Chat with uploaded documents using file attachments.
AI agents call chat_with_files to retrieve information from AgentSpawnMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries content from uploaded files to enable conversation. It performs read-only operations on data without side effects, modifications, or destructive actions. The file data is accessed for analysis and response generation, which is characteristic of Read category tools.
From the tool's definition Tool description states 'Chat with uploaded documents using file attachments' - the verb 'chat with' and the object 'documents' indicate retrieval and querying of data from files without modification.
Attacks that exploit this kind of access
Chat with uploaded documents using file attachments. It is categorised as a Read tool in the AgentSpawnMCP MCP Server, which means it retrieves data without modifying state.
Register the AgentSpawn MCP server in PolicyLayer and add a rule for chat_with_files: 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 AgentSpawnMCP. Nothing to install.
chat_with_files 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 chat_with_files 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 chat_with_files. 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.
chat_with_files is provided by the AgentSpawn MCP server (sandsaber/agentspawnmcp). 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 →