🏗️ [STEP 1/5: CREATE] Create a new RAG project. 📁 STORAGE LOCATION: Projects are stored in the IndexFoundry installation directory: {indexfoundry-install-path}/projects/{project_id}/ PROJECT PIPELINE OVERVIEW: 1. project_create → Initialize project structure 2. project_add_source → Add URLs, PD...
AI agents use indexfoundry_project_create 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 and initializes project metadata and directory structures in the IndexFoundry installation directory. This is a Write operation because it creates new data artifacts (project directories and configuration files) that can be modified or deleted later. There are no destructive, financial, or code execution side effects.
From the tool's definition Creates project directory structure and initializes project.json manifest. The description explicitly states it 'Creates a new RAG project' and 'Initialize project structure', which are reversible write operations that create new data/configuration artifacts.
Attacks that exploit this kind of access
🏗️ [STEP 1/5: CREATE] Create a new RAG project. 📁 STORAGE LOCATION: Projects are stored in the IndexFoundry installation directory: {indexfoundry-install-path}/projects/{project_id}/ PROJECT PIPELINE OVERVIEW: 1. project_create → Initialize project structure 2. project_add_source → Add URLs, PDFs, folders, or sitemaps 3. project_build → Chunk and embed content 4. project_export → Generate deployment files 5. project_serve → Start local server for testing WHAT THIS DOES: - Creates project directory structure (data/, src/, frontend/) - Initializes project.json manifest with embedding config - Generates deployment boilerplate (Dockerfile, package.json) - Creates frontend/index.html chat interface LIBRARIAN PROTOCOL TIP: After creating a project, use librarian_audit to verify project state before proceeding with add_source or build operations. NEXT STEPS: - Use project_add_source to add your content (URLs, PDFs, folders) - Multiple sources can be added before building. 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_create: 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_create 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_create 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_create. 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_create 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 →