How to Use the Salesforce MCP in LlamaIndex

Q: How does the Salesforce MCP server work with LlamaIndex's indexing?

It's straightforward. You wrap our client in the McpToolSpec. LlamaIndex then treats each tool, like listopportunities, as a document loader, ingesting the tool's output directly into your knowledge base.

Q: How do I run a Salesforce report from my LlamaIndex app?

Your agent does it in two steps. First, it calls listreports to get the ID of the report it needs. Then it passes that ID to the runreport tool to execute it and get the results for analysis or indexing.

Q: Can I restrict which Salesforce objects my LlamaIndex agent can access?

Yes. The McpToolSpec allows you to filter the tools you expose to the agent. If you don't want it touching Case records, you just don't give it the tools that can read or write them.

Ground your LlamaIndex RAG applications in live Salesforce data, not stale exports.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salesforce MCP to LlamaIndex

Create your Vinkius account to connect Salesforce to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salesforce with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Live CRM

Stop feeding your RAG apps with CSV exports. With this MCP server, your LlamaIndex agent can call `list_accounts`, `list_contacts`, and `list_opportunities` directly. The results are fed straight into your vector store. Now you have a knowledge base that reflects your CRM in near real-time. When you ask a question about an account, the answer is based on what's in Salesforce right now. This is how you build a reliable CRM chatbot.

Query-Time Data Augmentation

Your agent doesn't need to have all the data indexed upfront. You can build a query engine that uses tools on the fly. When a user asks a complex question, the agent can use `soql_query` to fetch fresh, specific data points from Salesforce. It then combines this live data with information already in its index. This hybrid approach gives you the speed of a vector database and the accuracy of a live API call, ensuring answers are both fast and correct.

Build a Salesforce Expert with LlamaIndex

A truly smart agent needs to understand the *structure* of your data. It can use `describe_object` to learn about your custom fields and objects. This context helps it construct better queries and interpret results correctly. Combine that with `run_report` to pull high-level summaries and `get_record` for specifics. LlamaIndex can ingest all of this—metadata, reports, and individual records—to build a comprehensive, searchable knowledge graph of your entire Salesforce organization.

Setup guide

Set up Salesforce MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Salesforce MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Salesforce tools.",
)
response = await agent.run("List recent Salesforce data")

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Salesforce now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Salesforce MCP in LlamaIndex

It's straightforward. You wrap our client in the `McpToolSpec`. LlamaIndex then treats each tool, like `list_opportunities`, as a document loader, ingesting the tool's output directly into your knowledge base.

Yes, that's a primary use case. Your LlamaIndex agent can use the `list_opportunities` and `get_record` tools to populate its index, then answer user questions about deal stages, amounts, and close dates based on live Salesforce data.

Your agent does it in two steps. First, it calls `list_reports` to get the ID of the report it needs. Then it passes that ID to the `run_report` tool to execute it and get the results for analysis or indexing.

Yes. The `McpToolSpec` allows you to filter the tools you expose to the agent. If you don't want it touching `Case` records, you just don't give it the tools that can read or write them.

The server fetches Salesforce data like Account and Opportunity records when your LlamaIndex agent calls a tool. The data is piped through a secure, temporary V8 sandbox directly to your application for indexing. Vinkius never stores or logs the content of these API calls.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript