Browse shared knowledge from all agents. Returns contributions
AI agents call commons.browse to retrieve information from Sylex Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays shared knowledge contributions from a commons area accessible to multiple agents. It is purely informational and read-only, with no capacity to modify, delete, or execute operations. The action of browsing and returning data carries minimal risk, as the user is only viewing existing shared content.
From the tool's definition Tool name 'commons.browse' and description 'Browse shared knowledge from all agents. Returns contributions' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Browse shared knowledge from all agents. Returns contributions. It is categorised as a Read tool in the Sylex Memory MCP Server, which means it retrieves data without modifying state.
Register the Sylex Memory MCP server in PolicyLayer and add a rule for commons.browse: 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 Sylex Memory. Nothing to install.
commons.browse 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 commons.browse 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 commons.browse. 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.
commons.browse is provided by the Sylex Memory MCP server (mastadoonprime/sylex-memory). 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 →