Skip to main content
Glama
nobrainer-tech

langflow-mcp-server

by nobrainer-tech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

run_workflow

Execute a Langflow v2 workflow in sync, stream, or background mode, with optional inputs and tweaks, to automate flow runs and retrieve outputs.

Instructions

Run a Langflow 1.12.x v2 workflow with sync, stream, or background mode.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoOptional live-canvas flow data override
modeNoExecution mode
filesNoPre-uploaded file paths
tweaksNoPer-component parameter overrides
flow_idYesFlow ID
globalsNoRequest-level global variables
output_idsNoOutput component IDs for sync mode
session_idNoOptional session ID
input_valueNoChat-style input value
idempotency_keyNoDeduplication key for background submits
stream_protocolNoStreaming protocol, for example langflow or agui
stop_component_idNoOptional partial-run stop component
expose_graph_stateNoFor streaming runs, include per-node graph events. Omitted or null uses the protocol default: false for AG-UI and true for Langflow. Ignored in sync mode.
start_component_idNoOptional partial-run start component

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changedv4.12.2
    • removedInput schema / properties / background
      Removed value: -{
-  "description": "Run in background",
-  "type": "boolean"
-}
    • addedInput schema / properties / data
      Added value: +{
+  "description": "Optional live-canvas flow data override",
+  "type": [
+    "object",
+    "null"
+  ]
+}
    • addedInput schema / properties / expose_graph_state
      Added value: +{
+  "description": "For streaming runs, include per-node graph events. Omitted or null uses the protocol default: false for AG-UI and true for Langflow. Ignored in sync mode.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}
    • addedInput schema / properties / files
      Added value: +{
+  "description": "Pre-uploaded file paths",
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}
    • changedInput schema / properties / globals / description
      Previous value: -"Request-level global variables (Langflow 1.10.0)"New value: +"Request-level global variables"
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Deduplication key for background submits",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / input_value
      Added value: +{
+  "description": "Chat-style input value",
+  "type": "string"
+}
    • removedInput schema / properties / inputs
      Removed value: -{
-  "description": "Workflow inputs",
-  "type": "object"
-}
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "Execution mode",
+  "enum": [
+    "sync",
+    "stream",
+    "background"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / output_ids
      Added value: +{
+  "description": "Output component IDs for sync mode",
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}
    • addedInput schema / properties / session_id
      Added value: +{
+  "description": "Optional session ID",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / start_component_id
      Added value: +{
+  "description": "Optional partial-run start component",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / stop_component_id
      Added value: +{
+  "description": "Optional partial-run stop component",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • removedInput schema / properties / stream
      Removed value: -{
-  "description": "Stream the run",
-  "type": "boolean"
-}
    • addedInput schema / properties / stream_protocol
      Added value: +{
+  "description": "Streaming protocol, for example langflow or agui",
+  "type": "string"
+}
    • addedInput schema / properties / tweaks
      Added value: +{
+  "description": "Per-component parameter overrides",
+  "type": "object"
+}
  2. First observedv4.11.0

TDQS

C2.6/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden, yet it only names the three modes. It does not explain that background mode returns a job handle while sync blocks, how streaming output is delivered, or how idempotency_key affects duplicate submits — all critical for a 14-parameter execution tool.

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?

A single front-loaded sentence with no filler or repetition. It is efficient, though given the tool's complexity the terseness borders on under-specification rather than true economy.

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

Completeness2/5

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

For a 14-parameter, nested-object, no-output-schema tool with zero annotations, one sentence is insufficient. Nothing is said about return values per mode (result payload vs. stream events vs. background job id), pagination, or how to retrieve async results via get_workflow_result.

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%, so the schema already documents flow_id, tweaks, globals, files, output_ids, and the rest. The description only restates the mode enum values that the schema already enumerates, adding no syntax or interaction detail beyond it.

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

Purpose3/5

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

It states a specific verb and resource ("Run a Langflow 1.12.x v2 workflow") and names the three execution modes, so the basic action is clear. However, it gives no differentiation from the many closely related siblings (run_flow, run_flow_advanced, process_flow, run_flow_session), leaving the agent unable to tell which runner to pick.

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

Usage Guidelines2/5

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

The description lists modes but never says when to choose this tool over run_flow, run_flow_advanced, or process_flow, nor when each mode is appropriate. No prerequisites, no exclusions, no alternatives — usage must be entirely inferred.

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