Chunk text using various strategies (recursive, semantic, sentence, fixed_size)
AI agents call chunk_text to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs text segmentation—a read-like operation that analyzes and transforms text input into chunks according to specified strategies. There is no indication it creates/modifies persistent data (Write), executes arbitrary code (Execute), deletes data (Destructive), or moves money (Financial). It is a pure computation/analysis utility with no side effects, making it firmly a Read-category risk.
From the tool's definition Tool description states it 'Chunk text using various strategies' — this is a text processing/analysis operation that segments input text without modifying the original data or triggering external side effects.
Attacks that exploit this kind of access
Chunk text using various strategies (recursive, semantic, sentence, fixed_size). It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for chunk_text: 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 ContextForge MCP Gateway. Nothing to install.
chunk_text 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 chunk_text 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 chunk_text. 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.
chunk_text is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →