session-isolation
Test session isolation between different clients
This record as markdown: /tools/frontmcp/session-isolation.md
What session-isolation does on Frontmcp
AI agents invoke session-isolation to trigger actions in Frontmcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why session-isolation is rated High
The tool 'tests' session isolation, which implies executing some form of operation or probe across different client sessions. This is an Execute-category action since it runs a test/validation process. The severity is medium because misuse could potentially expose session data or disrupt session boundaries, but the description is vague, which lowers confidence.
From the tool's definition 'Test session isolation between different clients' — triggers a test/execution operation across session boundaries
Attacks that exploit this kind of access
The rule that runs session-isolation safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Frontmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For session-isolation, this is the rule to start with:
session-isolation stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Frontmcp, apply this rule, and every session-isolation call is checked against it from then on.
Questions about session-isolation
Test session isolation between different clients. It is categorised as a Execute tool in the Frontmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Front MCP server in PolicyLayer and add a rule for session-isolation: 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 Frontmcp. Nothing to install.
session-isolation is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the session-isolation 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 session-isolation. 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.
session-isolation is provided by the Front MCP server (agentfront/frontmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Front, and thousands of servers like it.
Across the catalogue