Low Risk

use_context_pack

use_context_pack

How to control use_context_pack ↓

AI agents call use_context_pack to retrieve information from PAMPA without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Even though use_context_pack only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Documented attack patterns abuse exactly the kind of access use_context_pack gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and PAMPA, and nothing reaches the server without passing your rules. This is the rule we recommend for use_context_pack:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "use_context_pack": {}
  }
}

use_context_pack is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register PAMPA — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the use_context_pack tool do? +

use_context_pack. It is categorised as a Read tool in the PAMPA MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on use_context_pack? +

Register the PAMPA MCP server in PolicyLayer and add a rule for use_context_pack: 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 PAMPA. Nothing to install.

What risk level is use_context_pack? +

use_context_pack is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit use_context_pack? +

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

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

use_context_pack is provided by the PAMPA MCP server (tecnomanu/pampa). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PAMPA tool call.

Deterministic rules across all 6 PAMPA tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

6 PAMPA tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.