add_document
AI agents use add_document to create or update resources in KnowledgeSmith MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KnowledgeSmith MCP environment.
The tool appears to create or add documents to a structured knowledge base. This is reversible (documents can be deleted), so it is Write rather than Destructive. The empty description reduces confidence slightly, but the server description and sibling tools provide sufficient context.
From the tool's definition Tool name 'add_document' combined with server's advertised 'complete CRUD functionality' and 'editing of structured RBT documents' indicates document creation capability.
Attacks that exploit this kind of access
add_document. It is categorised as a Write tool in the KnowledgeSmith MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KnowledgeSmith MCP server in PolicyLayer and add a rule for add_document: 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 KnowledgeSmith MCP. Nothing to install.
add_document 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 add_document 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 add_document. 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.
add_document is provided by the KnowledgeSmith MCP server (leo7nel23/knowledgesmith-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 →