Compatible with every major AI agent and IDE
What is the Conductor (Netflix OSS) MCP Server?
Connect your Netflix Conductor instance to any AI agent to orchestrate complex microservices and workflows through natural conversation.
What you can do
- Workflow Management — List all registered workflow definitions, fetch specific versions, and manage the lifecycle of your orchestration logic.
- Task Definitions — Query and manage the underlying task types that power your microservices, ensuring your workers are correctly configured.
- Validation & Testing — Validate workflow JSON definitions before saving them to the server to prevent runtime errors.
- Execution Control — Start new workflow instances asynchronously directly from your AI assistant.
- Batch Operations — Update or create multiple workflow and task definitions in a single request for rapid deployment.
How it works
- Subscribe to this server
- Enter your Conductor Server URL (e.g.,
http://conductor-server:8080) - Start managing your distributed systems from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — quickly inspect and update workflow definitions without navigating the Conductor UI
- Backend Developers — validate task configurations and trigger test workflows directly from the IDE
- System Architects — visualize and query the structure of complex distributed processes via natural language
Built-in capabilities (49)
Add a log entry to a task
Bulk pause workflows
Bulk remove workflows
Bulk restart workflows
Bulk resume workflows
Bulk retry workflows
Bulk search workflows by ID
Bulk terminate workflows
Create a new event handler
Create new task definitions
Create a new workflow definition
Delete an event handler
Delete a task definition
Delete a workflow definition
Execute a workflow (Synchronous)
Get pending counts for all queues
Get workflows by correlation ID
Get all event handlers
Get queue depth for a task type
Get running workflow IDs by type
Get a task definition by name
Get all task definitions
Retrieve logs for a task
Get workflow execution by ID
Get a workflow definition by name
Get all workflow definitions
Get all workflow names and versions
Get tasks for a workflow execution
Pause a workflow
Long poll for multiple tasks
Poll for a single task
Remove a workflow from the system
Requeue pending tasks
Rerun a workflow from a specific task
Restart a workflow from the beginning
Resume a paused workflow
Retry the last failed task
Search workflows (returns WorkflowSummary)
Search workflows (returns full Workflow objects)
Skip a task in a running workflow
Start a new workflow execution (Asynchronous)
Terminate a running workflow
Update an existing event handler
Update task result
Update task by reference name
Update a task definition
Update task and poll for the next available task
Create or update workflow definitions (batch)
Validate a workflow definition without saving
Why AutoGen?
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Conductor (Netflix OSS) tools. Connect 49 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
- —
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Conductor (Netflix OSS) tools to solve complex tasks
- —
Role-based architecture lets you assign Conductor (Netflix OSS) tool access to specific agents. a data analyst queries while a reviewer validates
- —
Human-in-the-loop support: agents can pause for human approval before executing sensitive Conductor (Netflix OSS) tool calls
- —
Code execution sandbox: AutoGen agents can write and run code that processes Conductor (Netflix OSS) tool responses in an isolated environment
Conductor (Netflix OSS) in AutoGen
Conductor (Netflix OSS) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Conductor (Netflix OSS) to AutoGen through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Conductor (Netflix OSS) in AutoGen
The Conductor (Netflix OSS) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 49 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in AutoGen only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Conductor (Netflix OSS) for AutoGen
Every tool call from AutoGen to the Conductor (Netflix OSS) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check if my workflow JSON is valid without saving it to the server?
Yes! Use the validate_workflow_definition tool. It allows you to submit a workflow definition JSON for validation, and the server will return any structural or logic errors without persisting the changes.
How do I see all available workflows and their versions?
You can use the get_workflow_names_and_versions tool to get a high-level list of all registered workflows and their associated version numbers.
Is it possible to inspect the configuration of a specific task type?
Yes, use the get_task_definition tool with the specific taskType name. This will return the complete task metadata, including retry logic, timeouts, and input/output keys.
How does AutoGen connect to MCP servers?
Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call Conductor (Netflix OSS) tools during their conversation turns.
Can different agents have different MCP tool access?
Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.
Does AutoGen support human approval for tool calls?
Yes. Configure human-in-the-loop mode so agents pause and request approval before executing sensitive MCP tool calls.
McpWorkbench not found
Install: pip install "autogen-ext[mcp]"
Explore More MCP Servers
View all →
IBGE Full Access — Dados Brasileiros
15 toolsThe ultimate Brazil data Mega-Server: 15 tools spanning census, cities, CNAE economy, name trends, survey indicators, IBGE news, and country comparisons — all of Brazil's official statistics in one zero-auth integration.

SingleStore
6 toolsEquip your AI agent to natively interact with your SingleStore database. Execute raw SQL queries, perform semantic vector searches, list workspaces, and audit billing directly from the terminal.

ShipBob
30 toolsAutomate your e-commerce fulfillment with ShipBob — manage products, track orders, and monitor inventory levels directly from your AI agent.

Stanford Semantic Scholar
16 toolsDiscover academic papers with AI-powered search that understands research context, finds citations, and recommends related work.
