AI agents call get_subgraph to retrieve information from Wikimcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a graph query to support visualization of wiki structure. It has no side effects, does not modify data, and merely retrieves and returns existing graph topology information. The blast radius of misuse is minimal — an agent could only retrieve unwanted graph visualizations, not alter or execute anything.
From the tool's definition Tool 'get_subgraph' retrieves a 'bounded neighbourhood graph around page (nodes+edges), for visualization' — it queries and returns graph data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Bounded neighbourhood graph around page (nodes+edges), for visualization. It is categorised as a Read tool in the Wikimcp MCP Server, which means it retrieves data without modifying state.
Register the Wiki MCP server in PolicyLayer and add a rule for get_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 Wikimcp. Nothing to install.
get_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 get_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 get_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.
get_subgraph is provided by the Wiki MCP server (mohith-das/wikimcp). 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 →