quiet.

"Find users on the Starter plan who triggered the api_rate_limit_hit event more than ten times this month."

Getting Started

Step 1: Get Your API Key

Find your API key in UserGuiding Panel → Settings → Project Settings → MCP & API.

Step 2: Connect Your AI Tool

The MCP Server uses Server-Sent Events (SSE) as its transport. Add the following to your AI tool's MCP settings:

Server URL:

https://mcp.userguiding.com/mcp/sse

Authentication — pass your API key as a header:

UG-API-KEY: <your-api-key>

Or as a query parameter (for tools that don't support custom headers):

https://mcp.userguiding.com/mcp/sse?api_key=<your-api-key>

Claude.ai and Claude for Desktop

For both Claude. ai and Claude for Desktop, an admin must first add the UserGuiding MCP Server as a connector before other Claude users can connect.

Select your profile icon in the bottom-left corner of Claude, then select Admin settings.
Open the Connectors tab, then click on the (+) icon at the top of the Connectors field.
Choose Add Custom Connector:
1. Name: UserGuiding
2. Remote MCP Server URL: https://mcp.userguiding.com/mcp/sse
Click Connect to authenticate and start using the connector with Claude.

Configuration Examples

Claude. ai

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "userguiding": {
      "url": "https://mcp.userguiding.com/mcp/sse",
      "headers": {
        "UG-API-KEY": "<your-api-key>"
      }
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "userguiding": {
      "url": "https://mcp.userguiding.com/mcp/sse",
      "headers": {
        "UG-API-KEY": "<your-api-key>"
      }
    }
  }
}

OpenAI Codex (mcp.json):

Codex follows the same MCP server config format as Cursor. Drop the UserGuiding server entry into your Codex mcp.json using the JSON above. Check OpenAI's current Codex MCP docs for the exact file location on your system.

{
  "mcpServers": {
    "userguiding": {
      "url": "https://mcp.userguiding.com/mcp/sse",
      "headers": {
        "UG-API-KEY": "<your-api-key>"
      }
    }
  }
}

Available Tools

The UserGuiding MCP Server exposes 17 tools across five capability areas. Each is callable in plain English by any MCP-compatible AI assistant, and you can combine them in a single prompt — the AI assistant picks the right tools to answer your question.

User Management

get_user — Look up a user by ID. Returns all attributes, company association, and interaction history. Connects to: User Identification, Segmentation, Analytics.
upsert_user — Create a new user or update an existing one. Merges attributes and optionally attaches the user to a company. Connects to: User Identification, Segmentation.
delete_user — Permanently delete a user. Connects to: User Identification.
reset_user_history — Reset a user's interaction history (guide views, checklist progress, etc.) while keeping their custom attributes. Connects to: Guides, Checklists, Surveys, Hotspots, Resource Centers.
list_users — List all users with cursor-based pagination. Connects to: User Identification, Segmentation.

Search & Analytics

search_users — Search and filter users by attributes or events. Supports pagination and sorting. Connects to: Segmentation, Analytics.
get_user_count — Count users matching filters without fetching full user data. Connects to: Segmentation, Analytics.
list_attributes — Discover all available user attributes and their data types. Connects to: User Identification, Segmentation.
list_events — Discover all tracked event names in your project. Connects to: Analytics, No-Code Analytics, Custom Alerts.

Events

track_event — Track a named event for a user, optionally with metadata. Connects to: Analytics, No-Code Analytics, Custom Alerts, Segmentation.

Companies

get_company — Look up a company by ID. Returns attributes and member user IDs. Connects to: Segmentation, account-level targeting.
list_companies — List and filter companies with pagination and sorting. Connects to: Segmentation, account-level targeting.

Knowledge Base

search_kb_articles — Search your Knowledge Base articles by text query. Returns article IDs, titles, descriptions, and categories ranked by relevance. Connects to: Knowledge Base.
get_kb_article — Retrieve the full content of a Knowledge Base article by its ID, including title, body, description, publish status, and all locales. Connects to: Knowledge Base.
create_kb_article — Create a new Knowledge Base article with a title, content, and optional description. Connects to: Knowledge Base.
update_kb_article — Update the title or content of an existing Knowledge Base article by its ID. Connects to: Knowledge Base.
delete_kb_article — Permanently delete a Knowledge Base article by its ID. Connects to: Knowledge Base.

Searching and Filtering Users

The search_users tool supports two types of filters.

Attribute Filters

Filter users by any built-in or custom attribute:

{"attribute": "email", "equation": "contains", "value": "@acme.com"}
{"attribute": "plan", "equation": "equals", "value": "enterprise"}
{"attribute": "first_seen", "equation": "after", "value": 1704067200000}

Available equations by attribute type:

Text: equals, not_equals, contains, not_contains, starts_with, ends_with, regexp, is_not_known, has_any_value

Number: equals, not_equals, more_than, less_than, is_known, is_not_known

Date: before, after, equals, not_equals, more_than_days_ago, less_than_days_ago, exact_days_ago, is_not_known, has_any_value

Boolean: equals, not_equals, is_not_known, has_any_value

Event Filters

Filter by whether a user has (or has not) performed an event:

{"event": "signed_up", "equation": "has_done"}
{"event": "export_csv", "equation": "has_not_done"}

Available equations: has_done, has_not_done

Combining Filters

Pass multiple filter objects in the filters array. Filters are combined with AND logic:

[
  {"attribute": "plan", "equation": "equals", "value": "enterprise"},
  {"event": "export_csv", "equation": "has_done"}
]

Example Prompts

Once connected, here are some prompts your team can use:

"How many users signed up in the last 7 days?"
"Find all users on the enterprise plan whose last seen date is before January 2025."
"Show me the details for user u_abc123."
"Track a plan_upgraded event for user u_abc123."
"List all companies with more than 50 members."
"Search the knowledge base for articles about getting started."
"Find all knowledge base articles in the Developers category."
"Show me the full content of knowledge base article 182."
"Create a new knowledge base article titled 'How to use the REST API' with a short introduction."
"Update article 299 to mention that the new indexing options are available."

What the MCP Server Gives You

A quick summary of what's inside the box:

Read and write access — query users, companies, and events; upsert profiles, track events, and create or update Knowledge Base articles from your AI tool.
Interaction depth — individual guide, checklist, survey, and hotspot events with timestamps, not just aggregate counts.
No-code setup — connect via Claude. ai connector settings or a JSON config file. Takes about two minutes.
Natural-language queries — ask about users in plain English. The AI picks the right tools automatically.
Real-time data — queries reflect the current state, not a cached export.

Pairing With No-Code Event Tracking

The MCP server pairs naturally with UserGuiding's No-Code Event Tracking. Point-and-click on elements in your product to start capturing events — no code, no engineer time, no new SDK to install. Then query those events through the MCP server in plain English.

For most product, growth, and CS teams, this combo replaces a stack that previously required Amplitude, Heap, or Mixpanel for event tracking plus a separate analytics tool for exploration. Event capture lives in the same platform as your onboarding, your checklists, and your Knowledge Base, and the MCP server turns product analytics into a chat interface inside Claude, Cursor, or Codex.

FAQ

Which plans include MCP? MCP is available on all UserGuiding plans.

Do we need engineering help to set it up? No. It's a connection you enable in your AI tool's settings. Total setup time is about two minutes.

What data can the MCP server access? The MCP server can only access data within the project associated with your API key. It cannot access other projects or other accounts.

Is the connection secure? Yes. All communication is over HTTPS, and your API key authenticates every request.

What about data privacy? Data stays in your UserGuiding project. The AI tool sends queries to the UserGuiding MCP server and receives results. No bulk export or storage happens on the AI side.

Is the data real-time? Yes. MCP queries hit UserGuiding's live database, not a cached export. If a user triggered an event 30 seconds ago, your AI tool sees it.

Does it work with ChatGPT or other AI tools? MCP support is currently native in Claude (Desktop and Claude.ai), Cursor, and OpenAI Codex. ChatGPT and Gemini do not support MCP natively as of April 2026. Any tool that adopts MCP as a transport will be able to connect to the UserGuiding server without additional setup on our side.

Can users break things with write operations? Write tools (upsert_user, track_event, delete_user, reset_user_history, and the KB create/update/delete tools) use the same API key as read tools. Treat the key like any admin credential: share it carefully. Read-only use (search, get, list) is safe regardless.

Is there a rate limit? The MCP server follows the same rate limits as the UserGuiding Public API.

How does this compare to Amplitude, Heap, or Mixpanel? Amplitude, Heap, and Mixpanel are product analytics platforms with their own event-tracking SDKs and query interfaces. UserGuiding's No-Code Event Tracking captures the same kinds of user events without code or engineering help, and the MCP server lets you query them in natural language instead of building dashboards. For product, growth, and CS teams who want analytics without a dedicated analyst, it replaces a separate analytics contract with something already in your UserGuiding plan.

Did this answer your question?

Ask AI

Responses are generated using AI and may contain mistakes.

How can I help you?

Ask me anything about our product. I can help you find answers across the knowledge base.

Ask a question...Ctrl+I