Salesforce Service Cloud MCP. Manage the entire support lifecycle from your chat agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Salesforce Service Cloud MCP Server connects any AI agent to your core support data. It lets you search customer cases, find knowledge articles, track team metrics, and update records—all via natural conversation.
Stop opening Salesforce just to check a case history or status; get the answers directly in your chat client.
What your AI agents can do
Sf add case comment
Adds a new comment to an existing Salesforce case, logging notes or responses for the customer.
Sf case comments
Retrieves all internal and public comments associated with a specific support case ID.
Sf case metrics
Returns an aggregated count of cases, showing how many exist at each combination of status and priority.
Find specific support tickets by subject, number, or owner details.
Get aggregate counts of open cases grouped by priority (High/Medium/Low) and current status (New, Working, Escalated).
Find published articles in Salesforce Knowledge for instant troubleshooting steps or FAQs.
Log a brand-new customer issue, setting the subject, priority, and initial status automatically.
Change a case's status (e.g., New to Working) or escalate its priority level as needed.
Add both internal notes for agents and public responses visible to the customer on an existing ticket.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Salesforce Service Cloud: 8 Tools for Support Agents
Manage the entire lifecycle of customer support tickets—from creation to resolution—using these eight specialized tools.
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 Salesforce Service Cloud on Vinkius019d7602sf add case comment
Adds a new comment to an existing Salesforce case, logging notes or responses for the customer.
019d7602sf case comments
Retrieves all internal and public comments associated with a specific support case ID.
019d7602sf case metrics
Returns an aggregated count of cases, showing how many exist at each combination of status and priority.
019d7602sf cases by status
Lists all open Salesforce cases that match a specified status (e.g., 'New' or 'Escalated').
019d7602sf create case
Generates and logs a brand-new support case record, requiring subject and basic details.
019d7602sf search cases
Searches for specific customer cases using criteria like number or subject line to find context quickly.
019d7602sf search knowledge
Queries the internal knowledge base, returning titles and summaries of relevant published articles.
019d7602sf update case
Changes an existing case record's status or escalates its priority level to reflect progress.
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 Service Cloud, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ 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 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 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The current process of checking case history is a mess of tabs and clicks.
Right now, if you need to know what happened with Case 123-456, you have to open Salesforce. You click the case record, scroll up through internal notes, check if a customer reply was added, and then maybe jump over to Knowledge Base just in case someone already wrote about it. It's slow, requires context switching, and you lose time.
With this MCP server, you just ask your agent: 'What's the full history for Case 123-456?' The agent executes `sf_case_comments` and instantly pulls up every internal note and public reply right here. You get context without the headache.
Salesforce Service Cloud MCP Server: Manage case history & knowledge base
Before, escalating a ticket meant an agent had to manually change its status via one screen and then update the priority on another. If they forgot either step, the record was inaccurate, leading to mismanaged SLAs.
Now, you simply tell your agent: 'Escalate Case 123-456 because it's blocked.' The agent runs `sf_update_case` and handles both the status change and priority boost in a single command. It’s that simple.
What you can do with this MCP connector
Your AI client connects right into your core support data, letting you handle everything in Salesforce Service Cloud without ever leaving your chat window. You don't gotta open up a browser tab and navigate menus just to check a case history or change a status; your agent does it all through natural conversation.
When you need to find customer context, use sf_search_cases to quickly locate specific support tickets using criteria like the case number or subject line. If you know who owns the issue, you can search cases by owner details too. For general queue management, run sf_cases_by_status to pull a list of all open cases matching a specific status, whether it’s 'New' or 'Escalated.'
Need to track how busy your team is? The sf_case_metrics tool gives you an aggregate count showing exactly how many open cases exist at every combination of status and priority level. You can also find out what kind of issues are piling up by running searches on the case volume.
Want to start a new ticket? Use sf_create_case to generate and log a brand-new support record, setting both the subject and basic initial details right away. If you need to make changes to an existing ticket—like moving it from 'New' to 'Working' or bumping up its urgency—the sf_update_case tool lets you change the case status or escalate the priority level as needed.
Talking about context: The sf_search_knowledge tool queries your internal knowledge base, returning titles and summaries of relevant published articles. This gives you instant answers for common issues and troubleshooting steps without having to search through a manual. For full communication history, sf_case_comments retrieves all internal notes and public comments attached to a specific case ID.
When an agent responds or makes a note, use sf_add_case_comment to log that response or detailed note back onto the existing case record.
This setup means your AI client handles everything: you search for tickets using criteria like number or subject line with sf_search_cases; you create new issues with sf_create_case; you manage the lifecycle by calling sf_update_case or getting a full history via sf_case_comments. You can check out all open cases matching 'New' status using sf_cases_by_status, and if you need to add an agent note, you just use sf_add_case_comment.
019d7602-ce23-7158-a008-13c3164fabe9 
How Salesforce Service Cloud MCP Works
- 1 Tell your AI agent what you need done. For example: 'What is our count of high-priority cases that are currently working?'
- 2 The agent maps this request to the appropriate tool, like
sf_case_metrics, and executes it against Salesforce. - 3 You get a structured data response—a clean summary table or list—in your chat window, allowing you to take action immediately.
The bottom line is that your agent runs the necessary Salesforce API calls without you needing to open the UI.
Who Is Salesforce Service Cloud MCP For?
This tool is for anyone who spends too much time context-switching between their chat client and the full Salesforce GUI. If you're a support agent tired of clicking through dashboards, or a CS manager needing real-time queue health without logging in, this saves minutes, every minute.
