FlowUs MCP. Talk to your knowledge base, not the menus.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
FlowUs connects your AI agent directly to a centralized knowledge base. It lets you manage complex documentation, track product databases, and organize team wikis using only natural conversation.
Instead of clicking through menus and tabs, your agent talks to FlowUs, instantly listing pages, pulling out content blocks, or creating new records in structured tables.
What your AI agents can do
Create database row
Adds a brand new record (row) into one of your structured databases.
Create page
Makes a completely new, blank page within the FlowUs knowledge base.
Get database
Retrieves the structural schema and field names for any connected database.
Gets a list of every page available in your FlowUs workspace.
Pulls out text and media details from sections within a specific page.
Finds records in your databases based on complex rules or criteria.
Adds a brand new row of information to an existing database table.
Creates, reads, or updates entire pages within your knowledge base.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
FlowUs with 10 Tools
These ten tools allow you to fully control every aspect of your knowledge base, from creating new records to querying complex relationships in structured data.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using FlowUs on Vinkius019d843bcreate database row
Adds a brand new record (row) into one of your structured databases.
019d843bcreate page
Makes a completely new, blank page within the FlowUs knowledge base.
019d843bget database
Retrieves the structural schema and field names for any connected database.
019d843bget page
Pulls all details about a specific, existing page.
019d843blist blocks
Reads the individual content blocks (text or media) inside a designated page.
019d843blist databases
Provides an inventory of every database available in your FlowUs workspace.
019d843blist pages
Generates a list of all pages currently held by the workspace.
019d843blist users
Returns a directory listing of people who have access to the workspace.
019d843bquery database
Runs complex queries across your databases, returning only the data you need.
019d843bupdate page
Modifies content and metadata on an already existing page.
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 FlowUs, then connect any of our 4,900+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,900+ 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FlowUs. 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 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The Wiki Nightmare: Finding Information Across Silos
Today, finding one piece of information means clicking through a maze of menus: the main wiki page, then drilling down to the correct database tab, filtering by date, and maybe opening an external spreadsheet link. You end up spending more time navigating than actually reading.
With this MCP, your agent handles all that complexity. You just ask, 'What are the core requirements for the new widget?' It talks to FlowUs, gathers data from multiple sources—pages, databases, blocks—and gives you a single, conversational answer.
Managing Knowledge with FlowUs MCP
You eliminate the need to manually check if documentation is up-to-date. Instead of opening the page, checking for outdated sections, and then updating them, you simply tell your agent: 'Refresh the Product Roadmap section on Page X with these new findings.'
Your workflow stops requiring manual UI interaction. You talk to FlowUs via your AI client—it's done.
What you can do with this MCP connector
Think of it like having an entire company wiki—all the documents, project roadmaps, and databases—but instead of logging into a dozen different tools, you just talk to your AI client. This MCP turns that complex web interface into a conversation. You can ask your agent things like, 'What are all the pages related to Q3 planning?' or 'Give me a list of high-priority features from the Product Backlog.' Your agent handles the deep dive: it reads the page structure, pulls specific content blocks out of documents, and even executes queries across multi-dimensional databases.
You don't touch the manual controls; your agent uses this MCP through Vinkius to keep everything organized and instantly accessible.
019d843c-00f7-7053-84bd-15d0afc9fa9a 
How FlowUs MCP Works
- 1 Subscribe to this MCP and enter your FlowUs API Token.
- 2 Connect the token to your preferred AI client (like Cursor or Claude).
- 3 Ask your agent a question in plain language, like 'List all pages related to marketing' to execute actions.
The bottom line is: you talk to your agent, and it uses this MCP to run commands across your entire knowledge base.
Who Is FlowUs MCP For?
Knowledge workers who spend too much time hunting for specific documents or cross-referencing data points across multiple internal tools. It’s for anyone whose job requires synthesizing information from a large, disorganized wiki.
Needs to track feature requirements and manage roadmaps by querying the 'Product Backlog' database or updating pages with status changes.
