get_page_references
AI agents call get_page_references to retrieve information from Roam Research MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves reference data from a Roam Research graph without modifying any data. It falls under the Read category as a data retrieval operation. Severity is low because querying references poses minimal risk—no data is altered, deleted, or executed. The blast radius of misuse is limited to potential information disclosure.
From the tool's definition Tool name 'get_page_references' combined with server description stating it enables 'retrieving page content, finding references' indicates a read operation.
Attacks that exploit this kind of access
get_page_references. It is categorised as a Read tool in the Roam Research MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Roam Research MCP Server MCP server in PolicyLayer and add a rule for get_page_references: 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 Roam Research MCP Server. Nothing to install.
get_page_references 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_page_references 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_page_references. 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_page_references is provided by the Roam Research MCP Server MCP server (mickm3n/roam-research-mcp). 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 →