Merge multiple documents into one file
AI agents use merge_documents to create or update resources in ContextForge MCP Gateway — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ContextForge MCP Gateway environment.
This tool performs a Write operation—it creates a new combined document by merging inputs, which is a reversible modification of data. While the merge itself is not destructive (original documents may persist), it creates a new artifact and modifies the information structure.
From the tool's definition Tool name 'merge_documents' and description 'Merge multiple documents into one file' indicate creation/modification of data through combining existing documents.
Attacks that exploit this kind of access
Merge multiple documents into one file. It is categorised as a Write tool in the ContextForge MCP Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for merge_documents: 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.
merge_documents is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the merge_documents 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 merge_documents. 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.
merge_documents 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 →