Skip to main content
Glama

sn_mcp_create_server

Create a ServiceNow MCP server with optional tools. Draft adds a registry entry; active publishes the endpoint and waits for auto-created OAuth, ACL, and AI Control Tower records.

Instructions

Create a server in ServiceNow MCP Server Console (sn_mcp_server_registry), optionally with tools attached. The endpoint is /sncapps/mcp-server/mcp/. A draft server creates only the registry row. When the server is (or later becomes) active, ServiceNow itself auto-creates: an OAuth client in Application Registry named like the server (redirect mcp_redirect.do, JWT tokens), an AutoGen OAuth provider with profile and resource, an AutoGen connection alias with HTTP connection, OAuth 2.0 credential and Workflow Data Fabric mapping, an auth server connection, a default-allow execute ACL named after the endpoint, and AI Control Tower records (product model, CI, digital asset). For an active server this tool waits for those and returns them. Remove everything with sn_mcp_delete_server. REQUIRES WRITE_ENABLED=true and the sn_mcp_server.admin role.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "label": "<label>"
    },
    "name": "sn_mcp_create_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoUnique server name (lowercase, digits, _ and .). Default: the label as snake_case
labelYesDisplay label, e.g. "Service desk tools"
toolsNoExisting tool definition names or sys_ids to attach, e.g. ["sn_mcp_server.incident_summarization"]
statusNoDefault draft. active publishes the endpoint and triggers the OAuth / ACL / AI Control Tower setup
descriptionNoShort description MCP clients see (default: the label)
wait_secondsNoHow long to wait for the auto-created OAuth/ACL records of an active server (default 30, max 120)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations it discloses substantial hidden behavior: the exact list of side-effect records ServiceNow auto-creates (OAuth client, AutoGen provider/alias/credential, auth server connection, execute ACL, AI Control Tower records), that active creation blocks waiting for them, and the response contents. It also states hard prerequisites (WRITE_ENABLED=true and the sn_mcp_server.admin role), which the annotations alone would not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then endpoint, then draft-vs-active behavior, then the side-effect inventory, then cleanup and prerequisites — a sensible order. The long comma-separated list of auto-created records is dense but each item carries real information; minor tightening is possible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating, open-world creation tool with no output schema, it covers side effects, waiting semantics, prerequisites, and the teardown path. It could say more about what the return payload looks like (e.g., whether IDs of created records are included) and about failure/partial-creation behavior, but nothing essential to correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3; the description earns above that by tying parameters to behavior — 'active' triggers the OAuth/ACL setup and wait, and the name feeds the endpoint with dots converted to underscores. The tools, description, and wait_seconds parameters are not elaborated in prose, leaving some room unused.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Create a server in ServiceNow MCP Server Console (sn_mcp_server_registry)') and even gives the resulting endpoint URL pattern. It explicitly routes removal to the sn_mcp_delete_server sibling, so an agent can distinguish creation from deletion without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly distinguishes draft creation (registry row only) from active creation (publishes endpoint, triggers OAuth/ACL/AI Control Tower setup) and points to sn_mcp_delete_server for teardown. It does not explicitly say when to prefer this over sn_mcp_activate_server or sn_mcp_register_external_server, so alternatives are only partially covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools