send_context · Claude Senator MCP: Risk & Policy

WHAT IT DOES

What send_context does on Claude Senator

AI agents use send_context to create or update resources in Claude Senator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Senator environment.

WHY IT NEEDS A POLICY

Why send_context needs a policy

This tool writes/shares context information (data and pointers) to other Claude instances. It creates new shared state between AI agents, which is a Write operation. The severity is medium because injecting context into other AI instances could influence their behavior, but the description suggests it is a collaborative sharing mechanism rather than a command execution or destructive action.

From the tool's definition 'Share context and pointers with Claude instances for collaboration' — creates/transmits shared context data to other AI instances

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_context Rate-limited

send_context 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_context": {
      "limits": [
        {
          "counter": "send_context_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Senator, so you can run agents against it safely.

FAQ

Questions about send_context

What does the send_context tool do? +

Share context and pointers with Claude instances for collaboration. It is categorised as a Write tool in the Claude Senator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_context? +

Register the Claude Senator MCP server in PolicyLayer and add a rule for send_context: 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 Claude Senator. Nothing to install.

What risk level is send_context? +

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

Can I rate-limit send_context? +

Yes. Add a rate_limit block to the send_context 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 send_context completely? +

Set action: deny in the PolicyLayer policy for send_context. 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 send_context? +

send_context is provided by the Claude Senator MCP server (vvkmnn/claude-senator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.