This record as markdown: /tools/54rt1n-container-mcp/kb-manage.md
What kb_manage does on Container-MCP
AI agents use kb_manage to create or update resources in Container-MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Container-MCP environment.
Why kb_manage is rated Medium
The description is empty, so classification relies on the tool name and context. 'kb_manage' likely involves managing a knowledge base (create, update, delete operations). Sibling tools suggest a knowledge base subsystem exists. 'Manage' typically implies write-level operations (creating, modifying, organizing), but without a description it could span Write to Destructive.
From the tool's definition Tool name 'kb_manage' on a server with sibling tools including 'kb_create_document', 'kb_read', 'kb_search' — no description provided.
Attacks that exploit this kind of access
The rule that runs kb_manage safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Container-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For kb_manage, this is the rule to start with:
kb_manage 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Container-MCP, apply this rule, and every kb_manage call is checked against it from then on.
Questions about kb_manage
kb_manage is a write tool on the Container MCP server. It is categorised as a Write tool in the Container-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Container MCP server in PolicyLayer and add a rule for kb_manage: 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 Container-MCP. Nothing to install.
kb_manage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the kb_manage 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 kb_manage. 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.
kb_manage is provided by the Container MCP server (54rt1n/container-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Container, and thousands of servers like it.
This server
Across the catalogue