AI agents call find_untested to retrieve information from Synapse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query the FalkorDB-backed code graph to identify untested code paths or functions—a read-only analysis operation with no data modification, deletion, or execution capabilities. Even if it triggers analysis, it retrieves information without side effects. Confidence is moderate due to missing description, but the naming convention and sibling context strongly suggest a Read classification.
From the tool's definition Tool name 'find_untested' with sibling tools like 'find_callees', 'find_dead_code', 'find_usages', 'find_tests_for' indicates a querying/analysis function. The pattern across the server shows read-only navigation of code structure.
Attacks that exploit this kind of access
find_untested. It is categorised as a Read tool in the Synapse MCP Server, which means it retrieves data without modifying state.
Register the Synapse MCP server in PolicyLayer and add a rule for find_untested: 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 Synapse. Nothing to install.
find_untested 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 find_untested 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 find_untested. 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.
find_untested is provided by the Synapse MCP server (synappscodecomprehension/synapps). 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 →