# createIntrospect

Inspect an access token issued as the result of the Client Credentials Grant. OR Inspect an access token issued as the result of the Client Credentials Grant. OR Inspect an access token issued as the result of the User based grant such as the Authorization Code Grant, Implicit Grant, the User Credentials Grant or the Refresh Grant. OR Inspect an access token issued as the result of the User based grant such as the Authorization Code Grant, Implicit Grant, the User Credentials Grant or the Refresh Grant.

Agent View of the PolicyLayer registry record for `createIntrospect`. HTML page: https://policylayer.com/tools/io-fusionauth-mcp-api/createintrospect

## Facts

- Tool: `createIntrospect`
- Server: Fusionauth (`@fusionauth/mcp-api`) — https://policylayer.com/tools/io-fusionauth-mcp-api.md
- Install: `npx -y @fusionauth/mcp-api`
- Homepage: https://github.com/FusionAuth/fusionauth-mcp-api
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "createIntrospect",
    "arguments": {}
  }
}
```

## Why createIntrospect is rated Low

The tool inspects/introspects access tokens, which is a read-only operation that queries token metadata without modifying any state. Despite the 'create' prefix in the name, the description clearly indicates it only inspects tokens. Severity is low as it only reads token information.

From the tool's own definition: "Inspect an access token issued as the result of the Client Credentials Grant... Inspect an access token issued as the result of the User based grant"

## Use case

AI agents call createIntrospect to retrieve information from Fusionauth without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Fusionauth:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "createIntrospect": {}
  }
}
```

## Other tools on Fusionauth (313)

- `deleteAPIKeyWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteapikeywithid.md
- `deleteApplicationRoleWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteapplicationrolewithid.md
- `deleteApplicationWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteapplicationwithid.md
- `deleteConnectorWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteconnectorwithid.md
- `deleteConsentWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteconsentwithid.md
- `deleteEmailTemplateWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteemailtemplatewithid.md
- `deleteEntityGrantWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteentitygrantwithid.md
- `deleteEntityTypePermissionWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteentitytypepermissionwithid.md
- `deleteEntityTypeWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteentitytypewithid.md
- `deleteEntityWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteentitywithid.md
- `deleteFormFieldWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteformfieldwithid.md
- `deleteFormWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteformwithid.md
- `deleteGroupMembersWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletegroupmemberswithid.md
- `deleteGroupWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletegroupwithid.md
- `deleteIdentityProviderWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteidentityproviderwithid.md
- `deleteIPAccessControlListWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteipaccesscontrollistwithid.md
- `deleteJwtRefresh` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletejwtrefresh.md
- `deleteKeyWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletekeywithid.md
- `deleteLambdaWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletelambdawithid.md
- `deleteMessageTemplateWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletemessagetemplatewithid.md
- `deleteMessengerWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletemessengerwithid.md
- `deleteOAuthScopeWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteoauthscopewithid.md
- `deleteTenantWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletetenantwithid.md
- `deleteThemeWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deletethemewithid.md
- `deleteUserActionReasonWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteuseractionreasonwithid.md
- `deleteUserActionWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteuseractionwithid.md
- `deleteUserBulk` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteuserbulk.md
- `deleteUserLinkWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteuserlinkwithid.md
- `deleteUserRegistrationWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteuserregistrationwithid.md
- `deleteUserTwoFactorWithId` — Destructive — https://policylayer.com/tools/io-fusionauth-mcp-api/deleteusertwofactorwithid.md
- …and 283 more: https://policylayer.com/tools/io-fusionauth-mcp-api.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-fusionauth-mcp-api · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-fusionauth-mcp-api