AI agents use meshes_refresh_session to create or update resources in Mesheshq — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mesheshq environment.
This tool updates (refreshes) an existing session's access token, which is a reversible modification of authentication state. It does not create a new session record, but it does modify existing credentials. Misuse could allow unauthorized session prolongation, warranting medium severity.
From the tool's definition Refresh the access token for an existing session without minting a new session record
Attacks that exploit this kind of access
Refresh the access token for an existing session without minting a new session record. It is categorised as a Write tool in the Mesheshq MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mesheshq MCP server in PolicyLayer and add a rule for meshes_refresh_session: 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 Mesheshq. Nothing to install.
meshes_refresh_session is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the meshes_refresh_session 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 meshes_refresh_session. 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.
meshes_refresh_session is provided by the Mesheshq MCP server (mesheshq/meshes-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 →