read_raw_collection
AI agents call read_raw_collection to retrieve information from DataFlow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'read' prefix and 'collection' suffix strongly indicate this is a query/retrieval operation. MongoDB read operations have minimal blast radius—they access data but do not modify, delete, or execute arbitrary code. Confidence is slightly reduced due to missing description, but the tool name is explicit enough to classify reliably as Read with low severity.
From the tool's definition Tool name 'read_raw_collection' indicates a read operation on a MongoDB collection. Description is empty, but the name and context within a CRUD operations server clearly suggest data retrieval with no modification.
Attacks that exploit this kind of access
read_raw_collection. It is categorised as a Read tool in the DataFlow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DataFlow MCP Server MCP server in PolicyLayer and add a rule for read_raw_collection: 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 DataFlow MCP Server. Nothing to install.
read_raw_collection 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 read_raw_collection 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 read_raw_collection. 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.
read_raw_collection is provided by the DataFlow MCP Server MCP server (sreetarak2/dataflow_mcp). 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 →