Load files from a local folder using glob patterns. Validates file sizes and content types.
AI agents call indexfoundry_connect_folder to retrieve information from IndexFoundry MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads files from a local folder using glob patterns. It does not modify, delete, or execute anything — it loads/reads content. However, severity is medium because it can access arbitrary local filesystem paths, potentially exposing sensitive files if misused by an AI agent.
From the tool's definition 'Load files from a local folder using glob patterns. Validates file sizes and content types.'
Attacks that exploit this kind of access
Load files from a local folder using glob patterns. Validates file sizes and content types. It is categorised as a Read tool in the IndexFoundry MCP MCP Server, which means it retrieves data without modifying state.
Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_connect_folder: 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_connect_folder is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the indexfoundry_connect_folder 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_connect_folder. 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_connect_folder 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 →