AI agents call get_diff to retrieve information from Kontexta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays version control differences without altering state. It is a read-only query operation that compares historical commits. Even though it operates on a git-backed system, the action itself is purely informational retrieval with no side effects, making it Read category with low severity.
From the tool's definition Tool name 'get_diff' and description 'Return the unified diff of one file between two commit hashes' indicates retrieval of git diff information between versions. No modification, deletion, or execution occurs.
Attacks that exploit this kind of access
Return the unified diff of one file between two commit hashes (typically obtained from. It is categorised as a Read tool in the Kontexta MCP Server, which means it retrieves data without modifying state.
Register the Kontexta MCP server in PolicyLayer and add a rule for get_diff: 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 Kontexta. Nothing to install.
get_diff 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_diff 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_diff. 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_diff is provided by the Kontexta MCP server (safiyu/kontexta). 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 →