AI agents use agentbase_store_knowledge to create or update resources in AgentBase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentBase environment.
This tool creates new data in a shared knowledge base. It is a write operation (store/create) that adds a knowledge item and generates embeddings. It does not delete or overwrite existing data, execute code, or involve financial transactions. Misuse could pollute a shared collective knowledge base with false or harmful information, hence medium severity.
From the tool's definition Store a knowledge item. Content is automatically embedded for semantic search.
Attacks that exploit this kind of access
Store a knowledge item. Content is automatically embedded for semantic search. It is categorised as a Write tool in the AgentBase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AgentBase MCP server in PolicyLayer and add a rule for agentbase_store_knowledge: 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 AgentBase. Nothing to install.
agentbase_store_knowledge 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 agentbase_store_knowledge 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 agentbase_store_knowledge. 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.
agentbase_store_knowledge is provided by the AgentBase MCP server (revmischa/agentbase). 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 →