add prompt templates to MCP server for guided security workflows#296
Merged
Conversation
Closes msoedov#192 Three prompt templates via @mcp.prompt(): - security_scan_prompt: full scan with configurable probe budget - verify_llm_prompt: quick reachability check before committing to a scan - adversarial_probe_prompt: multi-step attack session with findings summary Placed before the tool definitions with a clear section comment. No existing tool behaviour changed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #192
Adds three reusable prompt templates to the MCP server using the
@mcp.prompt()decorator.What's in here:
security_scan_prompt(llm_spec, max_budget)— guides the client through a full security scan: start it, watch it, stop it.verify_llm_prompt(llm_spec)— quick reachability check so you can confirm a spec works before committing to a full scan.adversarial_probe_prompt(llm_spec)— sets up a multi-step adversarial run with optimization on and asks the client to surface the worst findings at the end.All three return plain strings, which is the correct return type for FastMCP prompts. They're placed in their own section above the tools so the file stays easy to navigate. No existing tool behaviour is touched.