start_context · Coord MCP: Risk & Policy

WHAT IT DOES

What start_context does on CoordMCP

AI agents invoke start_context to trigger actions in CoordMCP. 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 IT NEEDS A POLICY

Why start_context needs a policy

Without a description, classification relies on context. The sibling tools (assign_task, broadcast_message, complete_task, create_project) suggest this server manages active agent coordination. 'start_context' appears to be an operational control that initiates or activates state affecting multiple agents, making it Execute rather than Write (which would be reversible configuration only) or Read (passive query).

From the tool's definition Tool name 'start_context' suggests initiating or activating a coordination context in a multi-agent system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_context Rate-limited

start_context 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_context": {
      "limits": [
        {
          "counter": "start_context_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about start_context

What does the start_context tool do? +

start_context. It is categorised as a Execute tool in the CoordMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_context? +

Register the Coord MCP server in PolicyLayer and add a rule for start_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 CoordMCP. Nothing to install.

What risk level is start_context? +

start_context is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_context? +

Yes. Add a rate_limit block to the start_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 start_context completely? +

Set action: deny in the PolicyLayer policy for start_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 start_context? +

start_context is provided by the Coord MCP server (siddiquesahabaj/coordmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.