Uses this MCP to list all accessible pages, retrieve specific content blocks, and update documentation drafts in a single chat session.
Needs to manage shared operational databases by running complex queries or adding new user records without touching the manual UI.
What Changes When You Connect
- Stop manually listing pages. You can use
list_pagesto get an immediate inventory of your entire documentation site just by asking your agent. - Don't copy-paste data from complex tables. The MCP lets you run a query using
query_databaseand gets the results formatted for instant reading. - Need to update a document? Use
update_pagedirectly through chat, rather than navigating into the page editor and manually saving changes. - Building records is simple. Instead of filling out forms, just tell your agent what you need and let it run
create_database_rowfor you. - When collaborating, use the MCP's ability to list users (
list_users) so you always know who has access to which sections.
Real-World Use Cases
The quarterly audit of team documentation
A project manager needs to see if all departments have filled out their Q4 planning pages. Instead of manually checking 20 different folders, they ask their agent to list_pages and then check the metadata for completeness.
Identifying high-priority product bugs
A QA tester needs to know which features are flagged as 'Critical' in the product backlog. They tell their agent to run a query using query_database on the relevant table, getting a filtered list immediately.
Onboarding new team members
A new hire needs an overview of who works on what and what documentation exists. They ask their agent to combine results from list_pages and list_users for a comprehensive introduction.
The Tradeoffs
Trying to update data piece by piece
Opening the page, finding the section, copying the text into another document, pasting it back, and manually hitting 'Save' in the web UI.
→
Use your agent to run update_page. You just tell it: 'Update the Project Charter on Page X with this new paragraph.' It handles the saving process for you.
Manually searching through databases
Opening a database, scrolling through rows one by one, and filtering manually to find records that match complex criteria (e.g., Status='Pending' AND Priority='High').
→
Use query_database. Just ask your agent: 'Show me all pending items with high priority in the Product Backlog database.' The tool handles the complex filtering.
Forgetting what pages exist
Assuming a document is saved somewhere, but forgetting which of the 50+ internal wiki sections it was placed in.
→
Run list_pages first. This gives you an immediate inventory so you can ask your agent to retrieve the content from that specific page.
When It Fits, When It Doesn't
Use this MCP if your workflow requires connecting natural conversation directly to structured knowledge bases and complex, multi-part documentation (combining pages with relational data). It's ideal for analysts or PMs who constantly cross-reference information. Don't use it if you only need simple text generation or basic messaging; those tasks are better suited for dedicated communication tools. If your goal is simply to write a page from scratch, stick to the native editor. This MCP excels at reading, querying, and updating structured content.
Common Questions About FlowUs MCP
How do I find out what databases are available using the `list_databases` tool? +
You ask your agent to run the list_databases tool. It returns a list of all database names, letting you know exactly which structured data sets FlowUs can talk to.
Can I update pages using the `update_page` tool? +
Yes. You tell your agent what page ID to target and what new content or metadata should go there. It executes the change, keeping your documentation current in one step.
What is the difference between `get_database` and `list_databases`? +
list_databases gives you a name list of all databases. get_database, however, shows the actual structure—the columns and field names—for one specific database.
How does `query_database` work with my data? +
query_database lets you write natural language requests that are turned into structured queries. You don't need SQL; just ask your agent for the data, and it handles the rest.
What should I use if I need to retrieve all metadata for a specific page, like with the `get_page` tool? +
It pulls all content details and structural data associated with one unique page ID. Use this immediately after creating or finding a page; it's the fastest way to confirm the current state of that document.
When should I use `list_blocks` instead of calling `get_page`? +
You must call list_blocks when you only need a list of content blocks and their types, without retrieving the full text or media data for everything. This is much faster for structural checks.
What happens if I run `create_database_row` but forget to provide all necessary columns? +
The system will return an error detailing which required column names are missing or formatted incorrectly. Always check the database schema first using the get_database tool.
How does the `list_users` tool help me manage team access and coordination? +
It lists every user currently associated with your FlowUs workspace. You use this to verify who has participation rights or to identify potential collaborators for a project.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.