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.
Part of the Mcp Api MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use createIntrospect to create or modify resources in Mcp Api. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call createIntrospect repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Mcp Api.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
createIntrospect:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Mcp Api policy for all 310 tools.
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.. It is categorised as a Write tool in the Mcp Api MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for createIntrospect. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mcp Api MCP server.
createIntrospect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the createIntrospect rule in your Intercept 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 Intercept 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 Mcp Api MCP server (@fusionauth/mcp-api). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept