docx_table_from_context
AI agents call docx_table_from_context to retrieve information from Asset Aware without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming convention ('from_context') and position among conversion and retrieval tools suggest this extracts or retrieves table data without modifying the source document. No write, execute, or destructive operations are implied. Confidence is moderate (0.60) due to an empty tool description, which limits certainty about actual behavior.
From the tool's definition Tool name 'docx_table_from_context' suggests extraction of table data from DOCX context. The server description emphasizes 'retrieve and analyze PDF assets' with no mention of modifying documents.
Attacks that exploit this kind of access
docx_table_from_context. It is categorised as a Read tool in the Asset Aware MCP Server, which means it retrieves data without modifying state.
Register the Asset Aware MCP server in PolicyLayer and add a rule for docx_table_from_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 Asset Aware. Nothing to install.
docx_table_from_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the docx_table_from_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 docx_table_from_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.
docx_table_from_context is provided by the Asset Aware MCP server (u9401066/asset-aware-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 →