security

Audit all MCP server configs for security issues like hardcoded secrets, tokens in args, and shell injection patterns

Server Mcp Doctor realwigu/mcp-doctor
Category Read
Risk class Low
Parameters 00 required

What security does on Mcp Doctor

AI agents call security to retrieve information from Mcp Doctor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why security needs a policy

This is a read-only diagnostic and reporting tool. It analyzes MCP server configurations to identify potential security vulnerabilities but does not make any changes to systems, execute code, or trigger external actions. While the information it reveals could be sensitive (exposure of hardcoded secrets), the tool itself only retrieves and audits data.

From the tool's definition The tool 'security' performs auditing and scanning functions: 'Audit all MCP server configs for security issues like hardcoded secrets, tokens in args, and shell injection patterns.' It examines configurations and reports issues but does not modify, execute,…

Questions about security

What does the security tool do? +

Audit all MCP server configs for security issues like hardcoded secrets, tokens in args, and shell injection patterns. It is categorised as a Read tool in the Mcp Doctor MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on security? +

Register the Mcp Doctor MCP server in PolicyLayer and add a rule for security: 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 Doctor. Nothing to install.

What risk level is security? +

security is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit security? +

Yes. Add a rate_limit block to the security 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.

How do I block security completely? +

Set action: deny in the PolicyLayer policy for security. 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 security? +

security is provided by the Mcp Doctor MCP server (realwigu/mcp-doctor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.