recursive
Setting this parameter to true returns the objects or subtrees referenced by the tree. Default is false (boolean, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/recursive.md
What recursive does on GitHub
AI agents call recursive 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 recursive is rated Low
This is a read-only parameter that controls query granularity for tree data retrieval in Git operations. It retrieves nested references without side effects, aligning with the Read category (fetch/query operations). Severity is low because even if recursion is enabled on a large tree, the worst outcome is retrieving more data than intended—no destructive, financial, or executable consequences.
From the tool's definition Tool described as 'returns the objects or subtrees referenced by the tree' — a retrieval operation with no modification, deletion, or execution capability. Optional boolean parameter controlling tree traversal depth.
Attacks that exploit this kind of access
The rule that runs recursive 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 recursive, this is the rule to start with:
recursive 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 recursive call is checked against it from then on.
Questions about recursive
Setting this parameter to true returns the objects or subtrees referenced by the tree. Default is false (boolean, 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 recursive: 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.
recursive 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 recursive 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 recursive. 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.
recursive 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