How to Use the Vectara MCP in AutoGen

Q: How do I check corpus status using Vectara with AutoGen?

The agents use getcorpusdetails to pull metadata and configuration settings for a specific corpus. This ensures all participants agree on the state of the data source before proceeding.

Q: What if I need to delete documents using Vectara with AutoGen?

The deletecorpusdocument tool executes the permanent removal of an indexed document. Agents should only call this after a multi-agent debate confirms that data is no longer needed.

Q: Can I search across multiple datasets using Vectara with AutoGen?

Yes, performsemanticsearch lets the agent query one or more corpus keys. This allows different perspectives to gather evidence from diverse parts of your data estate.

Q: How do I list all available datasets using Vectara with AutoGen?

The initiating agent calls listcorpora to obtain a complete inventory of every corpus. This is essential for setting the scope and boundaries for the multi-agent conversation.

Drive consensus decisions with AutoGen using Vectara's structured data tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vectara MCP to AutoGen

Create your Vinkius account to connect Vectara to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Vectara with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute grounded chats and citations

The `execute_rag_chat` tool lets a group of agents query knowledge bases, returning an AI response complete with source citations. This ensures that the final consensus answer is verifiable against real data. The debate can be focused by using `perform_semantic_search`. Before debating, one agent can search across multiple corpora to gather foundational evidence for the other participants.

Discover and audit data sources

The first step in a multi-agent discussion is knowing what facts are available. Use `list_corpora` to give all participating agents an inventory of every dataset. Then, `get_corpus_details` allows them to check the specific configuration for any given corpus. Agents can also audit their own history by calling `list_chat_sessions`, providing full transparency into previous interactions.

Manage data integrity and deletion

If a document is compromised or outdated, the system needs to remove it. The `delete_corpus_document` tool permanently removes an indexed document from a corpus. Agents must treat this action as irreversible. The consensus process can incorporate cleanup steps; for example, one agent might confirm the deletion using `delete_corpus_document` after review.

Setup guide

Set up Vectara MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Vectara tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Vectara_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Vectara data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Vectara_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Vectara data")
    print(result.messages[-1].content)

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 Vectara. 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 Vectara 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 Vectara MCP in AutoGen

The agents use `get_corpus_details` to pull metadata and configuration settings for a specific corpus. This ensures all participants agree on the state of the data source before proceeding.

The `delete_corpus_document` tool executes the permanent removal of an indexed document. Agents should only call this after a multi-agent debate confirms that data is no longer needed.

Yes, `perform_semantic_search` lets the agent query one or more corpus keys. This allows different perspectives to gather evidence from diverse parts of your data estate.

The initiating agent calls `list_corpora` to obtain a complete inventory of every corpus. This is essential for setting the scope and boundaries for the multi-agent conversation.

This server interacts with Corpus Metadata, which includes system information about your datasets. The `list_corpus_documents` tool helps agents audit the specific documents contained within a corpus.

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