Integration

Permit.io Cloud PDP integration

The Permit.io Cloud PDP answers authorization questions against the policy and data of one Permit.io environment: can this user perform this action on this resource (one check or many at once), what can this user do across tenants and resource instances, and which users can perform an action on a resource. It evaluates role-based and relationship-based policies; attribute-based (ABAC) policies and custom Rego need a self-hosted PDP and are not evaluated here. Checks change nothing, are rate-limited per IP (1000 checks per minute), and are recorded in the Permit audit log. Policies, users and roles are managed with the Permit.io API. Authentication is the API key of the environment to check against, sent as a Bearer token.

Connect Permit.io Cloud PDP How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Permit.io Cloud PDP.Built from the 4 Permit.io Cloud PDP tools below, on the connection you add once.

What you can do with Permit.io Cloud PDP

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Allowed, 1 operation

check_permissionCheck permissionPOSTChecks whether a user may perform an action on a resource (a resource type, optionally one instance, in a tenant) and returns allow true or false. Read-only.

Authorized user, 1 operation

list_authorized_usersList authorized usersPOSTLists which users can perform an action on a resource (a resource type or one instance, in a tenant), with the role that gives each one access. Read-only.

Bulk, 1 operation

bulk_check_permissionsBulk check permissionsPOSTRuns several permission checks in one call; returns one allow result per check, in the order sent. Read-only; limited to 200 calls a minute.

User permission, 1 operation

get_user_permissionsGet user permissionsPOSTReturns what a user can do: for each tenant and resource instance they have access to, their roles and permissions (resource:action, such as document:read). Filter by tenants, resources or resource_types. Read-only.

Use Permit.io Cloud PDP from Claude Code, Cursor or Codex

Connect Permit.io Cloud PDP in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Permit.io Cloud PDP operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Permit.io Cloud PDP

Create your workspace
Sign up free. Nothing to install.
Connect Permit.io Cloud PDP once
Add your Permit.io Cloud PDP connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.