The PlainID MCP Server exposes PlainID capabilities to LLMs and AI agents over the Model Context Protocol. This allows administrators, developers, and security teams to query and manage authorization in natural language, while every action remains scoped to the permissions users already hold in the Tenant.
The server authenticates via OAuth, using the user's own PlainID credentials. A user with view access can read, a user with admin access can write only within the Environments and Workspaces already granted to them.
Getting Started
Prerequisites
- An active PlainID Tenant. Your Tenant name is the one in your PlainID Tenant URL.
- PlainID user credentials. Your existing permissions apply: View for all insight capabilities, Admin for generate operations, which are evaluated per Environment and Workspace.
- An MCP-capable client.
Setup
Connect the PlainID MCP Server to your client using the URL matching your tenant:
https://mcp-oauth.<region>.plainid.io/<tenant-name>/mcp
Valid <region> values:
| Value | Use |
|---|---|
us1 |
Production — US |
eu1 |
Production — Europe, including UK tenants |
ca1 |
Production — Canada |
preprod |
Pre-production |
How to use the PlainID MCP Server
The PlainID MCP Server lets you interact with your Authorization Environment using natural language through your preferred AI assistant. Instead of navigating through multiple Workspaces, you can ask questions, explore access relationships, analyze Policies, review audit activity, and perform supported operations, all within your existing PlainID permissions.
The following sections highlight common use cases and example queries to help you get started. Requests can be adjusted based on your organization's requirements.
Understanding What's in your Tenant
Answers the query “What do we actually have, and where", which is useful for release reviews, audits, and tracking what is still in development versus what is approved and live in production.
Potential Queries
- "List all Identity and Integration Workspaces in the Production environment."
- "List all active Policies in the Production environment."
- "Compare the Policies in Dev/PolicyWS against Prod/PolicyWS and show me the difference."
- "Which Dynamic Groups appear most often across Policies in this Workspace?"
- "Show me every Policy attached to the payments application."
Understanding Who Can Access What
Answers effective-access questions directly, which are the questions auditors and incident responders tend to ask first.
Understand who or what can access specific resources, explore access relationships, and identify how Policies determine access, without manually reviewing individual Policies.
Potential Queries
- "What can the invoice-processing agent access in this Environment?"
- "On whose behalf can the invoice-processing agent request access?"
- "Who can read customer financial records?"
- "How many Policies reference the Finance Managers group?"
Checking Policy Dependencies
Answers "What does this Policy rely on?" before you promote, change, or retire it. The server returns the combined dependencies of one or more Policies, like Applications, Asset Templates, Identity Templates, Scope, etc.
Potential Queries
- "What does the Loan Approval Policy depend on?"
- "Before I promote Policy A to Production, what does it depend on, and does the Production Workspace already have those objects?"
- "Which objects do the most Policies depend on?"
- "Which API Mappers does a Policy protect?"
- "Does more than one Policy protect the same URI?"
- "Which Policies would a change to this Asset Template affect?"
Reviewing Policy Building Blocks
Answers "Which building blocks exist, and how are they used?"
Potential Queries
- "Which Rulesets or Conditions do most of the Policies reuse?"
- "Do any two Rulesets on the same Asset Template define contradictory or overlapping Conditions?"
- "Are there leftover test or draft Dynamic Groups I should clean up?"
- "Is there an existing Dynamic Group or Ruleset that already restricts access by department and region?"
Creating Policies and Building Blocks
Create and manage Policies and their related building blocks using natural language. Describe your access requirements to generate new Policies, update existing ones, and configure supporting objects such as Asset Templates and Applications.
Potential Queries
- "Create a Policy allowing regional managers to approve loans under $50,000."
- "Create a Policy that restricts access to sensitive customer data to authorized employees."
- "Update the existing Policy to include an additional Dynamic Group."
Understanding Recent Changes
Track and review changes across your environment, including Policy updates, deletions, and other operations. Gain visibility into what changed, when, and by whom, to support auditing, troubleshooting, and security reviews.
Potential Queries
- "Summarize the changes made in this Environment over the last two weeks."
- "Who modified Policies in Production since Monday?"
- "Show me every Policy deleted this quarter."
- "Did any high-risk operations occur in the last month?"
The PlainID MCP Server enables you to explore and manage authorization through natural language, from analyzing Policies and access relationships to creating Policies and reviewing changes, all within your existing PlainID permissions.
If you encounter permission restrictions, contact your PlainID administrator to verify your Environment and Workspace access, or reach out to PlainID Support for assistance.