Start a new database connection
AI agents invoke db.start_connection to trigger actions in MCP Fullstack. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool establishes a database connection, which is an operation that triggers external system interaction and enables execution of arbitrary database commands. While the connection itself is not destructive, it is a gateway to Execute-category operations (db.end_connection, queries, etc.).
From the tool's definition "Start a new database connection" - initiates a database connection which enables subsequent database operations whose effects depend on how the connection is used (queries, modifications, or deletions).
Attacks that exploit this kind of access
Start a new database connection. It is categorised as a Execute tool in the MCP Fullstack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for db.start_connection: 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 MCP Fullstack. Nothing to install.
db.start_connection is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the db.start_connection 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 db.start_connection. 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.
db.start_connection is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →