Skip to main content
Glama
Sign In
now-sdk-ext-mcp

now-sdk-ext-mcp

by sonisoft-cnanda
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Create ACL

create_acl

Create ServiceNow ACLs with roles, conditions, or scripts, write them to a specified update set, and verify each change; confirm user approval first because this is a security change.

Instructions

Create an access control. This is a security change: before calling it, tell the user who gains or loses access and get their go-ahead. It elevates its own session to security_admin (only for ACL tools; other tools stay unelevated) and writes into the named update set, verifying each write by reading it back. With roles, the ACL is inserted inactive, given its roles, cleared of the snc_internal role the platform adds to a role-less ACL, checked, and only then activated. Without roles, snc_internal stays and every internal user who meets the condition or script passes. Put an ACL in its table's application: the platform's documented limits allow only role-based field ACLs on another application's table.

Input Schema

NameRequiredDescriptionDefault
nameNoOther types: the resource name (UI page, REST endpoint, script include, ...).
typeNosys_security_type name. Default record.
fieldNoRecord ACLs: the field, or * for every field. Omit for the table itself.
rolesNoRole names; any one of them passes the ACL. Omit (not []) for an ACL decided by its condition or script alone.
scopeNoThe ACL's application: its scope name (e.g. "x_acme_app"), or "global". Give this or scope_id.
tableNoRecord ACLs: the table.
activeNoDefault true. false creates it inactive.
scriptNoScript that sets `answer`. Also turns on advanced, so the form shows it (the platform runs it either way). Code on an ACL runs on the instance at every check, so setting it needs permission to run code as well as to write.
instanceNoThe ServiceNow instance auth alias to connect to. This is the alias configured via `snc configure` (e.g., "myinstance", "prod", "test"). The user will typically refer to this by name when saying things like "on my myinstance instance". If not provided, falls back to the SN_AUTH_ALIAS environment variable.
scope_idNoThe ACL's application by sys_scope sys_id, instead of scope.
conditionNoEncoded query condition the record must meet. A javascript: value in it is code: it needs permission to run code as well as to write.
operationYesOperation name: read, write, create, delete, execute, ...
update_setYessys_id of an In progress update set of that application (create one with create_update_set). Every write is captured there and verified; the user's own current update set is left as it is.
descriptionNoDescription. The platform may write its own on first save.
decision_typeNoallow (Allow-If; create_acl default) or deny (Deny-Unless: checked first, grants nothing on its own). update_acl: omit to leave it.
admin_overridesNoWhether admin passes regardless (the form's Admin overrides). create_acl default: true; update_acl: omit to leave it.
acknowledge_upgrade_skipNoOnly for an installed Store application, and only after the user has reviewed it: upgrades of that application then skip this ACL until the customization is reviewed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.5.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses self-elevation to security_admin scoped to ACL tools, that writes go into the named update set and are read back for verification, the inactive-then-activate ordering with roles, and the snc_internal clearing. The no-roles branch is spelled out explicitly ('every internal user who meets the condition or script passes'), which is exactly the kind of consequence an agent must surface before writing.

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-loads the highest-stakes fact (security change, get user approval) before mechanics, and every sentence carries operational content. It is dense and the elevation/update-set sentence packs several ideas together, but nothing is filler.

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 17-parameter mutation with no output schema and weak annotations (destructiveHint false), it covers the risk profile, side effects, and ordering that an agent needs. The main gap is that it never says what the call returns or how failures surface, which matters for a verified-write tool.

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 100%, so the baseline is 3, but the description adds conditional meaning the schema cannot convey — the roles vs. omit-roles behavioral fork and the snc_internal consequence, plus the application/scope constraint on field ACLs. It does not tie these back to individual parameter names, so it enriches semantics without fully annotating the 17 parameters.

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

Purpose4/5

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

Opens with a specific verb+resource ('Create an access control') and immediately follows with creation-specific mechanics (insert inactive, assign roles, activate). It never names update_acl or add_acl_role as the alternative, so the agent must infer the boundary from behavior alone rather than from explicit sibling differentiation.

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?

Gives a concrete precondition — tell the user who gains or loses access and get their go-ahead — plus placement guidance ('Put an ACL in its table's application'). It stops short of stating when to use update_acl or add_acl_role instead, leaving the create-vs-modify decision unstated.

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