How to Use the GitGuardian MCP in LlamaIndex

Q: How do I connect GitGuardian to my LlamaIndex pipeline?

Install llama-index-tools-mcp and initialize the MCP client. Wrap it in McpToolSpec and pass the tools to your agent to begin indexing incident metadata.

Q: Can LlamaIndex search through GitGuardian audit logs?

Yes. The agent can call listauditlogs to retrieve workspace activity and index those events, allowing you to run semantic queries on who accessed what.

Q: Does GitGuardian work with self-hosted enterprise servers in LlamaIndex?

Yes. You can override the default API URL by setting the GGAPIURL environment variable, allowing your MCP client to connect to your private GitGuardian instance.

Q: How do I filter out false positives using LlamaIndex?

Your agent can query listsecretincidents and use custom metadata to filter out low-risk alerts. You can also run ignoresecretincident directly from the query interface.

Index GitGuardian secret incidents and honeytoken events directly into your LlamaIndex vector store for semantic security search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitGuardian MCP to LlamaIndex

Create your Vinkius account to connect GitGuardian 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 GitGuardian with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Your GitGuardian MCP Server Semantically

This GitGuardian MCP Server feeds your active alerts into your index by calling `list_secret_incidents` to pull security issues. Your agent indexes the metadata so you can run natural language queries over your entire threat history. You can ask your agent which repositories leak credentials most often. By grounding answers in real-time API data, you eliminate hallucinations and get a clear picture of your actual security posture.

Context-Aware Honeytoken Management

Your LlamaIndex RAG pipeline queries `list_honeytokens` to build a semantic map of where traps are deployed. This stops you from losing track of your decoy credentials. When you need to update a trap, the agent uses `update_honeytoken` or `create_honeytoken_note` to document the context. This ensures your security team always knows which decoy belongs to which sub-system.

Real-time Quota and Health Auditing

Your agent queries `get_quotas` to monitor your current usage limits before launching large-scale document scans. This keeps your indexing pipelines running smoothly without hitting API ceilings. If things look slow, the agent calls `get_health` to verify the connection status. This automated self-check keeps your background security indexing tasks from failing silently.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the MCP client. Wrap it in `McpToolSpec` and pass the tools to your agent to begin indexing incident metadata.

Yes. The agent can call `list_audit_logs` to retrieve workspace activity and index those events, allowing you to run semantic queries on who accessed what.

Yes. You can override the default API URL by setting the GG_API_URL environment variable, allowing your MCP client to connect to your private GitGuardian instance.

Your agent can query `list_secret_incidents` and use custom metadata to filter out low-risk alerts. You can also run `ignore_secret_incident` directly from the query interface.

Only metadata, incident IDs, and honeytoken configurations are stored in your vector database. Raw source code processed by `scan_content` is never written to disk or indexed, protecting your proprietary IP.

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