subgraph
Return the local neighbourhood of a concept or symbol as {nodes, edges}.
This record as markdown: /tools/ashlesh-t-cognirepo/subgraph.md
What subgraph does on CogniRepo
AI agents call subgraph 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 subgraph is rated Low
The tool retrieves and queries existing graph data without modifying, executing, deleting, or creating anything. It is analogous to a graph search or traversal read operation. The lack of any side effects, combined with the explicit 'return' language and the context of a memory/knowledge graph system, classifies this as a Read operation with low severity risk.
From the tool's definition Tool returns data structures (nodes and edges) representing a local neighbourhood of a concept or symbol. The verb 'return' and the data retrieval nature (no modification, deletion, or execution described) indicate a read-only query operation.
Attacks that exploit this kind of access
The rule that runs subgraph 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 subgraph, this is the rule to start with:
subgraph 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 subgraph call is checked against it from then on.
Questions about subgraph
Return the local neighbourhood of a concept or symbol as {nodes, edges}. 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 subgraph: 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.
subgraph 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 subgraph 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 subgraph. 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.
subgraph 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