// MCP TOOL REFERENCE

kage_compact

ServerKage
CategoryDestructive

WHAT IT DOES

What kage_compact does on Kage

AI agents call kage_compact to permanently remove resources in Kage — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

THE RISK

Critical Risk

Why kage_compact needs a policy

When dry_run=false, this tool irreversibly prunes citations and deprecates memory packets in the repository's git-tracked JSON store. Pruning/deprecating stored memory entries is not easily reversible (especially across team-shared, git-tracked state), making this Destructive. The blast radius is high because misuse could wipe shared institutional memory for the entire team and all agents.

From the tool's definition prune dead citations, deprecate hard-stale packets...pass dry_run=false to apply pruning/deprecation

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

POLICY

How to control kage_compact

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

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "kage_compact"
  ]
}

kage_compact disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

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

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Kage tools

Destructive kage_context_slot_delete Delete a repo-local context slot by label. Execute kage_refresh Rebuild repo indexes, code graph, memory graph, metrics, and stale-memory metadata. Agents Write kage_graph_registry Build a signed graph-registry manifest for generated memory graph, code graph, indexes, me Write kage_structural_index Build the complete cache-backed structural index for large repos. This covers all supporte Write kage_observe Store an automatic local observation event from an agent session. Observations are privacy Write kage_capture Create a repo-local Kage memory packet immediately. Org/global promotion still requires ex Write kage_code_index Write external code index artifacts consumed by the code graph. Prefers SCIP when scip-typ Write kage_context_slot_set Create or update a repo-local pinned context slot. Use for durable, high-signal repo guida

All 62 Kage tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Kage → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about kage_compact

What does the kage_compact tool do? +

Consolidate repo memory: prune dead citations, deprecate hard-stale packets, and surface near-duplicate clusters to merge (via kage_supersede). Defaults to a dry run; pass dry_run=false to apply pruning/deprecation. Duplicate merging stays an agent decision — no hosted LLM is used. It is categorised as a Destructive tool in the Kage MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on kage_compact? +

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

What risk level is kage_compact? +

kage_compact is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit kage_compact? +

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

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

kage_compact is provided by the Kage MCP server (@kage-core/kage-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Kage tool call.

Start from Kage, 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.

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