update_context · Code Intelligence MCP Server MCP

WHAT IT DOES

What update_context does on Code Intelligence MCP Server

AI agents use update_context to create or update resources in Code Intelligence MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Intelligence MCP Server environment.

WHY IT NEEDS A POLICY

Why update_context needs a policy

The tool writes data (summaries) to a configuration file (context.yml), modifying state reversibly. This is a Write operation—it creates or modifies data without deleting or executing arbitrary code.

From the tool's definition Save LLM-generated summaries to context.yml.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_context Rate-limited

update_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": {
    "update_context": {
      "limits": [
        {
          "counter": "update_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 Code Intelligence MCP Server, so you can run agents against it safely.

FAQ

Questions about update_context

What does the update_context tool do? +

Save LLM-generated summaries to context.yml. It is categorised as a Write tool in the Code Intelligence MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_context? +

Register the Code Intelligence MCP Server MCP server in PolicyLayer and add a rule for update_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 Code Intelligence MCP Server. Nothing to install.

What risk level is update_context? +

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

Can I rate-limit update_context? +

Yes. Add a rate_limit block to the update_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 update_context completely? +

Set action: deny in the PolicyLayer policy for update_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 update_context? +

update_context is provided by the Code Intelligence MCP Server MCP server (tech-spoke/llm-helper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.