Salesforce Analytics & SOQL MCP. Query any object directly. No UI clicks required.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Salesforce Analytics & SOQL connects your AI client directly to Salesforce data. Run custom queries, pull reports, or view dashboards using natural conversation.
It gives you raw access to any standard or custom object in your organization without needing to write a single line of code.
What your AI agents can do
Sf get dashboard
Retrieves all component data—charts, metrics, and underlying tables—for a specific Salesforce dashboard ID.
Sf list dashboards
Lists available dashboards by title, folder, and last reference date. Use this to find the correct dashboard ID first.
Sf list reports
Returns a list of all reports, showing their name, format (Summary/Matrix), and ID. This helps you know what reporting assets exist.
You send a specific query (e.g., SELECT Id, Name FROM Account WHERE Industry = 'Tech') and the agent pulls back all matching records.
The tool returns a catalog of every report in your Salesforce account, including its folder location and format (Summary/Tabular).
After finding the correct report using sf_list_reports, you execute it to pull up to 2000 rows of data.
You ask for a count (e.g., 'How many Cases do we have?'), and the tool returns a single integer representing the total number of records.
The agent provides a list of all visual summaries, showing their titles, folder paths, and last reference dates so you know what's available.
You specify a dashboard ID, and the tool extracts the underlying metrics, charts, and tables that make up those visual summaries.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Salesforce Analytics & SOQL: 6 Tools for CRM Querying
These tools allow your agent to query objects, run reports, and analyze Salesforce data directly via raw API calls.
019d7601sf get dashboard
Retrieves all component data—charts, metrics, and underlying tables—for a specific Salesforce dashboard ID.
019d7601sf list dashboards
Lists available dashboards by title, folder, and last reference date. Use this to find the correct dashboard ID first.
019d7601sf list reports
Returns a list of all reports, showing their name, format (Summary/Matrix), and ID. This helps you know what reporting assets exist.
019d7601sf record count
Gets the total number of records for any object in Salesforce, perfect for quick volume checks like 'how many accounts do we have?'
019d7601sf run report
Executes a specific report by its ID and returns up to 2000 rows of structured data.
019d7601sf run soql
Runs any raw SOQL query against your Salesforce org, allowing you to filter, aggregate, or join data from multiple objects.
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 Salesforce Analytics & SOQL, 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 tired of clicking through menus just to see a number or two, right? This MCP Server hooks your AI client up straight to Salesforce data, giving you raw access to anything in your org—no code required. You can run custom queries, pull reports, and drill down into dashboards using plain conversation.
It’s like having an analyst sitting next to you who types faster than you speak.
Raw SOQL Querying
With the sf_run_soql tool, you'll send a specific query—for example, something asking for all Accounts where the Industry is 'Tech'—and your agent pulls back every single matching record. This lets you filter, join, or aggregate data across multiple objects in your Salesforce org. It’s how you get precise sets of data points that standard reports often miss.
You can query anything from complex relationships to basic object fields.
Running Specific Reports
To work with existing reporting assets, you'll use two tools. First, the sf_list_reports tool returns a full catalog showing every report in your Salesforce account. It lists their name, folder location, and whether they’re Summary or Matrix formatted. Once you know what reports exist, you can execute them using sf_run_report.
This runs the specific report by its ID and gives you up to 2000 rows of structured data right in your chat window. You don't just get the name; you get the whole damn dataset.
Checking Data Volume and Metrics
Need a quick pulse on how big something is? The sf_record_count tool handles that instantly. Just ask, 'How many Cases do we have?' and it spits out one integer: the total count of records for any object. It’s perfect for fast volume checks—you won't waste time navigating to a list view just to get a number.
Working with Dashboards
When you need a visual summary, you gotta work through two steps because dashboards are layered. First, use sf_list_dashboards. This tool shows you all the available visual summaries, listing their titles, folder paths, and when they were last referenced. You'll find the specific dashboard ID you need from this list.
Second, once you have that ID, the sf_get_dashboard tool extracts everything underneath those visuals—it grabs the component data, including charts, metrics, and underlying tables. This gives you the raw numbers and metrics that make up whatever visual summary is displayed on the board.
How It All Connects
You can run these tools independently or use them together. You'll start by listing available dashboards to find the ID, then pass that ID to pull out all the component data for deep analysis. If you need a report first, you list reports, grab the ID, and execute it into raw rows of data.
