High-risk tools in Mcp Api
6 of the 310 tools in Mcp Api are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
startIdentityProviderLoginWithIdExecute 3/5Begins a login request for a 3rd party login that requires user interaction such as HYPR.
-
startPasswordlessLoginWithIdExecute 3/5Start a passwordless login request by generating a passwordless code. This code can be sent to the User using the Send Passwordless Code API or using a mechanism outside of Fusi...
-
startTwoFactorLoginWithIdExecute 4/5Start a Two-Factor login request by generating a two-factor identifier. This code can then be sent to the Two Factor Send API (/api/two-factor/send)in order to send a one-time ...
-
startVerifyIdentityWithIdExecute 3/5Start a verification of an identity by generating a code. This code can be sent to the User using the Verify Send API Verification Code API or using a mechanism outside of Fusio...
-
startWebAuthnLoginWithIdExecute 3/5Start a WebAuthn authentication ceremony by generating a new challenge for the user
-
startWebAuthnRegistrationWithIdExecute 3/5Start a WebAuthn registration ceremony by generating a new challenge for the user
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.
More on Mcp Api
Enforce policy on Mcp Api
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init