Read the file contents of a specific blob.
AI agents call pg_git_read_blob 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.
This tool retrieves file contents from a Git repository without modifying, deleting, or executing anything. It is a pure data-access operation with read-only semantics. Even in the context of a semantic memory system, reading blob contents poses minimal risk—the action is non-destructive and produces no side effects beyond information retrieval.
From the tool's definition Tool name 'pg_git_read_blob' and description 'Read the file contents of a specific blob' indicate a retrieval operation with no data modification. Blob reading is a standard Git read operation.
Attacks that exploit this kind of access
Read the file contents of a specific blob. It is categorised as a Read tool in the PG-Git (Semantic Memory MCP) MCP Server, which means it retrieves data without modifying state.
Register the PG-Git (Semantic Memory MCP) MCP server in PolicyLayer and add a rule for pg_git_read_blob: 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.
pg_git_read_blob 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 pg_git_read_blob 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 pg_git_read_blob. 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.
pg_git_read_blob 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.
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 →