How to Use the Greenspark MCP in LlamaIndex

Q: How do I index Greenspark project data into a LlamaIndex vector store?

You run listprojects to fetch the data, convert the output into LlamaIndex Document objects, and insert them into your VectorStoreIndex. This makes all your environmental project details searchable by your agent.

Q: Can a LlamaIndex agent trigger a Greenspark offset during a query?

Yes, you register createimpact as a tool within your LlamaIndex FunctionAgent. When a user completes a query that triggers an offset, the agent executes the tool and returns the confirmation.

Q: Can I use this MCP to filter which environmental projects my agent can access?

Yes, you can configure your tool list to only expose getproject for approved initiatives. This ensures your agent only promotes projects that match your brand's specific environmental goals.

Index real-time environmental data and ground your LlamaIndex RAG applications with verified Greenspark climate metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greenspark MCP to LlamaIndex

Create your Vinkius account to connect Greenspark to LlamaIndex 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 Greenspark with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index your Greenspark impact history for LlamaIndex RAG

The `list_impacts` tool pulls your historical climate contributions directly into your LlamaIndex document store via our managed MCP. Your application indexes these records as nodes, making your entire environmental history searchable via semantic queries. This prevents your agent from hallucinating sustainability metrics when customers ask about your carbon offsets. The agent queries the vector store, retrieves the actual impact records, and cites verified Greenspark data.

Ground customer queries in live project data

The `get_project` tool retrieves detailed descriptions and verification links for specific environmental projects supported by Greenspark. Your LlamaIndex agent uses this raw data to answer customer questions about where their trees are planted, using this MCP Server to ground its responses. You can feed `list_projects` into your index to give your agent a complete directory of active initiatives. When a user asks about reforestation, the agent retrieves the exact project details and displays them instantly.

Monitor account limits within your LlamaIndex agent

The `get_subscription` tool checks your active Greenspark subscription tier and current usage limits. Your LlamaIndex agent queries this tool to verify that your account has sufficient credits before executing new climate actions, utilizing this MCP to query the subscription state. This prevents API errors during high-volume periods by letting the agent monitor usage. If limits are close, the agent can alert your team or queue requests instead of failing silently.

Setup guide

Set up Greenspark 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 Greenspark 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 Greenspark tools.",
)
response = await agent.run("List recent Greenspark 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 Greenspark. 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 Greenspark 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 Greenspark MCP in LlamaIndex

You run `list_projects` to fetch the data, convert the output into LlamaIndex Document objects, and insert them into your VectorStoreIndex. This makes all your environmental project details searchable by your agent.

Yes, you register `create_impact` as a tool within your LlamaIndex FunctionAgent. When a user completes a query that triggers an offset, the agent executes the tool and returns the confirmation.

This MCP Server provides direct access to structured data like `get_impact_summary`, eliminating the need for your agent to guess or hallucinate your climate contributions.

Yes, you can configure your tool list to only expose `get_project` for approved initiatives. This ensures your agent only promotes projects that match your brand's specific environmental goals.

Vinkius executes this server inside a secure, ephemeral sandbox that processes footprint calculations in memory. Your transactional footprint estimates are never written to persistent disk or shared with third parties.

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