Medium Risk

mesh_summary

Set a summary of what you are currently working on. This is visible to other agents on the mesh so they know your context.

How to control mesh_summary ↓

What mesh_summary does on Slm Mesh

AI agents use mesh_summary 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.

Medium Risk

Why mesh_summary needs a policy

This tool writes metadata about current work context to a shared state. The operation is reversible (a summary can be updated or cleared), has no destructive capability, and presents minimal security risk—the worst outcome of misuse would be misleading other agents about work status. It does not execute commands, delete data, or involve financial transactions, making Write the appropriate category with low severity.

From the tool's definition Tool performs 'Set a summary' action, which is a write operation that creates or modifies data (the summary state) reversibly. Description explicitly states it makes information 'visible to other agents', confirming data modification.

Documented attack patterns abuse exactly the kind of access mesh_summary gives an agent:

How to control mesh_summary

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_summary:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "mesh_summary": {
      "limits": [
        {
          "counter": "mesh_summary_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mesh_summary 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.

  1. Create a free account and register Slm Mesh — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about mesh_summary

What does the mesh_summary tool do? +

Set a summary of what you are currently working on. This is visible to other agents on the mesh so they know your context. 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.

How do I enforce a policy on mesh_summary? +

Register the Slm Mesh MCP server in PolicyLayer and add a rule for mesh_summary: 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.

What risk level is mesh_summary? +

mesh_summary is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mesh_summary? +

Yes. Add a rate_limit block to the mesh_summary 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.

How do I block mesh_summary completely? +

Set action: deny in the PolicyLayer policy for mesh_summary. 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.

What MCP server provides mesh_summary? +

mesh_summary 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.

Enforce policy on every Slm Mesh tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.