secret_type
A comma-separated list of secret types to return. All default secret patterns are returned. To return generic patterns, pass the token name(s) in the parameter. (string, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/secret-type.md
What secret_type does on GitHub
AI agents call secret_type to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why secret_type is rated Low
The description reads like a parameter definition for filtering secret scanning results, not an action tool itself. It describes a read/query operation (returning secret types/patterns) with no side effects. Confidence is low because the description is uninformative as a standalone tool — it appears to be a parameter fragment rather than a complete tool description.
From the tool's definition 'A comma-separated list of secret types to return' — this appears to be a filter/query parameter descriptor rather than a standalone tool description
Attacks that exploit this kind of access
The rule that runs secret_type safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For secret_type, this is the rule to start with:
secret_type is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every secret_type call is checked against it from then on.
Questions about secret_type
A comma-separated list of secret types to return. All default secret patterns are returned. To return generic patterns, pass the token name(s) in the parameter. (string, optional). It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP server in PolicyLayer and add a rule for secret_type: 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 GitHub. Nothing to install.
secret_type 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 secret_type 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 secret_type. 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.
secret_type is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue