Integration

Permify integration

Permify is a Zanzibar-style authorization service: an authorization model written in the Permify schema language defines entities, relations, permissions and attribute rules, and relationship tuples plus attributes stored per tenant answer access questions against it. This catalog entry lets an agent create, list and delete tenants, write a schema and read it back, apply a partial schema change without resending the whole model, list the schema versions a tenant holds, write and delete relationship tuples and attributes, read tuples and attributes back with a filter, ask whether a subject holds a permission on an entity, ask a batch of those questions in one call, expand a permission into the tree of relations that grant it, look up every entity of a type a subject may act on, look up every subject that may act on an entity, list all permissions one subject holds on one entity, and manage reusable data bundles: write, read, delete and run one against supplied arguments. The streaming legs are absent because they hold the connection open and emit results as they are found rather than answering once. The host is part of the credential because every install is its own deployment: point it at the Permify HTTP listener (port 3476 by default). Authentication is the server's pre-shared key, or an OIDC access token when the server is configured for one, sent as a bearer token in the Authorization header; a server started without authentication accepts any placeholder value.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Permify.Built from the 23 Permify tools below, on the connection you add once.

What you can do with Permify

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.

Read, 4 operations

  • read_attributesRead attributesPOSTread attributes.
  • read_bundleRead bundlePOSTread bundle.
  • read_relationshipsRead relationshipsPOSTread relationships.
  • read_schemaRead schemaPOSTread schema.

Write, 4 operations

  • write_bundleWrite bundlePOSTwrite bundle.
  • write_dataWrite dataPOSTwrite data.
  • write_relationshipsWrite relationshipsPOSTwrite relationships.
  • write_schemaWrite schemaPOSTwrite schema.

Delete, 3 operations

  • delete_bundleDelete bundlePOSTdelete bundle.
  • delete_dataDelete dataPOSTdelete data.
  • delete_relationshipsDelete relationshipsPOSTdelete relationships.

List, 2 operations

  • list_schema_versionsList schema versionsPOSTlist schema.
  • list_tenantsList tenantsPOSTlist tenants.

Bulk check, 1 operation

  • bulk_check_permissionsBulk check permissionsPOSTbulk check api.

Check, 1 operation

  • check_permissionCheck permissionPOSTcheck api.

Create, 1 operation

  • create_tenantCreate tenantPOSTcreate tenant.

Expand, 1 operation

  • expand_permissionExpand permissionPOSTexpand api.

Lookup entity, 1 operation

  • lookup_entitiesLookup entitiesPOSTlookup entity.

Lookup subject, 1 operation

  • lookup_subjectsLookup subjectsPOSTlookup-subject.

Partial write, 1 operation

  • partial_write_schemaPartial write schemaPATCHpartially update your authorization model.

Run bundle, 1 operation

  • run_bundleRun bundlePOSTrun bundle.

Subject permission, 1 operation

  • list_subject_permissionsList subject permissionsPOSTsubject permission.

Tenant, 1 operation

  • delete_tenantDelete tenantDELETEdelete tenant.

Use Permify from Claude Code, Cursor or Codex

Connect Permify in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Permify 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 Permify

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect Permify once

    Add your Permify connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. 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.

Permify integration FAQ

What can you do with the Permify integration?

LiveContext exposes 23 operations on Permify, covering read, write, delete and list.

Popular integrations

Browse the whole catalog