Permit.io MCP integration for AI agents.

Connect AI agents to Permit.io through 13 structured actions, including get tenant, assign role, delete tenant, and unassign role. Review authentication, inp…

ACTION CONTRACTS
13
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Permit.io integration exposes

The Permit.io Agent App exposes 13 provider-backed actions for developer tools and security work. Its current contract lets an authorized agent retrieve a permit.io tenant by id or key, assign a permit.io role to a user, and delete a permit.io tenant by id or key. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Permit.io account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Permit.io capabilities.

Showing 12 of 13 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

get_tenantREAD

Retrieve a Permit.io tenant by id or key.

INPUTS: projectId / environmentId / tenantId

assign_roleWRITE

Assign a Permit.io role to a user.

INPUTS: projectId / environmentId / user / role / tenant

delete_tenantHIGH IMPACT

Delete a Permit.io tenant by id or key.

INPUTS: projectId / environmentId / tenantId

unassign_roleREVIEW

Remove a Permit.io role assignment from a user.

INPUTS: projectId / environmentId / user / role / tenant

create_tenantWRITE

Create a tenant in a Permit.io environment.

INPUTS: projectId / environmentId / key / name / description

create_userWRITE

Create a user in a Permit.io environment.

INPUTS: projectId / environmentId / key / email / first_name

delete_userHIGH IMPACT

Delete a Permit.io user by id or key.

INPUTS: projectId / environmentId / userId

get_userREAD

Retrieve a Permit.io user by id or key.

INPUTS: projectId / environmentId / userId

list_role_assignmentsREAD

List role assignments in a Permit.io environment.

INPUTS: projectId / environmentId / user / role / tenant

list_tenantsREAD

List tenants in a Permit.io environment.

INPUTS: projectId / environmentId / search / page / perPage

list_usersREAD

List users in a Permit.io environment.

INPUTS: projectId / environmentId / search / role / page

update_tenantWRITE

Partially update a Permit.io tenant.

INPUTS: projectId / environmentId / tenantId / name / description

INPUT CONTRACTS

Know what the action needs before it runs.

get_tenant

projectIdOPTIONAL
The Permit.io project id or key. Required when the connected API key is not environment-scoped.
environmentIdOPTIONAL
The Permit.io environment id or key. Required when the connected API key is not environment-scoped.
tenantIdREQUIRED
The Permit.io tenant id or key.

assign_role

projectIdOPTIONAL
The Permit.io project id or key. Required when the connected API key is not environment-scoped.
environmentIdOPTIONAL
The Permit.io environment id or key. Required when the connected API key is not environment-scoped.
userREQUIRED
The user id or key receiving the role.
roleREQUIRED
The role id or key to assign or remove.
tenantOPTIONAL
The tenant id or key that scopes the role.

delete_tenant

projectIdOPTIONAL
The Permit.io project id or key. Required when the connected API key is not environment-scoped.
environmentIdOPTIONAL
The Permit.io environment id or key. Required when the connected API key is not environment-scoped.
tenantIdREQUIRED
The Permit.io tenant id or key.

unassign_role

projectIdOPTIONAL
The Permit.io project id or key. Required when the connected API key is not environment-scoped.
environmentIdOPTIONAL
The Permit.io environment id or key. Required when the connected API key is not environment-scoped.
userREQUIRED
The user id or key receiving the role.
roleREQUIRED
The role id or key to assign or remove.
tenantOPTIONAL
The tenant id or key that scopes the role.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Get Tenant

Retrieve a Permit.io tenant by id or key. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

get_tenant

Control Assign Role

Assign a Permit.io role to a user. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.

assign_role

Verify with Get User

Retrieve a Permit.io user by id or key. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

get_user

SAFETY BOUNDARY

Operate Permit.io with explicit limits

  • Authorize Permit.io with API key and grant only the provider access required by the selected actions.
  • 7 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
  • Treat `delete_tenant` and `delete_user` as high-impact operations and require an explicit approval boundary.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Permit.io rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Permit.io task completed successfully.

CONNECTION MODEL

API key

Permit.io API key sent as a Bearer token. Copy an environment key from the Projects screen or active environment menu at https://app.permit.io.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
5
WRITE SIGNALS
5
HIGH IMPACT
2
REVIEW SIGNALS
1

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Permit.io.

Official Permit.io website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS