Run all price data connectors (Open Food Facts, Kroger, Walmart, REWE, Migros, A101) to fetch fresh prices for a product in a specific country. Saves results to the database.
AI agents invoke run_connectors to trigger actions in PriceAtlas MCP Server. 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 actively executes multiple external connector integrations (Open Food Facts, Kroger, Walmart, etc.) and persists the fetched data to a database. It spans Execute (running connectors, triggering external network operations) and Write (saving results to DB). Since Execute > Write in severity ordering, it is classified as Execute.
From the tool's definition 'Run all price data connectors... to fetch fresh prices for a product... Saves results to the database' — triggers external operations (scraping/API calls to multiple retailers) and writes results to a database.
Attacks that exploit this kind of access
Run all price data connectors (Open Food Facts, Kroger, Walmart, REWE, Migros, A101) to fetch fresh prices for a product in a specific country. Saves results to the database. It is categorised as a Execute tool in the PriceAtlas MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PriceAtlas MCP Server MCP server in PolicyLayer and add a rule for run_connectors: 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 PriceAtlas MCP Server. Nothing to install.
run_connectors 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 run_connectors 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 run_connectors. 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.
run_connectors is provided by the PriceAtlas MCP Server MCP server (musaceylan/priceatlas-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 →