temporal-mcp
Provides tools for listing, describing, and fetching the event history of Temporal workflow executions, enabling LLM-assisted debugging of Temporal workflows.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@temporal-mcplist workflows with status Running"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Temporal MCP Server
An MCP (Model Context Protocol) server for debugging Temporal workflows. This server enables LLM-assisted debugging by exposing Temporal workflow inspection tools.
Features
list_workflows - List workflow executions with optional query filter
describe_workflow - Get detailed info about a specific workflow
get_workflow_history - Fetch event history for debugging
Related MCP server: pernosco-mcp
Requirements
Python 3.11+
uv for dependency management
A running Temporal server (local or cloud)
Installation
# Clone the repository
git clone <repo-url>
cd temporal-mcp
# Create virtual environment and install
uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"Configuration
Set environment variables to configure the Temporal connection:
Variable | Description | Default |
| Temporal server address |
|
| Temporal namespace |
|
| Path to TLS certificate (for Cloud) | - |
| Path to TLS key (for Cloud) | - |
| API key (for Cloud) | - |
Docker
Connect to Temporal Server
If you have Temporal running (locally or remotely):
# Connect to Temporal on host machine
docker compose up
# Or specify a custom address
TEMPORAL_ADDRESS=my-temporal:7233 docker compose upConnect to Temporal Cloud
For Temporal Cloud with mTLS certificates:
# Place your certificates in a certs/ directory, then:
docker compose up
# After uncommenting the TLS environment variables in docker-compose.ymlOr with API key:
TEMPORAL_ADDRESS=your-ns.tmprl.cloud:7233 \
TEMPORAL_NAMESPACE=your-ns \
TEMPORAL_API_KEY=your-key \
docker compose upLocal Development (without Docker)
Install and run directly with Python:
For Temporal Cloud, set the appropriate environment variables:
export TEMPORAL_ADDRESS="your-namespace.tmprl.cloud:7233"
export TEMPORAL_NAMESPACE="your-namespace"
export TEMPORAL_API_KEY="your-api-key"Or with TLS certificates:
export TEMPORAL_ADDRESS="your-namespace.tmprl.cloud:7233"
export TEMPORAL_NAMESPACE="your-namespace"
export TEMPORAL_TLS_CERT="/path/to/cert.pem"
export TEMPORAL_TLS_KEY="/path/to/key.pem"Usage
With Cursor
Add to your Cursor MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"temporal": {
"command": "uv",
"args": ["run", "temporal-mcp"],
"cwd": "/path/to/temporal-mcp",
"env": {
"TEMPORAL_ADDRESS": "localhost:7233",
"TEMPORAL_NAMESPACE": "default"
}
}
}
}Standalone
temporal-mcpAvailable Tools
list_workflows
List workflow executions with optional filtering.
list_workflows(query="", limit=10)query: Optional Temporal list filter syntax (e.g.,WorkflowType="MyWorkflow" AND ExecutionStatus="Running")limit: Maximum workflows to return (default 10, max 100)
describe_workflow
Get detailed information about a specific workflow.
describe_workflow(workflow_id, run_id="")workflow_id: The workflow ID to describerun_id: Optional run ID (uses latest if not specified)
get_workflow_history
Fetch the event history for a workflow execution.
get_workflow_history(workflow_id, run_id="", max_events=100)workflow_id: The workflow IDrun_id: Optional run ID (uses latest if not specified)max_events: Maximum events to return (default 100, max 1000)
Development
Setup
uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"Commands
# Format code
black src tests
# Lint
ruff check src tests
# Type check
mypy src
# Run tests
pytest
# Run all checks
black src tests && ruff check src tests && mypy src && pytestProject Structure
temporal-mcp/
├── pyproject.toml # Project config and dependencies
├── Dockerfile
├── docker-compose.yml # Docker setup for MCP server
├── README.md
├── src/temporal_mcp/
│ ├── __init__.py
│ ├── server.py # MCP server and tool definitions
│ ├── client.py # Temporal client wrapper
│ ├── config.py # Environment-based configuration
│ └── models.py # Pydantic models
├── tests/
│ ├── conftest.py # Test fixtures
│ ├── test_config.py
│ ├── test_client.py
│ └── test_server.py
└── docs/
└── PLAN.txtLicense
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kk-kd/temporal-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server