Mode MCP. Audit Sources, Find Reports, and Manage Your BI Stack via Chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Mode (Collaborative Data Platform) lets your AI client manage all your enterprise BI assets—reports, spaces, and data sources—via natural conversation.
You can audit database connections, list all reports generated in a workspace, or search for specific data insights without clicking through dashboards.
It gives you full control over the Mode analytics environment.
What your AI agents can do
Get report
Retrieves specific analytical parameters for a single reported token in the workspace.
Get space
Gets all parameters associated with an explicitly targeted organizational 'Space'.
List data sources
Lists every database and warehouse connector source connected to the Mode account.
List every database and warehouse connector source bound to the Mode account via list_data_sources.
Run workspace-wide searches against report metadata using search_reports or get an inventory of all reports with list_reports.
List available analytical 'Spaces' and retrieve the exact parameters for a targeted space using get_space.
Retrieve precise configuration details, like chart definitions and query states, for one specific report token via get_report.
List all tracked analytical users in the workspace using list_members to verify who owns what data.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Mode (Collaborative Data Platform): 7 Tools for Data Management
These tools let your agent interact with Mode's backend to list sources, search reports, define scope boundaries, and audit user access.
019d75d6get report
Retrieves specific analytical parameters for a single reported token in the workspace.
019d75d6get space
Gets all parameters associated with an explicitly targeted organizational 'Space'.
019d75d6list data sources
Lists every database and warehouse connector source connected to the Mode account.
019d75d6list members
Lists all analytical users who are statically tracked within the workspace for ownership checks.
019d75d6list reports
Provides a full inventory list of static data reports generated by the Mode workspace.
019d75d6list spaces
Lists all accessible 'Spaces' that isolate datasets across the entire Mode workspace.
019d75d6search reports
Executes a search for reports by running queries against the Mode API using metadata or keywords.
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 Mode (Collaborative Data Platform), 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
Forget clicking through dashboards just to find a chart's source parameters. Connect your Mode Analytics account to any AI agent and give your client full command over every single BI asset you own. This server lets your agent talk directly to the core of your data platform, letting you manage everything—from auditing database connections to locating obscure reports by keyword—all through natural conversation.
You're gonna have total control over that Mode analytics environment.
Finding and Defining Your Data Scope
When you need to know what data is even available, the agent starts with discovery. If you don't know where a report lives or what keywords are associated with it, your AI client runs workspace-wide searches against report metadata using search_reports. For a full count of everything generated in the workspace, it uses list_reports to give you an exhaustive inventory list.
Defining your data scope is simple: first, call list_spaces to see all accessible 'Spaces' that isolate datasets across the entire platform, then use get_space to pull every parameter associated with a specific space you want to focus on.
Auditing Your Backend Infrastructure
Understanding your data connections is critical. You can audit your infrastructure by calling list_data_sources; this function enumerates every database and warehouse connector source bound to the account, so you always know exactly what's connected. For ownership checks—who owns which datasets or reports—the agent uses list_members to list all analytical users tracked in the workspace.
Deep Dive Report Inspection
Once you find a report, sometimes you need more than just the name. To get deep into how it was built, your AI client executes get_report. This tool pulls precise configuration details—like chart definitions or query states—for one specific reported token in the workspace. It gives you the technical specs without making you navigate menus or copy tokens manually.
This suite of tools means you never have to guess where data lives or spend time clicking through multiple tabs just to verify a parameter. You just talk to your agent, and it handles running those structured calls—like list_data_sources, search_reports, or get_report—pulling the raw configuration details straight back for you to review.
How Mode MCP Works
- 1 Subscribe to the server and provide your Mode Workspace Name, Access Token, and Secret.
- 2 Tell your AI client exactly what you need (e.g., 'Show me all reports about Q2 revenue').
- 3 The agent runs the necessary sequence of tools—maybe
list_spacesthensearch_reports—and delivers the results back to you.
