List all OAuth2 client credential configurations in SAP CPI.
AI agents call list_oauth_credentials to retrieve information from Mcp Sap Cpi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves sensitive OAuth2 credential configurations from SAP CPI. While it performs no data modification (Read category), the severity is high because OAuth2 credentials are security-critical secrets. Exposure of credential configurations could enable unauthorized access to integrated systems.
From the tool's definition Tool name 'list_oauth_credentials' and description 'List all OAuth2 client credential configurations' indicate a query/retrieval operation. The verb 'list' and lack of any modification language confirm this is a read operation.
Attacks that exploit this kind of access
List all OAuth2 client credential configurations in SAP CPI. It is categorised as a Read tool in the Mcp Sap Cpi MCP Server, which means it retrieves data without modifying state.
Register the Mcp Sap Cpi MCP server in PolicyLayer and add a rule for list_oauth_credentials: 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 Mcp Sap Cpi. Nothing to install.
list_oauth_credentials 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 list_oauth_credentials 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 list_oauth_credentials. 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.
list_oauth_credentials is provided by the Mcp Sap Cpi MCP server (keelside/mcp-sap-cpi). 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 →