pg_git_read_tree

Read the directory structure (DAG node) of a specific repository. If tree_id is omitted, it attempts to read the root tree of the

Server PG-Git (Semantic Memory MCP) kruschdev/pg-git-mcp
Category Read
Risk class Low
Parameters 00 required

What pg_git_read_tree does on PG-Git (Semantic Memory MCP)

AI agents call pg_git_read_tree to retrieve information from PG-Git (Semantic Memory MCP) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why pg_git_read_tree needs a policy

This tool retrieves and queries directory structure information from a Git repository stored in PostgreSQL. It has no side effects, does not modify data, execute code, or delete content. The operation is purely informational, consistent with Read category tools like 'list' and 'get'. Low severity reflects minimal blast radius—an AI agent misusing this tool would only over-read directory metadata.

From the tool's definition Tool name includes 'read' and description states 'Read the directory structure'; returns tree structure metadata without modification, deletion, or execution capabilities.

Risk signalsAdmin/system-level operation

Questions about pg_git_read_tree

What does the pg_git_read_tree tool do? +

Read the directory structure (DAG node) of a specific repository. If tree_id is omitted, it attempts to read the root tree of the. It is categorised as a Read tool in the PG-Git (Semantic Memory MCP) MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on pg_git_read_tree? +

Register the PG-Git (Semantic Memory MCP) MCP server in PolicyLayer and add a rule for pg_git_read_tree: 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 PG-Git (Semantic Memory MCP). Nothing to install.

What risk level is pg_git_read_tree? +

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

Can I rate-limit pg_git_read_tree? +

Yes. Add a rate_limit block to the pg_git_read_tree 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 pg_git_read_tree completely? +

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

pg_git_read_tree is provided by the PG-Git (Semantic Memory MCP) MCP server (kruschdev/pg-git-mcp). 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.