---
title: "AWS Labs Step Functions Tools: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/awslabs-stepfunctions-tool/
description: "Exposes selected existing Step Functions state machines as executable MCP tools, with Standard polling and synchronous Express execution."
---

# AWS Labs Step Functions Tools: review, setup & limitations · Undominated.ai

> Exposes selected existing Step Functions state machines as executable MCP tools, with Standard polling and synchronous Express execution.

[← Explore all mcp servers](/mcp-servers/)

AWS DATA SERVICES / AWS Labs

# AWS Labs Step Functions Tools

Exposes selected existing Step Functions state machines as executable MCP tools, with Standard polling and synchronous Express execution.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/awslabs/mcp)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 5 linked sources
 Publisher AWS Labs
 Licence [Apache-2.0 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE)
 Revision 8840003820a7
 [Read what was—and wasn’t—checked ↓](#review)

“A Model Context Protocol (MCP) server for AWS Step Functions to select and run state machines as MCP tools without code changes.”

 [AWS Labs · upstream description ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Specialized publisher integration with documented IAM and data access boundaries.
- Invoke a reviewed workflow that already implements a constrained business operation.
- The README turns existing Step Functions state machines into MCP tools without editing their definitions.
- The model is limited to invoking those state machines. Other AWS calls stay inside the state machine's own role.

### A good fit for

 - Invoke a reviewed workflow that already implements a constrained business operation.
- Reuse existing state-machine descriptions and optional EventBridge schemas as tool context.
- Starting a known Standard or Express state machine from an assistant
- Restricting which machines appear by prefix, explicit list, or a complete tag pair

### Weigh up before choosing

 - If both STATE_MACHINE_LIST and STATE_MACHINE_PREFIX are empty, name selection accepts all discovered state machines. The starter supplies an explicit list; name selectors combine by OR before optional tags.
- Standard execution polls until completion without a bounded retry count in the inspected loop. A client timeout does not prove that the state machine stopped, and retrying can duplicate effects.
- Workflow actions use the state machine execution role and can write to other services even when the invoking credential only has Step Functions permissions.
- The monorepo now recommends Agent Toolkit for AWS for production. This specialized local server remains documented; its leaf and root documentation were checked for deprecation.
- An empty prefix and an empty list select every state machine that passes the name check.
- Setting only one of the tag key or tag value selects nothing.
- The MCP client does not receive direct access to the AWS services the state machine calls.
- A pin does not verify transitive dependencies. Documented uvx examples use a floating package tag, not the reviewed commit.
- This review did not execute the resource.
- The server was not started and its tools were not called.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - src/stepfunctions-tool-mcp-server/README.md
- src/stepfunctions-tool-mcp-server/pyproject.toml
- src/stepfunctions-tool-mcp-server/awslabs/stepfunctions_tool_mcp_server/server.py
- Root README.md and LICENSE
- LICENSE

### Our findings

 - Pinned implementation has an unbounded Standard completion polling loop and separate Express synchronous handling. Input schema references supplement documentation, not downstream authorization.
- The server exposes Standard and Express state machines as tools and can validate inputs with EventBridge Schema Registry. Definitions do not have to be edited.
- IAM on the MCP side is for invoking state machines. The README says models do not get direct access to other AWS services. Those calls use the state machine role. The default profile and region are default and us-east-1.
- With no prefix and no list, every state machine passes the name check. A tag filter with only the key or only the value selects no state machine.

### Not established by this review

 - Server startup, authentication, live tool execution and security isolation were not tested.
- Published package/container parity with a source revision and hosted implementation internals were not tested.
- The server was not started and its tools were not called.
- A pin does not verify transitive dependencies.
- No tools/list or tool call was made.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/README.md)

DOCUMENTED COMMAND

 uvx awslabs.stepfunctions-tool-mcp-server@latest Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Create and review the workflow separately, including execution-role permissions and failure/retry semantics.
- Set explicit state-machine selection and grant needed list/describe/start permissions for the intended region.
- Inspect the generated tool description/schema, then approve real execution; preserve the execution ARN for status reconciliation.

### Before you start

 - Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process.
- An AWS account, configured credentials and access to the intended region and service resources.

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "awslabs-stepfunctions-tool": {
 "command": "uvx",
 "args": [
 "awslabs.stepfunctions-tool-mcp-server@latest"
 ],
 "env": {
 "AWS_PROFILE": "YOUR_RESTRICTED_PROFILE",
 "AWS_REGION": "us-east-1",
 "STATE_MACHINE_LIST": "YOUR_REVIEWED_STATE_MACHINE"
 }
 }
 }
} Copy configuration ↗

### Compatibility

Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process. · An AWS account, configured credentials and access to the intended region and service resources.

### Implementation

Python

### Transports

stdio

### AWS data services

 - Calls StartExecution/DescribeExecution for Standard and StartSyncExecution for Express workflows; invokes actual workflow effects.

### Cost model

AWS service, model, query and storage charges apply; running the MCP process does not include those services.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Publisher setup, capabilities and operating boundaries ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports, license
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/pyproject.toml) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/pyproject.toml Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports, license
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/awslabs/stepfunctions_tool_mcp_server/server.py) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/stepfunctions-tool-mcp-server/awslabs/stepfunctions_tool_mcp_server/server.py Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports, license
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports, license
- [Applicable licence ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### AWS Keyspaces MCP ↗ Inspect Cassandra-compatible schemas and run SELECT queries with dedicated database credentials.](/mcp-servers/awslabs-keyspaces/)[### AWS Labs Amazon Kendra Index ↗ Queries an existing Kendra index and returns document excerpts, source URIs and confidence labels for retrieval workflows.](/mcp-servers/awslabs-kendra-index/)[### AWS Labs Amazon MQ ↗ Inspects and manages Amazon MQ brokers, with additional RabbitMQ management operations.](/mcp-servers/awslabs-amazon-mq/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
