☁️ Deploy a project to Railway (production deployment). PREREQUISITES: - project_export must have generated deployment files - Railway CLI must be installed and authenticated - OPENAI_API_KEY must be available for /chat endpoint USE dry_run=true FIRST to preview commands without executing WHAT TH...
AI agents invoke indexfoundry_project_deploy to trigger actions in IndexFoundry MCP. 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 executes a deployment pipeline that interacts with external cloud infrastructure (Railway), initializes remote environments, and pushes live applications. While not destructive in the sense of deleting data, it is an Execute category risk because it runs code and external operations whose side effects (new production service, exposed endpoints, resource consumption) are significant and dependent on the…
From the tool's definition The tool "Initializes Railway project in project directory", "Sets environment variables", "Deploys to Railway using Dockerfile", and "Returns public URL".
Attacks that exploit this kind of access
☁️ Deploy a project to Railway (production deployment). PREREQUISITES: - project_export must have generated deployment files - Railway CLI must be installed and authenticated - OPENAI_API_KEY must be available for /chat endpoint USE dry_run=true FIRST to preview commands without executing WHAT THIS DOES: 1. Initializes Railway project in project directory 2. Sets environment variables (OPENAI_API_KEY, etc.) 3. Deploys to Railway using Dockerfile 4. Returns public URL ALTERNATIVE: Use project_serve for local testing first. It is categorised as a Execute tool in the IndexFoundry MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_project_deploy: 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 IndexFoundry MCP. Nothing to install.
indexfoundry_project_deploy 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 indexfoundry_project_deploy 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 indexfoundry_project_deploy. 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.
indexfoundry_project_deploy is provided by the IndexFoundry MCP server (mnehmos/mnehmos.index-foundry.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 →