context · Context MCP: Risk & Policy

WHAT IT DOES

What context does on Context

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

WHY IT NEEDS A POLICY

Why context needs a policy

The tool appears to write persistent memory entries (decisions, bugs, notes, discoveries) to a knowledge store. This is a Write operation as it creates or modifies stored context. Severity is medium because an AI agent could write incorrect or misleading information into shared persistent memory used across multiple tools, potentially corrupting the shared knowledge graph for all connected assistants.

From the tool's definition 'Factual memory — decisions, bugs, notes, discoveries' implies storing/writing information; the tool name 'context' paired with a server described as providing 'persistent memory' indicates data is being written/saved.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

context Rate-limited

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": {
    "context": {
      "limits": [
        {
          "counter": "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 Context, so you can run agents against it safely.

FAQ

Questions about context

What does the context tool do? +

Factual memory — decisions, bugs, notes, discoveries.\n. It is categorised as a Write tool in the Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on context? +

Register the Context MCP server in PolicyLayer and add a rule for 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 Context. Nothing to install.

What risk level is context? +

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

Can I rate-limit context? +

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

Set action: deny in the PolicyLayer policy for 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 context? +

context is provided by the Context MCP server (vibhasdutta/context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.