STEP 2 for clients without sampling: Take analysis JSON from step 1 and return a formatted prompt for generating the video script. Copy the returned prompt to your LLM to get the script JSON.
AI agents call prepare_script_prompt to retrieve information from Git Commit Video Walkthrough Generator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads input data (analysis JSON) and formats it into a prompt string for downstream use. It performs no writes, deletions, executions, or financial operations. The output is informational only, intended to be copied to an external LLM. This is a classic Read operation: data retrieval and transformation without side effects.
From the tool's definition Tool description states it 'take[s] analysis JSON from step 1 and return[s] a formatted prompt' — a pure transformation and retrieval operation with no side effects, data modification, code execution, or external state changes.
Attacks that exploit this kind of access
STEP 2 for clients without sampling: Take analysis JSON from step 1 and return a formatted prompt for generating the video script. Copy the returned prompt to your LLM to get the script JSON. It is categorised as a Read tool in the Git Commit Video Walkthrough Generator MCP Server, which means it retrieves data without modifying state.
Register the Git Commit Video Walkthrough Generator MCP server in PolicyLayer and add a rule for prepare_script_prompt: 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 Git Commit Video Walkthrough Generator. Nothing to install.
prepare_script_prompt 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 prepare_script_prompt 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 prepare_script_prompt. 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.
prepare_script_prompt is provided by the Git Commit Video Walkthrough Generator MCP server (tomatitito/code-walkthrough-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 →