Scan the knowledge graph for hardcoded secrets: API keys, passwords, tokens, private keys, high-entropy strings
AI agents call secrets to retrieve information from code-intel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports information about hardcoded secrets already present in the codebase. It performs analysis and reporting without creating, modifying, deleting, or executing any code. While the sensitivity of the data returned (secrets themselves) warrants high severity due to potential information disclosure if an agent misuses the results, the tool's core function is read-only scanning.
From the tool's definition Tool name 'secrets' with description 'Scan the knowledge graph for hardcoded secrets: API keys, passwords, tokens, private keys, high-entropy strings'.
Attacks that exploit this kind of access
Scan the knowledge graph for hardcoded secrets: API keys, passwords, tokens, private keys, high-entropy strings. It is categorised as a Read tool in the code-intel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for secrets: 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 code-intel MCP Server. Nothing to install.
secrets 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 secrets 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 secrets. 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.
secrets is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). 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 →