Read and parse a Claude Code JSONL transcript file through the canonical transcript parser.
AI agents call graph_read_transcript to retrieve information from Graph-Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and parses existing transcript data without creating, modifying, deleting, or executing operations. It performs a query/retrieval function only, making it a Read operation with low severity since it has no side effects on the graph or external systems.
From the tool's definition Tool name contains 'read' and description states 'Read and parse...transcript file' with no modification, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
Read and parse a Claude Code JSONL transcript file through the canonical transcript parser. It is categorised as a Read tool in the Graph-Memory MCP Server, which means it retrieves data without modifying state.
Register the Graph-Memory MCP server in PolicyLayer and add a rule for graph_read_transcript: 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 Graph-Memory. Nothing to install.
graph_read_transcript 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 graph_read_transcript 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 graph_read_transcript. 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.
graph_read_transcript is provided by the Graph-Memory MCP server (stevepridemore/graph-memory). 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 →