identity-oidc-token-introspect
AI agents call identity-oidc-token-introspect to retrieve information from Vault MCP Server (mschuchard) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Introspection queries token metadata and validity status without side effects. However, in Vault's OIDC context, tokens may contain sensitive claims (user identity, permissions, etc.), so this read operation can expose sensitive authentication data. Medium severity reflects the information disclosure risk without data modification or destructive capability.
From the tool's definition Tool name 'identity-oidc-token-introspect' indicates introspection of OIDC tokens. OIDC token introspection is a read operation that validates and returns claims/metadata about a token without modifying it.
Attacks that exploit this kind of access
identity-oidc-token-introspect. It is categorised as a Read tool in the Vault MCP Server (mschuchard) MCP Server, which means it retrieves data without modifying state.
Register the Vault MCP Server (mschuchard) MCP server in PolicyLayer and add a rule for identity-oidc-token-introspect: 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 Vault MCP Server (mschuchard). Nothing to install.
identity-oidc-token-introspect 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 identity-oidc-token-introspect 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 identity-oidc-token-introspect. 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.
identity-oidc-token-introspect is provided by the Vault MCP Server (mschuchard) MCP server (mschuchard/vault-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →