> ## Documentation Index
> Fetch the complete documentation index at: https://outlit-codex-platform-actions-create-update-cli.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# MCP Integration
> Connect remote MCP clients to Outlit with your workspace URL, OAuth, or scoped API keys
## What is the Outlit MCP Server?
Outlit's MCP server lets MCP-compatible clients query customer data, revenue metrics, timelines, facts, search results, and SQL analytics over a remote MCP connection.
The Outlit CLI is not required for MCP setup. Use the workspace MCP URL directly in your MCP client.
## Authentication Model
Outlit's remote MCP endpoint uses OAuth-based authentication for customer-intelligence tools. In practice that means:
* you add the workspace MCP URL to your client
* you do not paste API keys or bearer headers into config files
* the client opens an OAuth sign-in flow and stores the resulting session
Platform configuration tools use API-key authentication today. Use an API key with `agents:read` for read-only configuration tools and `agents:write` for write tools.
## Connect Your MCP Client
Open [Settings > CLI & MCP](https://app.outlit.ai/settings/workspace/mcp) and copy the workspace-specific MCP URL for the workspace you want to connect.
It looks like:
```text theme={null}
https://mcp.outlit.ai/w//mcp
```
Use your client's remote MCP / connector / server settings and add the Outlit URL directly.
For clients that accept raw JSON config, the shape is typically:
```json theme={null}
{
"mcpServers": {
"outlit": {
"url": "https://mcp.outlit.ai/w//mcp"
}
}
}
```
No `Authorization` header is needed for OAuth-based customer-intelligence tools.
After you add the server, your client should prompt you to sign in to Outlit and authorize access for that workspace.
Ask your client:
```text theme={null}
Show me the available Outlit analytics views.
```
Use [Agent Skills](/ai-integrations/skills) for coding agents like Claude Code, Codex, and Gemini CLI. Use MCP when your primary surface is an MCP client such as Cursor, VS Code, or another remote-MCP connector.
## Platform Configuration Over MCP
Platform configuration tools inspect and mutate agents, automations, signals, and destinations. These tools require API-key authentication because they execute scoped platform actions.
Open [Settings > CLI & MCP](https://app.outlit.ai/settings/workspace/mcp) and create an API key for agent configuration. The key must include `agents:read` for read tools and `agents:write` for write tools.
For MCP clients that support custom headers or headless bearer-token setup, configure the same workspace MCP URL with an `Authorization` header:
```json theme={null}
{
"mcpServers": {
"outlit": {
"url": "https://mcp.outlit.ai/w//mcp",
"headers": {
"Authorization": "Bearer ok_your_api_key"
}
}
}
}
```
Ask your client:
```text theme={null}
List my Outlit agent templates.
```
Do not add API keys to OAuth-only client configs. If your MCP client cannot send bearer headers, use the CLI or REST API for platform configuration actions.
## What Tools Are Available?
| Tool | What it does | Example prompt |
| -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| `outlit_list_customers` | Filter customers by billing status, activity recency, revenue, and exact trait values | "Show me paying enterprise customers with `segment=enterprise` who haven't been active in 30 days" |
| `outlit_list_users` | Filter users by journey stage, activity, customer, and exact trait values | "Find all signed-up users at Acme Corp with `role=admin` who went inactive this week" |
| `outlit_list_workspace_users` | Browse internal workspace users such as CSMs, managers, account owners, and admins | "List workspace users who own customers in the enterprise segment" |
| `outlit_get_customer` | Get a complete customer profile with users, revenue, timeline, and metrics | "Get the full profile for acme.com including their users and revenue" |
| `outlit_get_timeline` | Get the activity timeline for a customer, filtered by channel and event type | "Show me Acme Corp's email and Slack activity from the last 7 days" |
| `outlit_list_facts` | Retrieve structured customer facts with status, source type, customer-memory fact type, public category, occurrence time filters, pagination, and source provenance (`sourceMetadata` includes `sourceType`, `sourceId`, `sourceOccurredAt`, `sourceQuote`, and `permalink`) | "Show me active churn-risk facts for acme.com from calls last quarter" |
| `outlit_get_fact` | Retrieve one exact fact by ID, optionally expanding best-effort related data like evidence | "Get fact\_123 with evidence" |
| `outlit_get_source` | Retrieve one exact source record by generic `sourceType` and `sourceId` | "Open the support ticket source for ticket\_456" |
| `outlit_list_sources` | List concrete source records such as calls, emails, calendar events, support tickets, and opportunities | "List Acme's support tickets and calls from January" |
| `outlit_search_customer_context` | Search across customer facts, emails, calls, calendar events, support tickets, and CRM opportunities using natural language. Returns grouped artifact-level matches for `source` and `fact` results, with `sourceTypes` and time-range filters | "What pricing concerns does Acme have?" |
| `outlit_query` | Run read-only SQL queries against your customer data | "Which channels lead to the most revenue?" |
| `outlit_schema` | Get view schemas to help write accurate SQL queries | "Show me the available analytics views" |
| `outlit_send_notification` | Send a notification through the organization's configured notifier; Slack is the default notifier | "Post the renewal-risk summary to the default Slack notifier" |
`outlit_send_notification` is an action tool for deliberate send, post, or notify workflows. It should not be used for passive analysis or previewing results.
## Platform Configuration Tools
API-key authenticated MCP clients can also inspect and manage selected agent and automation configuration through platform action tools:
| Tool | What it does |
| ------------------------------------- | ------------------------------------------------------------------- |
| `outlit_agent_list_templates` | List agent templates that can be created |
| `outlit_agent_list_available_actions` | List available agent configuration actions |
| `outlit_agent_list` | List configured agents |
| `outlit_agent_get` | Get one configured agent |
| `outlit_agent_create` | Create an agent |
| `outlit_agent_update` | Update one configured agent |
| `outlit_agent_enable` | Enable one configured agent |
| `outlit_agent_disable` | Disable one configured agent |
| `outlit_agent_rename` | Rename one configured agent |
| `outlit_automation_list` | List configured automations |
| `outlit_automation_get` | Get one configured automation |
| `outlit_automation_create` | Create an agent automation from an `agentId` |
| `outlit_automation_update` | Update an agent automation from an `agentId` |
| `outlit_automation_enable` | Enable one configured automation |
| `outlit_automation_disable` | Disable one configured automation |
| `outlit_automation_archive` | Archive one configured automation |
| `outlit_signal_list` | List configured automation signals |
| `outlit_signal_get` | Get one configured automation signal |
| `outlit_signal_create` | Create one automation signal |
| `outlit_signal_update` | Update one automation signal |
| `outlit_signal_archive` | Archive one configured automation signal |
| `outlit_destination_list` | List configured automation destinations with masked configuration |
| `outlit_destination_get` | Get one configured automation destination with masked configuration |
| `outlit_destination_create` | Create one automation destination |
| `outlit_destination_update` | Update one automation destination |
| `outlit_destination_enable` | Enable one configured automation destination |
| `outlit_destination_disable` | Disable one configured automation destination |
| `outlit_destination_archive` | Archive one configured automation destination |
Read tools require `agents:read`. Write tools require `agents:write`. Destination tools return masked configuration only.
See [Platform Actions](/ai-integrations/platform-actions) for the shared API, CLI, and MCP model behind these tools.