Resolving tickets on the fly. You use sf_search_cases to find history and then sf_add_case_comment to respond directly from your chat agent.
Monitoring team capacity. You ask for metrics using sf_case_metrics or check queue health with sf_cases_by_status without leaving your desk.
Reviewing customer context. You use the agent to look up a customer's entire case history (sf_case_comments) before making a proactive call.
What Changes When You Connect
- Instant Context Retrieval: Instead of logging into Salesforce, ask the agent to run
sf_search_cases. You get immediate case numbers and subjects without a single click. - Full History Review: Use
sf_case_commentsto pull all internal and customer-facing discussions for any ticket. This gives you full context before writing a response. - Proactive Metrics Checks: Don't guess about team load. Ask the agent to call
sf_case_metricsto get an accurate, real-time count of open cases by status/priority. - Knowledge Access on Demand: When stuck, ask for help articles. The agent runs
sf_search_knowledge, pulling documented solutions right into your workflow chat. - Streamlined Case Progression: Don't update records manually. Tell the agent to run
sf_update_case(e.g., 'Change status to Working') and it handles the API call for you.
Real-World Use Cases
A customer reports a critical bug.
The support agent doesn't know if this is a known issue. The agent first runs sf_search_knowledge to check the KB for '500 error'. If nothing shows up, they use sf_create_case, setting it as High priority, and then add an internal note via sf_add_case_comment documenting their initial findings.
The manager needs a quick team performance snapshot.
Instead of going to the dashboard, the CS Manager asks: 'What is our workload by status?' The agent executes sf_cases_by_status, providing an immediate count of cases categorized as New vs. Escalated.
A ticket needs escalation and follow-up.
The agent reviews the case history using sf_case_comments to understand why the first attempt failed. They then use sf_update_case to escalate the priority and change the status, notifying the next team member automatically.
Finding a specific old ticket number.
The agent remembers the customer mentioned 'billing issue' but can't find the case number. They ask the agent to use sf_search_cases and filter by keywords, pulling up the exact record details.
The Tradeoffs
Updating without context
An agent immediately calls sf_update_case to change a status from New to Working, but they forgot to log why it changed.
→
Always follow the update with documentation. First, run sf_case_comments to review history. Then, use sf_add_case_comment to explain the action taken before calling sf_update_case. This keeps the audit trail clean.
Mixing search types
The agent tries to find a solution by searching general chat history instead of using the dedicated knowledge tool.
→
If you need an answer documented for all customers, use sf_search_knowledge. If you need details on a specific customer's issue, use sf_search_cases.
Over-relying on creation
Instead of finding the right case and updating it, the agent just runs sf_create_case for every little detail.
→
If a customer issue already exists, always use sf_search_cases first. If you must create a new record, use sf_create_case, but make sure to link it back to any existing case ID in the description.
When It Fits, When It Doesn't
Use this MCP Server if your workflow requires complex, multi-step actions: checking history, finding documentation, and then making a record change. You need the agent to coordinate between sf_search_cases (context) and sf_update_case (action). Don't use it if you just need simple data retrieval; for example, if you only want to know 'how many total cases are open,' that metric might be better handled by a dedicated dashboard tool. If your process is simply: 'Search -> Read -> Respond,' this server handles the heavy lifting by exposing sf_case_comments and sf_search_knowledge. It's built for agents who need to operate deep within the system without ever leaving their chat view.
Common Questions About Salesforce Service Cloud MCP
How do I find out how many open cases we have using sf_case_metrics? +
The agent runs sf_case_metrics to return a structured table. This shows you the total count of cases, broken down by both their current status (New/Working) and their priority level (High/Medium). It's perfect for quick dashboard checks.
Can I add a public comment using sf_add_case_comment? +
Yes. When you use sf_add_case_comment, you specify that the comment should be visible to the customer (setting the published flag). This ensures the customer sees your response directly on their portal.
What's the difference between sf_search_cases and sf_search_knowledge? +
Use sf_search_cases when you need information about a specific customer issue or ticket. Use sf_search_knowledge when you are looking for general, documented answers that apply to any customer.
How do I create a new case using sf_create_case? +
You tell the agent to run sf_create_case, and it will prompt you for required details like the subject, description, priority (High/Medium/Low), and origin (Web/Phone/Email). It handles the full record creation.
What does using `sf_case_comments` allow me to see? +
It returns the full conversation history of a case. You get every comment's body, creator name, and date—whether it was an internal note or customer-visible response. This is essential for building context before you draft a reply.
How can I use `sf_cases_by_status` to check the current workload? +
This tool fetches all cases matching one specific status. You run it for 'Working' or 'Escalated' to get an immediate, filtered list of active tickets needing attention. It’s better than a general search when you only care about queue health.
If I need to change the priority and add notes, should I use `sf_update_case`? +
Yes, sf_update_case handles multiple changes in one call. You specify which fields are changing—for instance, advancing status from 'New' to 'Working,' or escalating priority—while appending a description note detailing your actions.
I need to find all open issues for one customer; how do I use `sf_search_cases`? +
sf_search_cases finds records using subject, case number, or other identifiers. To scope it to a single customer, you must pass the associated Contact ID contextually. It quickly delivers core details like status and priority for rapid review.
What types of cases can I manage? +
All Salesforce Case records — filter by status (New, Working, Escalated, Closed), priority (High, Medium, Low), and origin (Web, Phone, Email).
Can I search the Knowledge Base? +
Yes! Searches published Knowledge articles by keyword and returns title, summary, and direct link.
Can I add comments to cases? +
Yes — add internal notes or customer-visible comments to any case.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.