[OCD] コンテキストを変更 (create/update/delete/move 一括実行) 全ての書き込み操作を単一のツールで実行可能。 複数の操作を配列で渡すことで一括処理できます。 ${isLocalDev ?
AI agents call ocd_mutate_context to permanently remove resources in OCD - Organized Context Datastore (MCP) — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although this tool can perform Write operations (create/update) and Execute-like operations (move), it explicitly includes 'delete' capability on stored data. Deletion of context data from persistent storage is irreversible and cannot be undone, making this a Destructive operation. The batch nature ('一括処理') amplifies the risk—a single call could delete multiple contexts.
From the tool's definition Tool description explicitly lists 'create/update/delete/move 一括実行' (create/update/delete/move batch execution). The 'delete' operation on persistent structured memory (Markdown files in hierarchical tree) is irreversible.
Attacks that exploit this kind of access
[OCD] コンテキストを変更 (create/update/delete/move 一括実行) 全ての書き込み操作を単一のツールで実行可能。 複数の操作を配列で渡すことで一括処理できます。 ${isLocalDev ?. It is categorised as a Destructive tool in the OCD - Organized Context Datastore (MCP) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the OCD - Organized Context Datastore (MCP) MCP server in PolicyLayer and add a rule for ocd_mutate_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 OCD - Organized Context Datastore (MCP). Nothing to install.
ocd_mutate_context is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the ocd_mutate_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.
Set action: deny in the PolicyLayer policy for ocd_mutate_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.
ocd_mutate_context is provided by the OCD - Organized Context Datastore (MCP) MCP server (teamstove/organized-context-datastore-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →