tenant-read

Read data for a tenant — caller must belong to the same tenant (ABAC).

SERVERFrontmcp SOURCEagentfront/frontmcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/frontmcp/tenant-read.md

WHAT IT DOES

What tenant-read does on Frontmcp

AI agents call tenant-read to retrieve information from Frontmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why tenant-read is rated Low

This tool retrieves or queries tenant data with no side effects and includes built-in multi-tenant isolation controls. The ABAC requirement that the caller must belong to the same tenant significantly limits blast radius.

From the tool's definition Tool name contains 'read' and description states 'Read data for a tenant' with access control enforcement via ABAC (Attribute-Based Access Control) that requires caller to belong to the same tenant.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs tenant-read safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Frontmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tenant-read, this is the rule to start with:

tenant-read Allowed

tenant-read is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "tenant-read": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Frontmcp, apply this rule, and every tenant-read call is checked against it from then on.

FAQ

Questions about tenant-read

What does the tenant-read tool do? +

Read data for a tenant — caller must belong to the same tenant (ABAC). It is categorised as a Read tool in the Frontmcp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on tenant-read? +

Register the Front MCP server in PolicyLayer and add a rule for tenant-read: 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 Frontmcp. Nothing to install.

What risk level is tenant-read? +

tenant-read is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit tenant-read? +

Yes. Add a rate_limit block to the tenant-read 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 tenant-read completely? +

Set action: deny in the PolicyLayer policy for tenant-read. 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 tenant-read? +

tenant-read is provided by the Front MCP server (agentfront/frontmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Front, and thousands of servers like it.

This server

All 206 Front tools →

Across the catalogue

claude_read_file on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →