AI agents call get_transaction_info to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries transaction state and metadata only. It has no side effects, does not execute SQL, does not modify data, and does not commit or rollback transactions. The action is informational retrieval, fitting the 'Read' category. Severity is low because misuse cannot cause damage — an agent querying transaction info poses minimal risk.
From the tool's definition Tool description states it 'Get information about an active transaction' — purely retrieves metadata about existing transactions without modifying or executing any operations. No mutations, deletions, or code execution are involved.
Attacks that exploit this kind of access
Get information about an active transaction, including its name, server, database, and when it started. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for get_transaction_info: 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 Postgres. Nothing to install.
get_transaction_info 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 get_transaction_info 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 get_transaction_info. 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.
get_transaction_info is provided by the Postgres MCP server (teja-sudo/postgres-mcp-server). 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 →