AI ListTools

AI ListTools

Certified

List the tools exposed by an MCP server

Connects to a Model Context Protocol (MCP) server and returns its tool catalogue — name, description and argument JSON schema for each tool. Use io.kestra.plugin.ai.mcp.CallTool to invoke one of them.

yaml
type: io.kestra.plugin.ai.mcp.ListTools

Discover the tools available on an MCP server over Streamable HTTP.

yaml
id: mcp_list_tools
namespace: company.ai

tasks:
  - id: list
    type: io.kestra.plugin.ai.mcp.ListTools
    url: https://mcp.example.com/mcp
Properties

URL of the MCP server

Streamable HTTP or SSE endpoint of the MCP server, matching the chosen transport. No default: this property is required.

Assets this task consumes as inputs or produces as outputs, for lineage tracking and the asset graph (Enterprise Edition). A flow declaring this property on a task is rejected in the open-source edition.

Definitions
assetFailureBehaviorstring
Possible Values
IGNOREFAILWARN

Asset failure behavior

Behavior applied to the task state when a declared asset fails to render, emit, or be persisted (e.g. a lock conflict): FAIL escalates it to FAILED, WARN (default) warns it if it would otherwise succeed, IGNORE leaves the state untouched.

enableAutobooleanstring

Whether to auto-register assets referenced dynamically at runtime that are not statically declared in inputs or outputs.

inputsarray

The assets consumed as inputs.

id*string
Min length1
typestring
outputs

The assets produced as outputs.

id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*string
Min length1

Custom asset type

descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150

Custom headers

Extra HTTP headers sent with every request, typically to carry an authentication token via the Authorization header. Not set by default.

Defaultfalse

Log requests

If true, requests sent to the MCP server are logged at INFO level. Defaults to false.

Defaultfalse

Log responses

If true, responses received from the MCP server are logged at INFO level. Defaults to false.

Connection timeout duration

Maximum time to wait for a response from the MCP server. Not set by default, in which case the underlying MCP client's own default applies and this task enforces no timeout.

DefaultSTREAMABLE_HTTP
Possible Values
STREAMABLE_HTTPSSEUNKNOWN

Transport

Protocol used to reach the MCP server: STREAMABLE_HTTP or SSE. Defaults to STREAMABLE_HTTP.

Tool count

Number of tools returned by the server.

Tools

Tools the MCP server exposes, each with its name, description and input schema.

Definitions
descriptionstring

Tool description

Natural-language summary the server publishes for this tool, which an LLM uses to decide when to call it.

namestring

Tool name

Name the tool is invoked by, to pass as tool on an io.kestra.plugin.ai.mcp.CallTool task.

parametersobject

Tool argument JSON schema

JSON Schema describing the arguments the tool accepts, which CallTool arguments must conform to.

More Plugins in this Category

Azure
Azure

Leverage Microsoft Azure services within Kestra data workflows.

AICloudDataInfrastructure

82 tasks

19 blueprints

TypeSafe
TypeSafe

Evaluate content with TypeSafe AI's System One models.

AIData

2 tasks

1 blueprints