// SCAN REPORT

UseGrant MCP Server

26 tools. 14 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated: 5 Jul 2026

14 can modify or destroy data

12 read-only

26 tools total

Community server · catalogue entry verified 05/07/2026

How to control UseGrant MCP Server ↓

TOOL MAP

What UseGrant MCP Server exposes to your agents

Read (12) Write / Execute (8) Destructive / Financial (6)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous UseGrant MCP Server tools

Destructive · High delete_client Deletion is an irreversible operation that cannot be undone without manual intervention or backups. Destructive · High delete_domain Deletion of a domain is an irreversible operation that cannot be undone through normal means. Destructive · High delete_provider Deleting a provider is a destructive operation that cannot be undone and will remove the provider record from the UseGrant platform. Destructive · High delete_tenant This tool irreversibly deletes a tenant entity.

14 of UseGrant MCP Server's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control UseGrant MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and UseGrant MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_client": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_domain": {
    "limits": [
      {
        "counter": "add_domain_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_client": {
    "limits": [
      {
        "counter": "get_client_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register UseGrant MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON USEGRANT →

Instant setup, no code required.

FULL CATALOGUE

All 26 UseGrant MCP Server tools

DESTRUCTIVE 6 tools

Destructive delete_client Delete a client from a provider Destructive delete_domain Delete a domain from a provider Destructive delete_provider Delete a provider Destructive delete_tenant Delete a tenant Destructive delete_tenant_provider Delete a provider for a tenant Destructive delete_tenant_provider_policy Delete a policy for a tenant provider

EXECUTE 1 tools

Execute verify_domain Verify a domain for a provider

WRITE 7 tools

Write add_domain Add a domain to a provider Write create_access_token Create a new access token for a client Write create_client Create a new client for a provider Write create_provider Create a new provider Write create_tenant Create a new tenant Write create_tenant_provider Create a new provider for a tenant Write create_tenant_provider_policy Create a new policy for a tenant provider

READ 12 tools

Read get_client Get client details by provider and client ID Read get_domain Get a domain by provider and domain ID Read get_provider Get a provider by ID Read get_tenant Get a tenant by ID Read get_tenant_provider Get a provider for a tenant Read get_tenant_provider_policy Get a policy for a tenant provider Read list_clients List all clients Read list_domains List all domains for a provider Read list_providers List all providers Read list_tenant_provider_policies List all policies for a tenant provider Read list_tenant_providers List all providers for a tenant Read list_tenants List all tenants

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about UseGrant MCP Server

Can an AI agent delete data through the UseGrant MCP Server MCP server? +

Yes. The UseGrant MCP Server server exposes 6 destructive tools including delete_client, delete_domain, delete_provider. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through UseGrant MCP Server? +

The UseGrant MCP Server server has 7 write tools including add_domain, create_access_token, create_client. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach UseGrant MCP Server.

How many tools does the UseGrant MCP Server MCP server expose? +

26 tools across 3 categories: Destructive, Read, Write. 12 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on UseGrant MCP Server? +

Register the UseGrant MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every UseGrant MCP Server tool call.

Deterministic rules across all 26 UseGrant MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON USEGRANT →

Instant setup, no code required.

26 UseGrant MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.