Klasördeki tüm desteklenen dosyalardan text çıkar
AI agents call extract_text_from_directory to retrieve information from KnowledgeBaseMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and extracts text content from documents without creating, modifying, or deleting any data. It is a passive information retrieval operation with no side effects. The blast radius of misuse is minimal—worst case, an agent could extract sensitive text from documents in a directory, but this is a Read-category risk.
From the tool's definition Tool name 'extract_text_from_directory' and description 'extract text from all supported files in folder' indicate pure data retrieval with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Klasördeki tüm desteklenen dosyalardan text çıkar. It is categorised as a Read tool in the KnowledgeBaseMCP MCP Server, which means it retrieves data without modifying state.
Register the KnowledgeBase MCP server in PolicyLayer and add a rule for extract_text_from_directory: 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 KnowledgeBaseMCP. Nothing to install.
extract_text_from_directory 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_text_from_directory 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_text_from_directory. 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_text_from_directory is provided by the KnowledgeBase MCP server (mehmetozcan-zz/knowledgebasemcp). 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 →