mcpField
O
Outlit

Outlit

Remote
github.com/OutlitAIBusiness & Marketing0Updated 8w ago
Repository

About Outlit

Outlit is a hosted remote MCP server for agents automating customer operations, with real-time customer context and workspace capabilities. Its catalog spans customer discovery, analytics, integrations, and activation.

Key features

  1. 01Search customer profiles and timelines
  2. 02Read-only SQL analytics and schema inspection
  3. 03Manage customer ownership and collaboration access
  4. 04Discover integrations and setup status
  5. 05Activate customers and manage workspace settings

Use cases

  1. 01Find customer context and activity for an agent
  2. 02Run read-only analytics on customer and revenue data
  3. 03Check integration setup and synchronization
  4. 04Discover or create Behavior Metrics

MCP support

The hosted remote MCP server exposes Outlit tools, including customer context, read-only SQL views, integration and workspace operations. It supports OAuth and scoped Outlit API keys, with access limited by member permissions or key grants.

#outlit#mcp#remote-mcp#ai-agents#customer-context#customer-operations

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.outlit.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Outlit MCP

Outlit is the real-time understanding of every customer, the infrastructure agents use to automate customer operations.

This repository is the public discovery pointer for the hosted Outlit remote MCP server. It does not contain the server implementation. Canonical runtime metadata is served from Outlit-owned domains so MCP clients, registries, and crawlers have one source of truth.

Connect

Use the workspace-specific URL shown in Outlit Settings > CLI & MCP:

https://mcp.outlit.ai/w/<workspace-slug>/mcp

The shared discovery endpoint is:

https://mcp.outlit.ai/mcp

The remote MCP endpoint supports OAuth and scoped Outlit API keys. OAuth is the preferred setup for interactive clients; both methods expose the same public tool catalog, while each call remains limited by the signed-in member's current permissions or the API key's explicit grants. The MCP OAuth metadata is published at:

Scoped workspace API keys remain supported as bearer credentials for manual or headless clients that cannot complete OAuth.

Discovery

The official MCP Registry package name is ai.outlit/outlit.

Tools

The hosted server exposes the public capability catalog published in the canonical server card and documentation. Current capability families cover:

  • Customer and user discovery, profiles, timelines, facts, sources, and semantic context search
  • Customer ownership and collaboration access
  • Read-only SQL analytics and schema inspection
  • Safe destination lifecycle management
  • Integration discovery, browser setup, and setup/sync status
  • Customer activation, workspace settings, and Behavior Metric discovery and creation

The server also exposes read-only SQL views for activity, customers, users, and revenue.

Keep detailed tool names, descriptions, and schemas in the canonical server card, MCP docs, and Platform Capabilities docs rather than copying them here.

Skills

Install the official Outlit skills through the Outlit CLI:

outlit setup skills

Or install directly from the public skills repository:

npx -y skills add https://github.com/OutlitAI/outlit-agent-skills --skill outlit -g

Source Of Truth

The hosted MCP server is part of Outlit's platform infrastructure. Public metadata should point to:

  • Runtime and OAuth metadata on mcp.outlit.ai
  • Product and agent discovery metadata on outlit.ai
  • API contract metadata on docs.outlit.ai

Do not copy server cards, OpenAPI specs, or OAuth metadata into this repository as independent sources of truth.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.