Return a page as two content blocks: [0] a JSON envelope {path, lastModified}, [1] the raw markdown body. The lastModified is the version marker — pass it back as expected_last_modified on a follow-up write_page to guard against interim edits. Accepts a page name with or without the .md suffix (e.g.
AI agents call read_page to retrieve information from Silverbullet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and queries existing page data with no side effects. It does not create, modify, delete, or execute any operations. The sibling tools (append_to_page, create_page, delete_page, write_page) handle mutations; read_page is explicitly a read operation. Severity is low because retrieval of notes poses minimal risk even if invoked by an untrusted agent.
From the tool's definition Tool returns page content and metadata without modification: 'Return a page as two content blocks: [0] a JSON envelope {path, lastModified}, [1] the raw markdown body.' No creation, deletion, or alteration of data occurs.
Attacks that exploit this kind of access
Return a page as two content blocks: [0] a JSON envelope {path, lastModified}, [1] the raw markdown body. The lastModified is the version marker — pass it back as expected_last_modified on a follow-up write_page to guard against interim edits. Accepts a page name with or without the .md suffix (e.g. It is categorised as a Read tool in the Silverbullet MCP Server, which means it retrieves data without modifying state.
Register the Silverbullet MCP server in PolicyLayer and add a rule for read_page: 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 Silverbullet. Nothing to install.
read_page 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 read_page 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 read_page. 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.
read_page is provided by the Silverbullet MCP server (xmatthewx/silverbullet-mcp-server). 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 →