New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

secrets

Secrets: filesystem scan, env variable audit, SSH key sprawl, git history leak detection

SERVERDefense SOURCEdefense-mcp-server
Low RISK CLASS
Category Read
Parameters 101 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/defense/secrets.md

What secrets does on Defense

AI agents call secrets to retrieve information from Defense without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
path string Root path to scan
action string Yes Secrets scanning action
dryRun boolean Preview only
repoPath string Path to git repository
check_env boolean Check environment variables for sensitive names
max_depth number Maximum directory depth to search
scan_type string Type of secrets to scan for
check_files boolean Check for exposed .env files on disk
search_path string Root path to search for SSH keys
check_authorized_keys boolean Also audit authorized_keys files

Parameters from the server's own tool schema.

Why secrets is rated Low

The tool performs scanning and auditing operations — reading the filesystem, environment variables, SSH keys, and git history to detect leaks. These are read/query operations with no stated side effects. However, severity is medium because this tool accesses highly sensitive data (secrets, keys, credentials) and could expose critical information if misused or if results are logged/exfiltrated.

From the tool's definition filesystem scan, env variable audit, SSH key sprawl, git history leak detection

Risk signalsAccepts file system path (path) · High parameter count (10 properties)

Questions about secrets

What does the secrets tool do? +

Secrets: filesystem scan, env variable audit, SSH key sprawl, git history leak detection. It is categorised as a Read tool in the Defense MCP Server, which means it retrieves data without modifying state.

What parameters does secrets accept? +

secrets accepts 10 parameters: path, action, dryRun, repoPath, check_env, max_depth, scan_type, check_files, search_path, check_authorized_keys. Required: action. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on secrets? +

Register the Defense 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 Defense. Nothing to install.

What risk level is secrets? +

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

Can I rate-limit secrets? +

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.

How do I block secrets completely? +

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.

What MCP server provides secrets? +

secrets is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Defense, and thousands of servers like it.

Across the catalogue

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Defense's. Pull the full record:

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.