How to Use the Codefresh MCP in LlamaIndex

Q: Can LlamaIndex search through past Codefresh builds?

Yes, by indexing the output of listcodefreshbuilds. Your agent stores the execution history in a vector database, allowing you to run semantic searches over old build statuses.

Q: Can I filter which tools LlamaIndex can access?

Yes, you can use the allowedtools filter when setting up the tool spec. This lets you restrict your agent to read-only actions like listing pipelines while blocking build triggers.

Q: Does this MCP Server expose Codefresh cluster metadata or shared secrets?

No, cluster lists and shared secrets retrieved via listsharedcontexts are processed locally. Your sensitive environment variables and cluster details are never cached or sent to external servers.

Index Codefresh build logs and cluster configurations directly into your LlamaIndex vector store for RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codefresh MCP to LlamaIndex

Create your Vinkius account to connect Codefresh 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 Codefresh with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your LlamaIndex agent with live Codefresh data

Stop guessing why a deployment failed. Your agent runs `get_build_execution_details` to pull real-time logs, then indexes that data directly into your local vector store so your queries are grounded in real telemetry. By feeding the output of `list_codefresh_builds` into your index, the agent can cross-reference recent failures with previous successful runs. This gives you factual, search-backed answers instead of LLM hallucinations.

Query cluster configurations using semantic search

This MCP Server lets you turn your active delivery infrastructure into a queryable knowledge base. Your LlamaIndex agent calls `list_delivery_clusters` and indexes the returned cluster states. Once indexed, you can ask plain-English questions about which clusters are connected. The agent searches the vector store to find matching configurations without needing to hit the raw API every single time.

Index pipeline configurations for quick debugging

Keep your deployment blueprints searchable by fetching them with `get_pipeline_configuration`. The tool retrieves the YAML structure, which LlamaIndex parses and stores as document nodes. When you need to audit your CI/CD setup, the agent searches these nodes to find misconfigured steps. It combines live API data with your local documentation to suggest precise fixes.

Setup guide

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

Connect the BasicMCPClient and wrap it in McpToolSpec. You can then call the tools to load pipeline data and convert the outputs into document nodes for your index.

Yes, by indexing the output of list_codefresh_builds. Your agent stores the execution history in a vector database, allowing you to run semantic searches over old build statuses.

The MCP server manages authentication details securely. LlamaIndex only sees the schema and the clean JSON payloads returned by tools like get_my_codefresh_profile.

Yes, you can use the allowed_tools filter when setting up the tool spec. This lets you restrict your agent to read-only actions like listing pipelines while blocking build triggers.

No, cluster lists and shared secrets retrieved via list_shared_contexts are processed locally. Your sensitive environment variables and cluster details are never cached or sent to external servers.

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