The bottom line is, your AI client turns complex data navigation into a simple chat command.
Who Is Mode MCP For?
Data Analysts who spend too much time clicking through dashboards. Business users who can't find the right report summary and just want to ask, 'Where is the Q3 marketing ROI?' Analytics Engineers managing multiple data source connections across different environments.
Uses the agent to verify complex SQL reporting parameters or audit configuration details for reports without manually navigating the workspace.
Asks the agent to search for specific data insights by keyword, getting rapid summaries of available reports across the entire platform.
Monitors and manages data warehouse connectors (list_data_sources) or tracks space hierarchies when dealing with multiple Mode environments.
What Changes When You Connect
- Stop clicking through dashboards. Use
search_reportsto query the entire workspace by keyword metadata instead of guessing which report lives where. - Need to know what data you're even using? Run
list_data_sourcesto get a clean inventory of every database and warehouse connector attached to your Mode account. - Verify who owns what. Call
list_membersto see all tracked analytical users, making it easy to audit report ownership boundaries in the workspace. - Get details on specific assets immediately. If you have a report token, use
get_reportto retrieve its precise configuration and chart definitions instantly. - See your entire data scope at a glance. Use
list_spacesbefore running any queries; it shows all accessible 'Spaces' isolating different datasets.
Real-World Use Cases
The Engineer needs to check connectivity first.
An analytics engineer starts a new project and can't tell which data sources are available. Instead of manually checking the settings pane, they prompt their agent: 'Show me all connected databases.' The agent runs list_data_sources and immediately gives them a list of schemas like Snowflake-Prod and BigQuery-Warehouse.
The Business User can't find the quarterly report.
A business user needs the Q2 marketing ROI, but they have no idea which 'Space' it lives in. They simply ask their agent: 'Search for reports related to Q2 ROI.' The agent runs search_reports and returns a list of matching tokens, eliminating manual navigation.
The Analyst needs to check report dependencies.
An analyst suspects a dashboard is using stale data. They use the agent to run get_report on the suspected report token. The output instantly shows the detailed analytical parameters and chart definitions, letting them audit exactly what's broken.
The Team Lead needs to confirm user access.
A team lead suspects a specific department shouldn't see certain data. They ask their agent to run list_members and review the list of statically tracked analytical users, verifying who has access across the workspace.
The Tradeoffs
Trying to list everything in one go.
Typing 'List all reports, spaces, sources, and members.' This floods your agent with too many unconnected calls and makes the output unreadable.
→
Break it down. Start by running list_spaces to define scope. Then use search_reports or list_reports within that context. Always guide the agent step-by-step.
Assuming a report token is enough.
Just providing a random report ID and expecting parameters without first checking if the Space is correct.
→
First, use list_spaces to get your current scope. Then, call get_space with that Space ID before running get_report. This ensures accuracy.
Using general chat for technical audit.
Asking 'What data do we have?' without telling the agent to check specific connectors. The answer will be vague and unhelpful.
→
Be explicit: 'Run list_data_sources and list all available database types.' This forces the agent to use the precise auditing tool.
When It Fits, When It Doesn't
Use this server if your problem is managing complex, multi-layered data assets within a structured BI platform like Mode. You need to audit sources (list_data_sources), inventory reports (list_reports), or define scope boundaries (list_spaces).
Don't use it if you just want to run one simple query against a single table (a direct connector tool is better). Don't use it if your data isn't organized into 'Spaces'. You only need this when the structure and metadata of the platform are part of the problem.
If you know the report name, try search_reports. If you need to check who can see it, use list_members. It’s about platform governance, not just querying data.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mode. 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
Finding a single metric shouldn't require three different tabs and copy-pasting tokens.
Right now, finding an insight means bouncing between the main dashboard, the settings panel for sources, and then manually cross-referencing reports in different 'Spaces.' You spend 80% of your time navigating, not analyzing. If you need to check who owns a report or what data source it's tied to, you open five tabs.
