🔍 Search a project
AI agents call indexfoundry_project_query 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 searches/queries a project to retrieve results. Searching is a non-destructive read operation that retrieves data without modification, creation, or deletion. The context (vector database search within a RAG application) reinforces that this is data retrieval. Severity is low because misuse would at worst expose indexed content the AI can already access, with no destructive or financial impact.
From the tool's definition Tool name contains 'query' and description states 'Search a project' — these are read-only retrieval operations with no side effects.
Attacks that exploit this kind of access
🔍 Search a project. 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_project_query: 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_query 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_project_query 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_query. 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_query 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 →