AI agents call word_count to retrieve information from Small without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only analysis of text input, returning computed statistics (word count, character count, line count) with no capability to modify, delete, or execute external operations. It has no blast radius if misused by an agent, as it cannot alter state or trigger unintended consequences.
From the tool's definition Tool name 'word_count' and description 'Count words, characters, and lines in the given text' indicate a data analysis operation that retrieves metrics from provided input without side effects.
Attacks that exploit this kind of access
Count words, characters, and lines in the given text. It is categorised as a Read tool in the Small MCP Server, which means it retrieves data without modifying state.
Register the Small MCP server in PolicyLayer and add a rule for word_count: 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 Small. Nothing to install.
word_count 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 word_count 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 word_count. 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.
word_count is provided by the Small MCP server (nishant-iit/smallmp). 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 →