Skip to main content
Glama
mfa-servicenow-mcp

mfa-servicenow-mcp

by jshsakura

manage_flow_designer

Read and analyze ServiceNow Flow Designer structures, conditions, executions, and action sources; compare instances and inspect step details before editing via Workflow Studio.

Instructions

Flow Designer read/analyse: structure, conditions, executions, cross-instance compare, action source. No write API: build/edit by driving Workflow Studio with act_in_debug_window yourself, then verify with get_detail.

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": "manage_flow_designer"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNoAdditional encoded query
scopeNoScope namespace
actionYesWhat to read
offsetNo
flow_idNoFlow sys_id; get_detail also accepts flow_name instead
node_idNoAction/logic/trigger instance id; on get_detail reads that ONE step in full
flow_nameNoFlow name: get_detail exact/contains lookup, or executions filter
flow_typeNoflow (default) | subflow | all | action | playbook | decision
action_refNoAction sys_id/name; discover via action=list with flow_type=action
context_idNoExecution sys_id (sys_flow_context)
count_onlyNo
exec_stateNoComplete/Error/Waiting/Cancelled/In Progress
trace_pillNoTrace data pill through flow
errors_onlyNo
flow_statusNoStatus: Draft/Published/etc
name_filterNoName contains-match
repeat_fullNoget_detail: return the full answer even if identical to your last call
source_tableNoTable to resolve a source_record number in (default task)
source_recordNoTriggering record: sys_id, or its number (see source_table)
summary_formatNoCompact format; False = raw JSON
include_inactiveNo
include_triggersNo
include_versionsNo
include_structureNo
include_subflow_treeNo
include_executions_summaryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.25.43
    • addedInput schema / properties / repeat_full
      Added value: +{
      +  "description": "get_detail: return the full answer even if identical to your last call",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changedv1.25.8
    • addedInput schema / properties / query / description
      Added value: +"Additional encoded query"
  3. Changed2 schema fields changedv1.25.4
    • changedInput schema / properties / source_record / description
      Previous value: -"Source record display value"New value: +"Triggering record: sys_id, or its number (see source_table)"
    • addedInput schema / properties / source_table
      Added value: +{
      +  "description": "Table to resolve a source_record number in (default task)",
      +  "type": "string"
      +}
  4. Changed4 schema fields changedv1.24.83
    • changedInput schema / properties / action / description
      Previous value: -"Read-only: list/get_detail/get_executions/compare/get_action_source/read_action. Edit flows in the Flow Designer UI."New value: +"What to read"
    • removedInput schema / properties / confirm
      Removed value: -{
      -  "enum": [
      -    "approve"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / confirm_publish
      Removed value: -{
      -  "enum": [
      -    "approve"
      -  ],
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "action",
      -  "confirm"
      -]New value: +[
      +  "action"
      +]
  5. Changed1 schema field changedv1.24.67
    • changedInput schema / properties / action / description
      Previous value: -"Writes (checkout/set_*/add_branch/save/publish/activate/deactivate/copy/update) need browser auth; rest are reads."New value: +"Read-only: list/get_detail/get_executions/compare/get_action_source/read_action. Edit flows in the Flow Designer UI."
  6. Changed1 schema field changedv1.24.61
    • addedInput schema / properties / node_id
      Added value: +{
      +  "description": "Action/logic/trigger instance id; on get_detail reads that ONE step in full",
      +  "type": "string"
      +}
  7. Changed1 schema field changedv1.23.8
    • addedInput schema / properties / confirm_publish
      Added value: +{
      +  "enum": [
      +    "approve"
      +  ],
      +  "type": "string"
      +}
  8. Addedv1.21.20
  9. Removedv1.21.13
  10. First observedv1.18.41

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries full disclosure burden, and it does clearly state the tool is read-only with no write API and that get_detail is used for verification. However it says nothing about result shape, pagination defaults, or the dedupe behavior implied by repeat_full, and 'cross-instance compare' has no corresponding action in the enum, which muddies what the tool actually does.

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 dense sentences with the purpose front-loaded and the write limitation immediately after; nothing is padded. The compression is near the edge of cryptic, and the unexplained 'cross-instance compare' claim costs it a point.

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 27-parameter, four-action read tool with no output schema, the description establishes scope, read-only safety, and the verification workflow an agent needs. The main gap is that the advertised 'cross-instance compare' capability is not reachable via any listed action, which could mislead an agent about the tool's surface.

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 coverage is 63% across 27 parameters, so many parameters (flow_id, node_id, trace_pill, action_ref, context_id) are already documented in the schema. The description adds little parameter meaning beyond reinforcing 'get_detail' as the verification call. Baseline 3 is appropriate given the moderate coverage and absence of added syntax detail.

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?

Names the resource (Flow Designer) and the concrete read operations it covers: structure, conditions, executions, cross-instance compare, action source. The 'No write API' statement immediately distinguishes it from build/edit workflows, so an agent can tell it is the inspection tool. It stops short of naming a sibling, but the verb+resource are specific.

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?

Explicitly says what this tool cannot do (writing) and routes the agent to an alternative path: drive Workflow Studio with act_in_debug_window, then verify with get_detail. That is real when-not guidance with a follow-up step. It leaves selection among the four action modes to the schema enum rather than explaining the decision here.

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