deleteJwtRefresh

// WHEN AI AGENTS USE THIS TOOL

AI agents may call deleteJwtRefresh to permanently remove or destroy resources in Mcp Api. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON DELETEJWTREFRESH

Without a policy, an AI agent could call deleteJwtRefresh in a loop, permanently destroying resources in Mcp Api. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

io-fusionauth-mcp-api.yaml

tools:
  deleteJwtRefresh:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full Mcp Api policy for all 314 tools.

// DETAILS

Tool Name deleteJwtRefresh

Category Destructive

MCP Server Mcp Api MCP Server

Risk Level Critical

// MORE MCP API TOOLS

Destructive cancelActionWithId Destructive changePasswordWithId Destructive deleteAPIKeyWithId Destructive deleteApplicationRoleWithId Destructive deleteApplicationWithId Destructive deleteConnectorWithId Destructive deleteConsentWithId Destructive deleteEmailTemplateWithId

View all 314 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like deleteJwtRefresh have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete ACR — Agent Composition Records acknowledge_threat AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

deleteJwtRefresh is one of the critical-risk operations in Mcp Api. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the deleteJwtRefresh tool do? +

Revokes refresh tokens using the information in the JSON body. The handling for this method is the same as the revokeRefreshToken method and is based on the information you provide in the RefreshDeleteRequest object. See that method for additional information. OR Revoke all refresh tokens that belong to a user by user Id for a specific application by applicationId. OR Revoke all refresh tokens that belong to a user by user Id. OR Revoke all refresh tokens that belong to an application by applicationId. OR Revokes a single refresh token by using the actual refresh token value. This refresh token value is sensitive, so be careful with this API request. OR Revokes refresh tokens. Usage examples: - Delete a single refresh token, pass in only the token. revokeRefreshToken(token) - Delete all refresh tokens for a user, pass in only the userId. revokeRefreshToken(null, userId) - Delete all refresh tokens for a user for a specific application, pass in both the userId and the applicationId. revokeRefreshToken(null, userId, applicationId) - Delete all refresh tokens for an application revokeRefreshToken(null, null, applicationId) Note: <code>null</code> may be handled differently depending upon the programming language. See also: (method names may vary by language... but you'll figure it out) - revokeRefreshTokenById - revokeRefreshTokenByToken - revokeRefreshTokensByUserId - revokeRefreshTokensByApplicationId - revokeRefreshTokensByUserIdForApplication. It is categorised as a Destructive tool in the Mcp Api MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on deleteJwtRefresh? +

Add a rule in your Intercept YAML policy under the tools section for deleteJwtRefresh. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mcp Api MCP server.

What risk level is deleteJwtRefresh? +

deleteJwtRefresh is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit deleteJwtRefresh? +

Yes. Add a rate_limit block to the deleteJwtRefresh 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.

How do I block deleteJwtRefresh completely? +

Set action: deny in the Intercept policy for deleteJwtRefresh. 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.

What MCP server provides deleteJwtRefresh? +

deleteJwtRefresh 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.

Let agents act without letting them run wild.