The SOQL tool remains your ultimate fallback; if no pre-built report or dashboard works, you write the query yourself using sf_run_soql to get exactly what you're looking for.
This server treats Salesforce like a database endpoint—it doesn’t care about the UI, only the data. You talk business logic, and your agent delivers the raw records, counts, or component metrics instantly. It’s fast. It’s accurate. It skips all the corporate bullshit layers between you and the truth in your CRM.
How Salesforce Analytics & SOQL MCP Works
- 1 Start by telling your agent what you need: 'What was our total revenue from closed deals last month?'
- 2 The server identifies the necessary tool (likely
sf_run_soql), constructs the query, and executes it against Salesforce. - 3 You get back a structured data table containing only the results of that specific calculation or query.
The bottom line is that you talk to your agent like talking to a person who already has read access to every spreadsheet in your CRM.
Who Is Salesforce Analytics & SOQL MCP For?
This server's core user is the Ops Analyst or RevOps professional. They run into walls when they need data immediately but the BI team schedule says 'next week.' You're also here if you’re an Executive who needs a quick, accurate answer about quarterly performance without reading 50 pages of PowerPoint.
You use this to build instant operational reports. Instead of waiting for the BI queue, you run specific SOQL queries to check lead conversion rates or opportunity pipeline health.
You pull ad-hoc data sets when a meeting requires it. You use sf_list_reports first to see what reports exist, then run them with sf_run_report to get the numbers.
You check key performance indicators instantly. You ask 'What was our win rate last quarter?' and the agent runs the complex query for you, giving a simple number.
What Changes When You Connect
- Instant Insights: Skip the BI queue. Instead of waiting days for a report, you ask your agent to run an
sf_run_soqlquery and get data in seconds. - Full Data Visibility: The server gives you raw SOQL access. You can join objects and write complex filters that no pre-built dashboard could handle.
- Navigation Check: Need to know what reports are available? Use
sf_list_reports. It provides a full catalog of reporting assets so you never guess a name again. - Visual Breakdown: If the raw data is too much, use
sf_get_dashboardafter runningsf_list_dashboardsto pull the actual component metrics behind the visual charts. - Capacity Planning: Never manually count records again. The simple
sf_record_counttool gives you an immediate total for any object (Account, Contact, Lead, etc.). - Efficiency Through Flow: By sequencing tools—first
sf_list_reports, then passing the ID tosf_run_report—you automate multi-step data retrieval.
Real-World Use Cases
The Executive Quarterly Review
A VP needs to know the total revenue from deals that closed in Q3, but the standard dashboard doesn't track it. They prompt their agent: 'Total Closed Won Amount Q3.' The agent uses sf_run_soql with a complex date and stage filter, returning $X million instantly.
The Analyst Needs to Cross-Reference Data
An analyst needs to know the count of all Accounts in 'Technology' that have more than 10 Contacts. They first run sf_record_count for Account, then use sf_run_soql with a JOIN clause to get the accurate cross-object number.
Finding Obscure Reports
A user needs a report on 'Q4 Marketing Spend' but can't remember the folder or name. They run sf_list_reports. The list appears, they see the correct title, and then use that ID to execute it with sf_run_report.
Checking Lead Volume by Industry
A RevOps manager needs a quick snapshot: 'How many leads do we have broken down by industry?' They ask the agent, who uses sf_run_soql to group and count records from the Lead object.
The Tradeoffs
Trying to guess report names
Typing 'Show me the Q3 revenue dashboard' and having the agent fail because it can't find a matching ID.
→
Always start by running sf_list_dashboards or sf_list_reports. This gives you the exact IDs needed to successfully execute the data retrieval with sf_get_dashboard or sf_run_report.
Running a dashboard without listing it first
The user just asks for 'the sales summary.' The agent fails because it doesn't know the correct, unique Dashboard ID.
→
First, use sf_list_dashboards to find the exact title and ID. Then pass that ID to sf_get_dashboard.
Over-relying on pre-built reports
A report shows total deals but doesn't filter by 'Enterprise' clients, so the user can't get the specific data they need.
→
When standard reports fail, switch to sf_run_soql. Write a query that includes the necessary filters (e.g., WHERE Account.Industry = 'Enterprise').
