Skip to main content
Glama

fluent_cicd

Run ServiceNow CI/CD tasks from your IDE: install, publish, or roll back app versions and execute ATF tests or test suites, including runs on the ATF Cloud Runner.

Instructions

Run ServiceNow CI/CD operations via the SDK (now-sdk cicd): install an app version from the app repository, publish an app to it, roll an app back, or run an ATF test or test suite (optionally on the ATF Cloud Runner). REQUIRES FLUENT_ENABLED=true and WRITE_ENABLED=true.

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": {
      "action": "<action>"
    },
    "name": "fluent_cicd"
  }
}

Input Schema

NameRequiredDescriptionDefault
authNonow-sdk credential alias (optional)
asyncNoRun as a background job and return a job_id at once. Poll it with get_job. Calls that take longer than about 20 seconds switch to a job on their own.
scopeNoApp scope, e.g. x_acme_app (install, publish, rollback). Use this or appSysId.
actionYesinstall / publish / rollback an app, or run an ATF test suite or a single ATF test
appSysIdNoApp sys_id (install, publish, rollback). Use this or scope.
testNameNoATF test name (test). Use this or testSysId.
directoryNoFluent project directory, used for default app sys_id/version (optional)
testSysIdNoATF test sys_id (test)
appVersionNoApp version, e.g. 1.0.0 (install, publish, rollback)
runInCloudNoRun UI steps on the ATF Cloud Runner (testsuite, test)
browserNameNoBrowser for UI tests, e.g. chrome (testsuite, test)
testSuiteNameNoATF test suite name (testsuite). Use this or testSuiteSysId.
testSuiteSysIdNoATF test suite sys_id (testsuite)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv5.0.1
    • changedInput schema / properties / action / description
      Previous value: -"install a published app version, publish an app scope to the app repo, or run an ATF test suite"New value: +"install / publish / rollback an app, or run an ATF test suite or a single ATF test"
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "install",
      -  "publish",
      -  "testsuite"
      -]New value: +[
      +  "install",
      +  "publish",
      +  "rollback",
      +  "testsuite",
      +  "test"
      +]
    • changedInput schema / properties / appSysId / description
      Previous value: -"App sys_id (required for action=install)"New value: +"App sys_id (install, publish, rollback). Use this or scope."
    • changedInput schema / properties / appVersion / description
      Previous value: -"App version, e.g. 1.0.0 (install/publish)"New value: +"App version, e.g. 1.0.0 (install, publish, rollback)"
    • addedInput schema / properties / async
      Added value: +{
      +  "description": "Run as a background job and return a job_id at once. Poll it with get_job. Calls that take longer than about 20 seconds switch to a job on their own.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / auth
      Added value: +{
      +  "description": "now-sdk credential alias (optional)",
      +  "type": "string"
      +}
    • addedInput schema / properties / browserName
      Added value: +{
      +  "description": "Browser for UI tests, e.g. chrome (testsuite, test)",
      +  "type": "string"
      +}
    • addedInput schema / properties / directory
      Added value: +{
      +  "description": "Fluent project directory, used for default app sys_id/version (optional)",
      +  "type": "string"
      +}
    • addedInput schema / properties / runInCloud
      Added value: +{
      +  "description": "Run UI steps on the ATF Cloud Runner (testsuite, test)",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / scope / description
      Previous value: -"App scope, e.g. x_acme_app (required for action=publish)"New value: +"App scope, e.g. x_acme_app (install, publish, rollback). Use this or appSysId."
    • addedInput schema / properties / testName
      Added value: +{
      +  "description": "ATF test name (test). Use this or testSysId.",
      +  "type": "string"
      +}
    • changedInput schema / properties / testSuiteName / description
      Previous value: -"ATF test suite name (required for action=testsuite)"New value: +"ATF test suite name (testsuite). Use this or testSuiteSysId."
    • addedInput schema / properties / testSuiteSysId
      Added value: +{
      +  "description": "ATF test suite sys_id (testsuite)",
      +  "type": "string"
      +}
    • addedInput schema / properties / testSysId
      Added value: +{
      +  "description": "ATF test sys_id (test)",
      +  "type": "string"
      +}
  2. Addedv4.9.0

TDQS

B3.4/5.0
Behavior3/5

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

The annotations already declare openWorldHint=true, destructiveHint=false, and idempotentHint=false, so the description's main added value is the environment-flag prerequisite, which is genuinely useful. However, it says nothing about the downstream effects of publish (writing to a shared app repository) or rollback (reverting a deployed version), nor that operations run non-idempotently against an external system. For a mutation tool with open-world reach, that side-effect disclosure is missing.

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?

Two sentences, front-loaded with the core purpose and closed with hard prerequisites; no filler. The action enumeration is dense but each item earns its place by signaling a distinct operation. Slightly long single sentence, but structure is sound.

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

Completeness3/5

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

With 13 parameters, 5 actions, and no output schema, the description covers the operation surface and the gating flags but omits what comes back — notably whether async invocations return a job_id and how ATF test results are surfaced, which matters for choosing `async`. It is adequate but leaves the return-shape question entirely unresolved for a fairly complex tool.

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

Parameters3/5

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

Schema description coverage is 100%, and each parameter already documents which actions it applies to (e.g., 'App sys_id (install, publish, rollback)'), so the schema carries the parameter burden. The description's action list roughly mirrors the enum without adding syntax, defaults, or interaction rules (such as how `scope` and `appSysId` resolve against `directory`). Baseline 3 is appropriate here.

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?

The description gives a concrete verb+resource ('Run ServiceNow CI/CD operations via the SDK (`now-sdk cicd`)') and enumerates the four operation families: install, publish, rollback, and ATF test/test-suite runs. That is far more specific than a title restatement. It stops short of 5 because it never positions itself against the closely named sibling `fluent_install`, leaving an agent to guess which one performs app installation.

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

Usage Guidelines3/5

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

Usage context is implied by the enumerated operations (app repository lifecycle and ATF testing) and by the stated prerequisites ('REQUIRES FLUENT_ENABLED=true and WRITE_ENABLED=true'), which tells the agent when the tool is even callable. There is no explicit when-not guidance and no mention of when to prefer `fluent_install`, `fluent_pack`, or `fluent_build` instead, so the routing decision is left to inference.

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