extract_keywords
AI agents call extract_keywords to retrieve information from FastMCP Document Analyzer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Keyword extraction from documents is a non-destructive data retrieval and analysis operation. Even though the description is empty, the tool name combined with the server's stated capabilities (sentiment analysis, keyword extraction, text statistics) strongly indicates this is a read operation that queries document content without side effects.
From the tool's definition Tool name 'extract_keywords' indicates text analysis/querying of documents. Server description confirms it performs 'keyword extraction' as a read-only analysis operation. No modification, deletion, or execution of external code implied.
Attacks that exploit this kind of access
extract_keywords. It is categorised as a Read tool in the FastMCP Document Analyzer MCP Server, which means it retrieves data without modifying state.
Register the FastMCP Document Analyzer MCP server in PolicyLayer and add a rule for extract_keywords: 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 FastMCP Document Analyzer. Nothing to install.
extract_keywords 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 extract_keywords 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 extract_keywords. 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.
extract_keywords is provided by the FastMCP Document Analyzer MCP server (tathagat017/document-analyser-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 →