With this MCP server, the agent handles all that context switching. Just ask: 'What sources feed the Q3 Marketing Report?' The agent runs `list_data_sources` and checks the specific metadata for that asset, giving you a direct answer in plain text.
Mode MCP Server: Use `search_reports` to find insights without knowing the token.
Previously, if your boss asked for 'revenue comparisons,' you had to know the exact report name and its location. If it was in a shared space or a personal folder, you wasted time listing every single asset just to check titles against keywords.
Now, you tell the agent: 'Find all reports related to revenue comparison.' The agent runs `search_reports` across the entire workspace metadata, giving you a list of tokens and summaries instantly. It’s that simple.
Common Questions About Mode MCP
How do I check what data sources are available using `list_data_sources`? +
Running list_data_sources provides a full inventory of all database and warehouse connectors bound to your Mode account. It shows you the connection name, type (e.g., Snowflake), and status for auditing purposes.
What's the difference between `list_reports` and `search_reports`? +
list_reports gives you a flat inventory of every single report token in the workspace. search_reports, however, runs deeper; it searches reports by metadata or keywords across the entire platform.
Can I use `get_report` if I only know the Space name? +
No. You must first run list_spaces to find the correct 'Space' token, and then use get_space before calling get_report. The agent needs scope context.
How do I check user ownership with `list_members`? +
The list_members tool lists all statically tracked analytical users in the workspace. This helps you verify who has report access and confirms collaborative boundaries for reporting.
What credentials do I need to execute `list_spaces` or other workspace tools? +
You must provide your Mode Workspace Name, Access Token, and Access Secret. These three keys grant your agent the necessary permissions to read data boundaries and perform actions across your organization's analytics.
How can I use `list_spaces` to limit my query scope? +
The tool retrieves all spaces you have access to. If you only want results for a specific department, remember that the returned space name is required; your AI client handles scoping based on permissions tied to those listed spaces.
What analytical parameters does `get_report` retrieve? +
It retrieves detailed metadata about a single report. Specifically, you get its exact chart configurations, the full list of input parameters, and the current state of the underlying query definitions.
If I run many searches with `search_reports`, are there usage limits? +
The Vinkius Marketplace handles standard rate limiting. If your agent hits a threshold, it will receive an explicit API error code indicating the required wait time before retrying the search query.
Can I see the chart configurations for a specific Mode report through my agent? +
Yes. Use the get_report tool with a specific Report Token. Your agent will retrieve the detailed analytical parameters, exposing the chart configurations and the underlying query logic used to generate the report data.
How do I check which databases are currently linked to my Mode workspace? +
The list_data_sources tool retrieves all database and warehouse connectors bound to your account. Your agent will report the source names and mapped schemas, helping you identify which data is available for SQL reporting.
Can my agent help me find specific reports across different organizational spaces? +
Absolutely. Use the search_reports tool with a search query. Your agent will filter through the metadata of all reports across your workspace, helping you locate critical data insights instantly without manual navigation.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
U.S. Treasury Full — Complete Fiscal & Debt Intelligence
The definitive U.S. Treasury Mega-Server: 13 tools covering national debt ($34T+), interest rates, auction results, federal budget accounting (revenue, spending, deficit), daily cash balances, and official exchange rates. Total access to the financial pulse of the U.S. government without API keys.
Datadog AI (LLM Observability)
Monitor LLM performance via Datadog — track token usage, audit prompts, and monitor AI model metrics directly from any AI agent.
Glean
Empower enterprise search via Glean — search across all SaaS apps, retrieve AI answers, manage custom indexing, and handle chat directly from any AI agent.
You might also like
Momence
Manage sessions, members, teachers, memberships, and bookings for your Momence-powered fitness or yoga studio through natural conversation.
Honeywell Process
Connect Honeywell Process to any AI agent via MCP.
ByteNite
Manage distributed video encoding via ByteNite — track jobs, use encoding templates, and monitor performance directly from any AI agent.