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 Cre...
This record as markdown: /tools/io-fusionauth-mcp-api/createintrospect.md
What createIntrospect does on Fusionauth
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.
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 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
Attacks that exploit this kind of access
The rule that runs createIntrospect safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Fusionauth, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For createIntrospect, this is the rule to start with:
createIntrospect is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Fusionauth, apply this rule, and every createIntrospect call is checked against it from then on.
Questions about 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. It is categorised as a Read tool in the Fusionauth MCP Server, which means it retrieves data without modifying state.
Register the Fusionauth MCP server in PolicyLayer and add a rule for createIntrospect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Fusionauth. Nothing to install.
createIntrospect is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the createIntrospect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for createIntrospect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
createIntrospect is provided by the Fusionauth MCP server (@fusionauth/mcp-api). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Fusionauth, and thousands of servers like it.
This server
Across the catalogue