indexfoundry_project_add_source

WHAT IT DOES

What indexfoundry_project_add_source does on IndexFoundry MCP

AI agents use indexfoundry_project_add_source 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.

WHY IT NEEDS A POLICY

Why indexfoundry_project_add_source needs a policy

This tool creates or modifies project state by ingesting and registering data sources (URLs, sitemaps, folder paths, PDFs) into a vector database project. While reversible (sources can presumably be removed), it permanently alters the indexed content and project configuration.

From the tool's definition Tool description explicitly states '[STEP 2/5: ADD] Add data source(s) to a project' and lists SOURCE TYPES for ingesting content into a project. The verb 'Add' and the word 'source(s)' indicate data is being written/created into the vector database project.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

indexfoundry_project_add_source Rate-limited

indexfoundry_project_add_source stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "indexfoundry_project_add_source": {
      "limits": [
        {
          "counter": "indexfoundry_project_add_source_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches IndexFoundry MCP, so you can run agents against it safely.

FAQ

Questions about indexfoundry_project_add_source

What does the indexfoundry_project_add_source tool do? +

📥 [STEP 2/5: ADD] Add data source(s) to a project. PREREQUISITES: project_create must have been run first SOURCE TYPES (use exactly one per source): - url: Single webpage (HTML content extracted) - sitemap_url: Crawl all pages in sitemap.xml - folder_path: Local folder with text/markdown/PDF files - pdf_path: Single PDF file (local path or URL) MODES: - Single: Provide one source directly in parameters - Batch: Use \. 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.

How do I enforce a policy on indexfoundry_project_add_source? +

Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_project_add_source: 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.

What risk level is indexfoundry_project_add_source? +

indexfoundry_project_add_source is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit indexfoundry_project_add_source? +

Yes. Add a rate_limit block to the indexfoundry_project_add_source 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.

How do I block indexfoundry_project_add_source completely? +

Set action: deny in the PolicyLayer policy for indexfoundry_project_add_source. 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.

What MCP server provides indexfoundry_project_add_source? +

indexfoundry_project_add_source 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.