Latenode LogoLatenode

MCP Tools Reference

The Latenode MCP Server exposes 12 tools that AI agents can call to manage scenarios, run executions, and work with connections.

Scenarios

create_scenario

Creates a new scenario with the given name, description, and nodes.

Input

ParameterTypeRequiredDescription
namestringyesScenario name
descriptionstringnoScenario description
nodesarrayyesList of nodes to include (see node object below)

Node object

FieldTypeRequiredDescription
namestringyesNode name (unique within the scenario)
typeAliasstringyesNode type identifier (use search_node_types to find)
parametersobjectyesNode configuration parameters
prevNodesobjectnoMap of upstream node names to route conditions

Output

FieldTypeDescription
scenarioIdstringID of the created scenario

Notes

  • The scenario is always saved with the provided name and description as metadata.
  • MCP automatically assigns a display name to every node in the scenario, even if you do not set one explicitly.

update_scenario

Replaces an existing scenario by ID. All current nodes are replaced with the ones you provide.

Input

ParameterTypeRequiredDescription
idstringyesScenario ID to update
namestringnoNew scenario name
descriptionstringnoNew description
nodesarraynoNew node list (same structure as create_scenario)

Output

FieldTypeDescription
scenarioIdstringID of the updated scenario

Notes

  • Full replacement: the existing node list is discarded and replaced with the one you provide. To make partial changes, first call get_scenario, modify the result, then call update_scenario.
  • MCP automatically assigns display names to all nodes, same as in create_scenario.

get_scenario

Returns the full definition of a scenario by ID.

Input

ParameterTypeRequiredDescription
idstringyesScenario ID (valid ObjectID, e.g. 5f92cbf10cf217478ba93561)
versionnumbernoSpecific version to retrieve. Defaults to latest

Output

FieldTypeDescription
namestringScenario name
descriptionstringScenario description
nodesarrayFull node list with parameters and connections

activate_scenario

Activates or deactivates a scenario.

Input

ParameterTypeRequiredDescription
idstringyesScenario ID
activatebooleanyestrue to activate, false to deactivate

Output

FieldTypeDescription
statusstringactivated or deactivated

Node types and connections

search_node_types

Searches available node types by keyword. Returns up to 20 results per keyword.

Input

ParameterTypeRequiredDescription
querystring[]yesOne keyword per array item. Results must match all keywords
includeOutputSchemabooleannoIf true, returns up to 2 output schema examples per node type. Default: false

Output: array of node type objects.

FieldDescription
aliasNode type identifier to use in typeAlias
nameDisplay name
descriptionWhat the node does
paramsConfigurable parameters with key, title, type, required flag, description, default value, and options
defaultWebhookURLPre-configured webhook URL if applicable

get_dynamic_node_parameters

Returns additional parameters that become available for a node type once initial parameters are set (e.g. a sheet list after a spreadsheet is selected).

Input

ParameterTypeRequiredDescription
nodeTypeAliasstringyesNode type identifier
currentParametersobjectyesCurrent parameter values already set on the node

Output: array of additional parameter descriptors (same structure as params in search_node_types).


search_connections

Searches for the current user's saved connections by type alias.

Input

ParameterTypeRequiredDescription
aliasstring[]yesOne or more connection type aliases to search for

Output

FieldDescription
idConnection ID to use in node parameters
titleConnection display name
typeAliasConnection type
lastModifiedAtLast modification timestamp

create_connection

Creates a new connection. For OAuth-based services, returns a URL the user must open to complete authorization manually.

Input

ParameterTypeRequiredDescription
typeAliasstringyesConnection type alias
titlestringyesDisplay name for the connection
parametersobjectnoConnection parameters (e.g. API keys for non-OAuth connections)

Output

FieldDescription
connectionIdID of the created connection
urlAuthorization URL (returned when the client does not support elicitation)

Executions

run_scenario_once

Runs a scenario once and returns the execution result.

Input

ParameterTypeRequiredDescription
scenarioIdstringyesScenario to run
versionstringnoSpecific version to run. Defaults to latest
asyncbooleannoIf true, returns only executionId without waiting. Default: false

Output

FieldDescription
executionIdExecution ID
resultStatus: new, waiting, success, error, in_process, cancel
errorError message if the execution failed

run_node_once

Runs a single node inside a scenario and returns its output. Useful for testing a specific step without running the full scenario.

Input

ParameterTypeRequiredDescription
scenarioIdstringyesScenario containing the node
nodeNamestringyesName of the node to run
nodesarrayyesFull node list (same structure as create_scenario)
versionnumbernoScenario version. Defaults to latest
asyncbooleannoIf true, returns only executionId. Default: false
overrideParametersobjectnoParameter values to override for this run only
compactOutputbooleannoIf true, returns only the first 100 bytes of output. Default: true

Output

FieldDescription
executionIdExecution ID
resultStatus: new, waiting, success, error, in_process, cancel
outputNode output (truncated if compactOutput is true)
errorError message if the node failed

Notes

  • compactOutput defaults to true and returns only the first 100 bytes. Set it to false when you need the full output.
  • Use overrideParameters to inject test values without modifying the saved scenario.

get_execution

Returns the status and node outputs of an execution by ID.

Input

ParameterTypeRequiredDescription
executionIdstringyesExecution ID to fetch
nodeOutputsByNamestring[]noNode names whose outputs to include in the response

Output

FieldDescription
statussuccess, error, in_process, or cancel
errorError message if the execution failed
executedNodesCountMap of node name to execution count
nodeOutputsMap of node name to output string (for nodes in nodeOutputsByName)

Notes

  • Use this tool to poll the result after calling run_scenario_once or run_node_once with async: true.

get_executions_history

Returns the execution history for a scenario with optional filters.

Input

ParameterTypeRequiredDescription
scenarioIdstringyesScenario ID
limitnumbernoMax executions to return. Default: 10
filters.statusesstring[]noFilter by status: new, waiting, success, error, in_process, cancel
filters.fromstringnoStart datetime (ISO 8601)
filters.tostringnoEnd datetime (ISO 8601)
filters.versionsstring[]noFilter by scenario version
filters.environmentstringnodev or prod

Output

FieldDescription
idExecution ID
statusExecution status
startedAtStart timestamp
durationInSecDuration in seconds
versionScenario version
environmentdev or prod

Need Help? Ask the community

If something on this page is missing or unclear, post on the Latenode community forum. Our team and other users usually reply quickly.

0/100
0/2000