Flowise MCP. Control, debug, and audit your low-code AI flows.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Flowise. Manage and audit low-code AI workflows through a single MCP connection. This server lets your AI client list, test, and track every component of your generative AI application, from complex agent logic to simple chat predictions.
You can run live predictions, examine execution history for debugging, and inventory all connected tools and credentials without leaving your development environment.
What your AI agents can do
Get chatflow
Retrieves the specific architectural details (nodes and edges) for a named chatflow.
Get history
Pulls the detailed conversational and execution log for a given chatflow.
List agentflows
Returns a list of all complex, multi-step agentflows defined in the instance.
Retrieve a list of all deployed chatflows and get the detailed architectural blueprint (nodes and edges) for a specific flow.
Send a user question to a specific chatflow and receive the AI's generated response immediately, simulating a real-time user interaction.
Pull detailed execution traces and conversational logs for a chatflow to debug past interactions and monitor performance.
Access and list complex agentflows, allowing your agent to understand multi-step reasoning logic.
List all custom tools and stored API credentials used by your Flowise instance to verify available integrations and authentication settings.
Verify the operational status of the Flowise instance and available base endpoints.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Flowise MCP Server: 7 Tools for Workflow Management
Use these tools to list, inspect, run predictions, and audit every component of your low-code AI application stack.
019d759cget chatflow
Retrieves the specific architectural details (nodes and edges) for a named chatflow.
019d759cget history
Pulls the detailed conversational and execution log for a given chatflow.
019d759clist agentflows
Returns a list of all complex, multi-step agentflows defined in the instance.
019d759clist chatflows
Lists all currently deployed chatflows available in the Flowise environment.
019d759clist credentials
Shows a list of all API keys and credentials stored for the AI logic chains.
019d759clist tools
Returns a list of all custom third-party tools integrated into the Flowise setup.
019d759cpredict
Runs a live prediction by submitting a question to a specific chatflow to get an immediate AI response.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Flowise, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're trying to build an AI app with Flowise? This server lets your agent poke around your whole setup. You'll get direct access to the backend tools, so you can manage and audit everything without leaving your development environment.
To check what's going on, your agent can use list_chatflows to see a list of every chatflow you've deployed. When you need to see the specific structure of one, get_chatflow pulls the detailed architectural blueprint, showing all the nodes and edges. You can run live tests by sending a question to a specific flow with predict, getting an immediate AI response that mimics a real user interaction.
If you need to debug what happened last time, get_history pulls the detailed conversational and execution log for a given chatflow. To handle complex, multi-step reasoning, your agent can list all complex agentflows using list_agentflows. You can also check what third-party integrations you've wired up with list_tools, and verify all the stored API keys and credentials with list_credentials.
Finally, get_history also pulls the detailed conversational and execution log for a given chatflow.
How Flowise MCP Works
- 1 Subscribe to the Flowise server and provide your Base URL and API Key.
- 2 Your AI client sends a command (e.g., 'List all chatflows').
- 3 The server executes the tool and returns structured data (e.g., a list of flow names or an execution log) directly to your client.
The bottom line is, you manage your entire low-code AI application stack from a single conversation interface.
Who Is Flowise MCP For?
This is for the AI developer who needs to test and debug complex flows without leaving their main workspace. It’s for the automation engineer who needs to monitor live execution history. If you build AI applications using visual, node-based logic, this server is required.
Tests and debugs Chatflows and Agentflows directly, checking nodes and edges without switching to the Flowise UI.
Triggers live AI predictions and reviews execution histories using natural language commands.
Audits available AI tools and verifies conversational logs to ensure the AI logic meets product requirements.
What Changes When You Connect
- Live Testing: Use
predictto send a user query to a chatflow and instantly see the AI's generated response. You test the conversation flow without needing to manually copy inputs. - Full Debugging:
get_historypulls the exact execution trace and conversational log. This lets you pinpoint where a complex agent flow failed, far better than just seeing the final error message. - Architecture Mapping:
get_chatflowlets you pull the detailed node and edge structure for any chatflow. You see the entire logic graph, which is crucial for understanding complex data routing. - Security Audit:
list_credentialsenumerates every stored credential component. You verify which API keys the AI logic uses for authentication, keeping your stack secure. - Tool Inventory:
list_toolsreturns a list of every custom tool and third-party integration available. You know exactly what capabilities the AI agent can call when it needs to. - Workflow Oversight:
list_agentflowsandlist_chatflowslet you list and manage all your deployed workflows, giving you a single view of your entire AI application inventory.
Real-World Use Cases
Debugging a broken customer bot
A customer service bot suddenly starts giving wrong answers. Instead of guessing, you ask your agent to use get_history for the 'Support Bot' chatflow. The logs immediately show the bot skipped the 'Context Retrieval' node, revealing a logic error in the flow's architecture.
Validating a new feature integration
You just built a new knowledge base chatflow. Before going live, you use predict to run ten different test questions against it. This ensures the chatflow handles edge cases and complex queries correctly in real-time, confirming its readiness.
Checking agent dependencies
Your agent is supposed to run a multi-step legal review. You ask the agent to use list_agentflows to confirm the steps. This confirms the entire reasoning sequence is active and ready before running the full task.
Verifying API access
You need to confirm if your AI agent can access external payment data. You use list_tools to check for a 'Payment Gateway' tool and list_credentials to ensure the required API key is present and active.
