AI agents call find_dependencies 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.
Although deprecated, the tool's intended purpose was to retrieve dependency information from the indexed codebase—a read-only operation. The removal status and lack of active implementation further reduce any potential risk. Classification as Read is appropriate since dependency queries are non-destructive information retrieval operations.
From the tool's definition Tool description states it has been removed and redirects to get_context_for. The stated predecessor functionality (finding dependencies) is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
This tool has been removed. Use get_context_for instead -- it includes dependencies in its output. 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_dependencies: 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_dependencies 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_dependencies 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_dependencies. 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_dependencies 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 →