When It Fits, When It Doesn't
Use this server if your data needs require real-time access or complex filtering across multiple objects. If you need to know what data is available, start with listing tools (sf_list_reports, sf_list_dashboards). Use sf_run_soql when the standard reporting structure fails and you need a custom query (e.g., joining Account and Opportunity data). Don't use this if your goal is merely to read documentation or view general Salesforce help pages; that requires navigating the native UI. You can also run full reports using sf_run_report, but remember, for maximum flexibility, raw SOQL access is always superior.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Salesforce. 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 6 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Getting data from Salesforce used to mean a lot of clicking and waiting.
Today, getting accurate metrics means opening the dashboard, navigating through multiple tabs, manually running reports, then exporting everything to Excel. You spend time figuring out which report ID you need, or worse, sending an email request just to get a CSV file that's already outdated.
With this MCP server, you skip all that friction. Your agent talks directly to Salesforce and runs the necessary tools—like `sf_run_soql`—to deliver exactly what you asked for. You get clean data in plain text, no clicks required.
Salesforce Analytics & SOQL MCP Server: Raw access is immediate.
Previously, if you needed a metric that spanned three different objects—say, 'Leads from Tech companies who opened an email over $5k'—you were limited to the specific reports Salesforce built. You couldn't combine those fields in one place.
Now, you use `sf_run_soql`. This gives your agent the power to write a custom query that joins Account, Contact, and Opportunity records just like you need them, giving you data granularity before it was possible.
Common Questions About Salesforce Analytics & SOQL MCP
How do I find out what reports are available using sf_list_reports? +
Run sf_list_reports to get a full catalog of all reporting assets. The output lists the report name, its folder path, and whether it's Tabular or Summary format.
Can I query data that isn't in a standard dashboard using sf_run_soql? +
Yes. sf_run_soql is the most powerful tool because you write the exact criteria, allowing you to pull records and calculate metrics far outside the scope of any pre-built visual summary.
What's the difference between sf_run_report and sf_run_soql? +
Use sf_run_report when you want the data from a report that already exists in Salesforce. Use sf_run_soql when you need to build a brand new, custom query combining specific objects or filters.
If I just want an estimate of how many leads we have, do I use sf_record_count? +
Yes. sf_record_count is the fastest way to check data volume. You pass it any object name (like 'Lead' or 'Account'), and it returns a single number.
If I use sf_list_dashboards, what do I need to get the actual data using sf_get_dashboard? +
You must first run sf_list_dashboards to find the specific ID of the dashboard you want. After getting that ID, pass it to sf_get_dashboard. This process fetches all component data—the charts, metrics, and underlying tables—from the visual summary.
I found a report using sf_list_reports; how do I execute it with sf_run_report? +
You need to pass the exact Report ID you retrieved from sf_list_reports into sf_run_report. This action mimics clicking 'Run' in Salesforce, returning up to 2000 rows of raw data for that specific saved report.
What are the limitations or constraints when I run a complex query using sf_run_soql? +
sf_run_soql allows you to query any object, but remember it operates on Salesforce's data limits. It returns up to 2000 rows and requires standard SOQL syntax for joins and filtering. You use this tool when the specific data structure isn't available in a pre-built report.
How do I perform grouped analysis or counts when using sf_run_soql? +
You include aggregate functions like COUNT() or SUM(), and then append the GROUP BY clause to your query. For example, SELECT Industry, COUNT(Id) FROM Account GROUP BY Industry tells the system exactly which fields you want totaled and grouped.
Can I run any SOQL query? +
Yes! Any valid SOQL query against standard or custom objects, respecting your field-level security.
Can I run existing Salesforce reports? +
Yes — list all reports, then run any by ID. Returns full row data.
Is this safe to use? +
All queries are read-only and respect your Salesforce permissions. The SOQL tool only reads data — it cannot modify records.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
iLEVEL (S&P Global)
Manage private equity investments, portfolios, and funds via iLEVEL API.
Trimble
Equip your AI agent with enterprise-grade truck routing, commercial geocoding, and advanced toll cost logistics algorithms.
OneSignal
Send push notifications, emails, and in-app messages to millions of users with segmentation and A/B testing built in.
You might also like
Qovery
Bring effortless Kubernetes and cloud deployment management to your IDE. List environments, check application states, restart pods, and deploy exact Git commits via chat.
Ragas
Equip your AI with Ragas to create datasets, run RAG evaluations, and track experiment metrics directly from your workflow.
NVIDIA Vision
Generate images, analyze visuals, detect objects, and caption images via NVIDIA Vision APIs.