Store custom data entry
AI agents use log_custom_data to create or update resources in SDOF Knowledge Base — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SDOF Knowledge Base environment.
This tool stores (writes) a custom data entry into the knowledge base. It creates new data persistently, which is a Write operation. It is not destructive (no deletion), not financial, and not purely execution. Severity is medium because an AI agent could misuse it to inject false or misleading data into the persistent memory system, potentially corrupting context used by future AI operations.
From the tool's definition 'log_custom_data' and 'Store custom data entry' indicate creating/writing a new data record
Attacks that exploit this kind of access
Store custom data entry. It is categorised as a Write tool in the SDOF Knowledge Base MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SDOF Knowledge Base MCP server in PolicyLayer and add a rule for log_custom_data: 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 SDOF Knowledge Base. Nothing to install.
log_custom_data 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 log_custom_data 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 log_custom_data. 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.
log_custom_data is provided by the SDOF Knowledge Base MCP server (tgf-between-your-legs/sdof-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 →