// SCAN REPORT

Alfred MCP Server

20 tools. 11 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

11 can modify or destroy data

9 read-only

20 tools total

Community server · catalogue entry verified 04/07/2026

How to control Alfred MCP Server ↓

TOOL MAP

What Alfred MCP Server exposes to your agents

Read (9) Write / Execute (7) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Alfred MCP Server tools

Destructive · High alfred_delete_api_key The tool irreversibly deletes an API key, which cannot be recovered once removed. Destructive · High alfred_delete_connection This tool performs an irreversible deletion operation on a connection object. Destructive · High alfred_delete_execution This tool permanently removes execution records from the system without the ability to undo the operation. Destructive · High alfred_delete_skill This tool performs an irreversible deletion operation on Alfred workflow automation skills.

11 of Alfred MCP Server's 20 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Alfred MCP Server

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

Deny destructive operations

{
  "alfred_delete_api_key": {
    "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

{
  "alfred_create_api_key": {
    "limits": [
      {
        "counter": "alfred_create_api_key_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "alfred_get_connection": {
    "limits": [
      {
        "counter": "alfred_get_connection_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 Alfred 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 ALFRED →

Instant setup, no code required.

FULL CATALOGUE

All 20 Alfred MCP Server tools

DESTRUCTIVE 4 tools

Destructive alfred_delete_api_key Delete an API key by ID. This action is permanent and cannot be undone. Any applications using this key will l Destructive alfred_delete_connection Delete a connection by ID Destructive alfred_delete_execution Delete a specific execution record Destructive alfred_delete_skill Delete a skill by ID with optional force delete

WRITE 7 tools

Write alfred_create_api_key Create a new API key for authenticating with the Alfred API. The API key will only be shown once - save it sec Write alfred_create_connection Create a new connection with name, type, and configuration Write alfred_create_skill Create a new skill with steps, connections, and trigger configuration Write alfred_patch_connection Partially update a connection - only provided fields will be modified Write alfred_patch_skill Partially update a skill - only provided fields will be modified Write alfred_update_connection Update a connection with a complete replacement (all fields should be provided) Write alfred_update_skill Update a skill with a complete replacement (all fields should be provided)

READ 9 tools

Read alfred_get_connection Retrieve a specific connection by its ID Read alfred_get_execution Get detailed information about a specific execution Read alfred_get_execution_stats Get execution statistics including success rates, duration averages, and costs Read alfred_get_execution_trace Get detailed trace/logs for a specific execution Read alfred_get_skill Retrieve a specific skill by its ID Read alfred_list_api_keys List all API keys associated with your Alfred account. Note: actual key values are not shown for security - on Read alfred_list_connections List all Alfred connections with optional filtering, sorting, and pagination Read alfred_list_executions List executions with optional filtering by skill, status, trigger type, and date range Read alfred_list_skills List all Alfred skills with optional filtering, sorting, and pagination

EXPLORE

Related servers

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

FAQ

Questions about Alfred MCP Server

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

Yes. The Alfred MCP Server server exposes 4 destructive tools including alfred_delete_api_key, alfred_delete_connection, alfred_delete_execution. 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 Alfred MCP Server? +

The Alfred MCP Server server has 7 write tools including alfred_create_api_key, alfred_create_connection, alfred_create_skill. 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 Alfred MCP Server.

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

20 tools across 3 categories: Destructive, Read, Write. 9 are read-only. 11 can modify, create, or delete data.

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

Register the Alfred 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 Alfred MCP Server tool call.

Deterministic rules across all 20 Alfred MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ALFRED →

Instant setup, no code required.

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