📦 [STEP 4/5: EXPORT] Generate deployment files for the project. PREREQUISITES: project_build must have processed sources WHAT THIS DOES: 1. Generates src/index.ts - MCP server with HTTP endpoints 2. Creates Dockerfile for containerized deployment 3. Creates railway.toml for Railway deployment 4....
AI agents use indexfoundry_project_export to create or update resources in IndexFoundry MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your IndexFoundry MCP environment.
This tool creates or modifies files as part of the build/export pipeline. While the files generated are primarily configuration and deployment artifacts rather than arbitrary data, the tool irreversibly writes multiple files to the project structure.
From the tool's definition Generates and creates multiple deployment files: 'Generates src/index.ts', 'Creates Dockerfile', 'Creates railway.toml', 'Generates DEPLOYMENT.md', 'Creates frontend/'
Attacks that exploit this kind of access
📦 [STEP 4/5: EXPORT] Generate deployment files for the project. PREREQUISITES: project_build must have processed sources WHAT THIS DOES: 1. Generates src/index.ts - MCP server with HTTP endpoints 2. Creates Dockerfile for containerized deployment 3. Creates railway.toml for Railway deployment 4. Generates DEPLOYMENT.md with step-by-step instructions 5. Creates frontend/ with chat UI NEXT STEPS: - Run project_serve to test locally - Push to GitHub and deploy to Railway - Or use project_deploy for automated Railway deployment. It is categorised as a Write tool in the IndexFoundry MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_project_export: 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_export is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the indexfoundry_project_export 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_export. 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_export 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 →