Willow User MCP Server
Access user-scoped Willow resources: MCP servers, toolkits, commands, skills, and integration connections.
What is the Willow User MCP Server?
The Willow User MCP server gives AI agents structured, permission-aware access to Willow User through the Model Context Protocol. With 13 pre-built actions, agents can read, create, and update Willow User data on behalf of authorized users.
Willow ships the Willow User MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Willow User is being used by every AI agent in your stack.
Tools
List User MCP Servers
List or search MCP servers (integrations) accessible to the current user. Returns a summary for each server: slug, name, description, logo_url, status, and tools_count. Pass `search` to find servers for a task, and `include_tools` to see what each server can do.
List User Toolkits
List toolkits accessible to the current user, including both user-owned and organization-level toolkits. Returns a summary for each toolkit: slug, name, description, and status.
Create User Toolkit
Create a new toolkit owned by the current user. The toolkit slug is automatically prefixed with the user's email. Toolkits group integration tools, prompts, and resources together.
Update User Toolkit
Update an existing user toolkit by slug. Only the fields provided will be updated. The authenticated user must be the owner of the toolkit.
Delete User Toolkit
Permanently delete a user toolkit by slug. Only the owner can delete it. This operation cannot be undone.
List User Commands
List active commands accessible to the current user. Returns a summary for each command: slug, name, description, and status.
List User Skills
List or search skills accessible to the current user. Returns a summary for each skill: slug, name, description, and status. Pass `search` to find skills for a task.
Create User Skill
Create a new skill owned by the current user. The skill slug is automatically prefixed with the user's email. Skills contain instructions, scripts, references, and assets that agents can use. The skill goes through the organization's security review: the response's `review.status` is `published`, `draft`, or `pending` (held as a hidden draft until an admin approves it). Tell the user when it is pending.
Update User Skill
Update an existing user skill by slug. Only the fields provided will be updated. The authenticated user must be the owner of the skill. Changing the content, scripts, or references, or publishing, re-runs the organization's security review, and the response's `review.status` says whether the skill is `published`, `draft`, or `pending`. Editing a skill that is pending or was rejected sends it back for admin review. Tell the user when it is pending.
List User Plugins
List or search plugins the current user can install. A plugin bundles skills, commands, rules, and MCP servers into one install for Cursor or Claude Code. Returns a summary for each plugin: slug, name, description, version, verified, tags, skills_count, and mcp_servers_count.
Submit Issue
Submit a support issue on behalf of the current user. Creates a new issue with the specified title and description.
Check Connection
Check whether the current user has an active connection to a given integration. Use this to determine if the user needs to authenticate before using an integration's tools.
Get Auth URL
Generate an authentication URL for the current user to connect their account to an integration (e.g., GitHub, Slack, Jira). The returned URL initiates the OAuth flow.
Customize Tools
Edit descriptions, modify arguments, select tools, or add new ones
Set Up Your Willow User MCP Server in Minutes
Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.
Claude Desktop
{
"mcpServers": {
"willow-willow-user": {
"type": "http",
"url": "https://<org>.mcp-s.com/mcp/mcp/willow-user"
}
}
}Cursor
{
"mcpServers": {
"willow-willow-user": {
"type": "http",
"url": "https://<org>.mcp-s.com/mcp/mcp/willow-user"
}
}
}Claude Code
claude mcp add willow-willow-user --transport http https://<org>.mcp-s.com/mcp/mcp/willow-usern8n
{
"url": "https://<org>.mcp-s.com/mcp/mcp/willow-user",
"method": "POST"
}Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.
Enterprise Governance for Willow User
Willow adds the layer Willow User and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.
Willow User MCP Server FAQ
What is the Willow User MCP server?
The Willow User MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Willow User data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.
How is Willow's Willow User MCP server different from the official one?
The official Willow User MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.
Which AI clients work with the Willow User MCP server?
Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.
Is the Willow User MCP server secure? How does Willow handle authentication?
Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Willow User, nothing more. No credentials reach the LLM. Every action writes to an audit trail.
Can I limit which Willow User actions agents can take?
Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.
How do I detect shadow Willow User MCP servers in my org?
Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Willow User MCP locally, you'll see it.
What does the Willow User MCP server cost?
Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.
How do I install the Willow User MCP server with Willow?
Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.
Compare Willow MCP Gateway
See how Willow stacks up against other MCP platforms on governance, security, and enterprise readiness.
Your agents are already in the wild.
Give them a Basecamp. Go from AI chaos to AI work, in minutes.