update_active_context

Overwrites or patches the session-level active context (current focus, open issues, recent changes). Provide content for full replacement OR patch_content for partial merge (set a key to

ServerEngrams
CategoryWrite

How to control update_active_context ↓

WHAT IT DOES

What update_active_context does on Engrams

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

THE RISK

Medium Risk

Why update_active_context needs a policy

This tool creates or modifies data reversibly within an in-memory context system. It does not delete data (which would be Destructive), execute external code (Execute), or move money (Financial). The 'overwrite' capability means it can replace existing context, but this is reversible by subsequent updates.

From the tool's definition 'Overwrites or patches the session-level active context' — the tool modifies existing session state either via full replacement or partial merge operations.

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

POLICY

How to control update_active_context

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_active_context": {
      "limits": [
        {
          "counter": "update_active_context_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

update_active_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.

Create a free account and register Engrams — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Engrams tools

Destructive delete_item Permanently deletes an Engrams item. For decisions, patterns, and progress entries: provid Destructive unbind_code_from_item Permanently removes a code binding by its numeric binding_id. Destructive and irreversible Write batch_log_items Logs multiple items of the SAME type in a single call, reducing round-trips. Supported ite Write bind_code_to_item Creates a code binding linking an Engrams entity to file paths via glob patterns. Valid it Write link_engrams_items Creates a directional relationship link between two Engrams items (e.g., a decision Write log_custom_data Stores or updates a custom key-value entry organized by category. Use for any structured d Write log_governance_rule Creates an enforcement rule within a governance scope. Rules define what is blocked or war Write log_system_pattern Creates or updates a named system/coding pattern (e.g.,

All 42 Engrams tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about update_active_context

What does the update_active_context tool do? +

Overwrites or patches the session-level active context (current focus, open issues, recent changes). Provide content for full replacement OR patch_content for partial merge (set a key to. It is categorised as a Write tool in the Engrams 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_active_context? +

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

What risk level is update_active_context? +

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

Can I rate-limit update_active_context? +

Yes. Add a rate_limit block to the update_active_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_active_context completely? +

Set action: deny in the PolicyLayer policy for update_active_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_active_context? +

update_active_context is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Engrams tool call.

Start from Engrams, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.