add_context · Context MCP: Risk & Policy

WHAT IT DOES

What add_context does on Context MCP

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

WHY IT NEEDS A POLICY

Why add_context needs a policy

This tool creates and stores new data in a vector database in a reversible manner. It does not execute arbitrary code, delete data irreversibly, or move money. The severity is medium because while it modifies stored data, the operation is reversible (sibling tool 'delete_context' exists) and the blast radius is limited to corrupting or poisoning the knowledge base rather than system-wide damage.

From the tool's definition Tool name 'add_context' and description states it is used to 'Add a piece of context/knowledge to the vector database' and 'store information that can be retrieved later.' This is a create/write operation that persists data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_context Rate-limited

add_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": {
    "add_context": {
      "limits": [
        {
          "counter": "add_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 MCP, so you can run agents against it safely.

FAQ

Questions about add_context

What does the add_context tool do? +

Add a piece of context/knowledge to the vector database. Use this to store information that can be retrieved later for relevant queries. It is categorised as a Write tool in the Context MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_context? +

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

What risk level is add_context? +

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

Can I rate-limit add_context? +

Yes. Add a rate_limit block to the add_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 add_context completely? +

Set action: deny in the PolicyLayer policy for add_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 add_context? +

add_context is provided by the Context MCP server (raunak-dev-18/context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.