The Tradeoffs
Relying on manual UI exploration
A developer has to navigate through the Flowise UI, click on 'History', select the flow, and then copy the relevant execution log to send to a teammate. This takes minutes and breaks focus.
→
Just ask your agent to 'Show me the execution history for the Legal Assistant chatflow.' The agent calls get_history, pulls the log, and presents it to you instantly in your chat client.
Assuming all tools are active
The agent fails a multi-step task and the developer doesn't know if the failure was due to a bad flow or missing API keys. They waste time checking documentation.
→
First, run list_tools to see what capabilities are available. Then, use list_credentials to verify the required keys are configured. This narrows the problem down to the logic, not the setup.
Testing logic without real context
A developer tests a flow by asking a simple question, but the failure only happens when a large document is provided as context. The simple test gives a false sense of security.
→
Use predict and manually feed it the complex context data. This simulates the real-world scenario and guarantees the chatflow handles large inputs correctly.
When It Fits, When It Doesn't
Use this server if your primary workflow challenge is debugging, auditing, or inspecting the internal mechanics of your generative AI application. You need to know why the AI said what it did. If you only need to build a simple chat bot that asks one question and gets one answer, you might not need all the tools. But if your app relies on multi-step reasoning, external APIs, or complex data routing, this MCP server gives you the deep visibility you need. Don't use this if you just need to list files; use a basic file system tool instead. Use this if you need to understand the full lifecycle of the AI interaction, from the initial prompt to the final tool call, because it gives you the complete picture via get_history and get_chatflow.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Flowise. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually tracing AI logic is a nightmare.
When an AI flow breaks, developers waste hours jumping between the Flowise UI, the API docs, and the terminal. You have to manually check the flow graph, figure out which node failed, and then copy-paste the entire conversation log to a bug tracker. It's slow and error-prone.
With the Flowise MCP Server, you just ask your agent to 'Show the history for the Legal Assistant'. It calls `get_history`, pulls the complete, structured execution trace, and presents it instantly in your chat. The debugging time drops from hours to seconds.
Flowise MCP Server: Audit every single AI step.
You don't have to click through the chatflow nodes, the agent steps, and the credential settings. Your agent can call `list_chatflows` to see every deployed flow, and then `get_chatflow` to pull the full architectural blueprint in a single command.
Your AI client becomes your control panel. It gives you full, programmatic visibility into the internal workings of your entire low-code AI application, no UI required.
Common Questions About Flowise MCP
How do I use the `predict` tool with complex context? +
The predict tool requires you to pass the chatflow name and the user question, along with any necessary context data. Your agent handles the formatting, sending the full payload to the chatflow backend for a real-time response.
Can I see the steps in my agentflow using `list_agentflows`? +
Yes, list_agentflows returns a list of all complex agentflows. You then use get_chatflow or similar tools to access the detailed definition and logic of the flow.
What information does `get_history` provide? +
It provides the full execution trace, including all inputs, outputs, and intermediate steps taken by the AI, allowing you to track exactly where the logic deviated.
Do I need to use `list_tools` before calling `predict`? +
No. list_tools simply shows what integrations exist. To run a prediction, you only need the target chatflow name and the input question.
Does the Flowise MCP Server handle authentication? +
The server relies on your API Key and Base URL. You can use list_credentials to verify that the necessary authentication components are stored and accessible to your agent.
How do I check what credentials are stored using `list_credentials`? +
It lists all stored credential components. This includes API keys or tokens necessary for your AI logic chains to authenticate securely.
What does `get_chatflow` return about a specific chatflow? +
It provides detailed architectural nodes and edges. You can see the full structure, allowing you to understand how the conversation logic is built.
How can I check if the server is running using `get_history`? +
While get_history retrieves past runs, you should use list_chatflows or list_agentflows to confirm the overall system status. Always check the system health endpoint first.
Can my agent run a prediction against a specific Flowise chatflow? +
Yes. Use the 'predict' tool. Provide the 'chatflow_id' and your question. The agent will command the Flowise backend to process the logic chain and return the AI-generated response directly in your chat.
How do I see the past conversational logs for a chatflow via chat? +
Use the 'get_history' tool with the 'chatflow_id'. Your agent will retrieve the past execution traces and logs, helping you understand how users have interacted with that specific logic chain natively.
Can I list all custom tools configured in my Flowise instance through the agent? +
Absolutely. Use the 'list_tools' tool. Your agent will retrieve custom tools and integrations configured in your environment, allowing you to audit available capabilities through natural conversation.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Adobe Firefly
Generate images and vectors via Adobe Firefly — perform generative fill and expand, create text effects, and remove backgrounds directly from any AI agent.
Chroma (Vector DB)
Manage vector embeddings via Chroma — list collections, query embeddings, and audit document counts directly from any AI agent.
DataRobot
Manage AutoML via DataRobot — monitor projects and models, track deployments, and audit ML datasets directly from any AI agent.
You might also like
Wikidata
Access the world's largest open knowledge graph—query entities via SPARQL, perform vector searches, and manage structured data directly from your AI agent.
Cedar AI
Process insurance documents with AI that extracts claims data, validates coverage, and accelerates underwriting decisions.
DecileHub
Segment your customers by value and behavior with predictive analytics that reveal your most profitable audience segments.