This record as markdown: /tools/ashlesh-t-cognirepo/who-calls.md
What who_calls does on CogniRepo
AI agents call who_calls to retrieve information from CogniRepo without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why who_calls is rated Low
The tool appears to be a Read operation that queries relationships or call patterns from persistent memory structures (knowledge graph, dependency tracking). It retrieves information about how functions/services call each other, with no indication of modification or execution capability.
From the tool's definition Tool name 'who_calls' suggests querying call graphs or dependency relationships. Server provides 'semantic memory, knowledge graph, and session history' - who_calls likely retrieves call chain information from the knowledge graph or dependency data.
Attacks that exploit this kind of access
The rule that runs who_calls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CogniRepo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For who_calls, this is the rule to start with:
who_calls is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CogniRepo, apply this rule, and every who_calls call is checked against it from then on.
Questions about who_calls
who_calls is a read tool on the CogniRepo MCP server. It is categorised as a Read tool in the CogniRepo MCP Server, which means it retrieves data without modifying state.
Register the CogniRepo MCP server in PolicyLayer and add a rule for who_calls: 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 CogniRepo. Nothing to install.
who_calls 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 who_calls 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 who_calls. 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.
who_calls is provided by the CogniRepo MCP server (pypi:cognirepo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CogniRepo, and thousands of servers like it.
This server
Across the catalogue