Read or write shared state across agent sessions. Use for sharing config values, API endpoints, status flags, etc.
AI agents use mesh_state to create or update resources in Slm Mesh — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slm Mesh environment.
Although the tool supports both read and write operations, the write capability dominates the risk profile. An AI agent misusing this tool could modify shared configuration, endpoints, or status flags across multiple agent sessions and machines, potentially causing widespread disruption to the mesh network and dependent agents.
From the tool's definition Tool description explicitly states 'Read or write shared state' - the write capability is the defining risk. Can modify 'config values, API endpoints, status flags' across sessions.
Documented attack patterns abuse exactly the kind of access mesh_state gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Slm Mesh, and nothing reaches the server without passing your rules. This is the rule we recommend for mesh_state:
{
"version": "1",
"default": "deny",
"tools": {
"mesh_state": {
"limits": [
{
"counter": "mesh_state_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mesh_state stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read or write shared state across agent sessions. Use for sharing config values, API endpoints, status flags, etc. It is categorised as a Write tool in the Slm Mesh MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slm Mesh MCP server in PolicyLayer and add a rule for mesh_state: 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 Slm Mesh. Nothing to install.
mesh_state 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 mesh_state 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 mesh_state. 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.
mesh_state is provided by the Slm Mesh MCP server (qualixar/slm-mesh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Slm Mesh, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Slm Mesh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.