RCA-MCP Connector
Integrates with LangChain to enable AI agents to use RCA-MCP tools for root cause analysis within LangChain workflows.
Integrates with LangGraph to create reactive agents that can perform root cause analysis using RCA-MCP tools.
Allows local Ollama models to run root cause analysis via the RCA-MCP server with support for causal graphs and 13 RCA model families.
Integrates with OpenAI Agents SDK to let AI agents find root causes, run analyses, and generate reports using RCA-MCP tools.
Provides access to Salesforce's PyRCA algorithms for anomaly detection and root cause localization (BSD-3-Clause licensed adaptation).
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RCA-MCP ConnectorFind root cause of payment failures spike"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RCA-MCP Connector
⚠️ Early access. RCA-MCP's backend is live and this connector has been verified end-to-end against it. The
api.rca-mcp.comcustom domain isn't wired up yet — pointRCA_MCP_API_URLat the current backend URL below. Tool schemas and documentation may still change before the first stable public launch.
What is RCA-MCP?
The only MCP server purpose-built for causal Root Cause Analysis. 56 tools covering causal graph construction, 10 RCA model families plus 3 dedicated PyRCA algorithms (Salesforce PyRCA, BSD-3-Clause), multi-model consensus, and PDF/HTML/Excel/Markdown report generation. Works with Claude, Ollama, Groq, OpenAI, Gemini, LangChain, Cursor — 10 providers.
Related MCP server: Think Strategies
Quick Start (2 minutes)
rca-mcp-connector is a published PyPI package — no clone needed. Point any MCP
client at it with uvx (or pip install rca-mcp-connector if you'd rather manage
the install yourself):
uvx rca-mcp-connectorGet a free API key at rca-mcp.pages.dev — no credit
card required — then set RCA_MCP_API_KEY in your MCP client's config (examples
below).
Claude Code Setup
Add to .mcp.json in your workspace root:
{
"mcpServers": {
"rca-mcp": {
"command": "uvx",
"args": ["rca-mcp-connector"],
"env": {
"RCA_MCP_API_URL": "https://rcamcp-production.up.railway.app",
"RCA_MCP_API_KEY": "your_api_key_here"
}
}
}
}Ollama Setup
go install github.com/mark3labs/mcphost@latest
mcphost -m ollama:qwen3:14b --config providers/mcp-servers.jsonOpenAI Agents SDK
from agents import Agent, MCPServerStdio
import asyncio
async def main():
async with MCPServerStdio(
params={
"command": "uvx",
"args": ["rca-mcp-connector"],
"env": {
"RCA_MCP_API_URL": "https://rcamcp-production.up.railway.app",
"RCA_MCP_API_KEY": "your_api_key_here",
},
}
) as rca_server:
agent = Agent(name="RCA Agent", model="gpt-4o", mcp_servers=[rca_server])
result = await agent.run("Find the root cause of the API latency spike.")
print(result.final_output)
asyncio.run(main())LangChain
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_anthropic import ChatAnthropic
from langgraph.prebuilt import create_react_agent
import asyncio
async def main():
async with MultiServerMCPClient({
"rca-mcp": {
"command": "uvx", "args": ["rca-mcp-connector"],
"env": {
"RCA_MCP_API_URL": "https://rcamcp-production.up.railway.app",
"RCA_MCP_API_KEY": "your_api_key_here",
},
"transport": "stdio",
}
}) as client:
tools = await client.get_tools()
agent = create_react_agent(ChatAnthropic(model="claude-sonnet-4-6"), tools)
result = await agent.ainvoke({"messages": [{"role": "user", "content": "Run an FMEA analysis"}]})
print(result["messages"][-1].content)
asyncio.run(main())See providers/ for ready-to-use config templates and full examples (Groq, Gemini,
OpenRouter, Claude Desktop).
Third-Party Licences
PyRCA (Salesforce): BSD-3-Clause Copyright (c) 2022, salesforce.com, inc. https://github.com/salesforce/PyRCA
Algorithms in rca_pyrca_* tools are independently-written adaptations of PyRCA's
published methods (Zheng et al. 2023, arXiv:2306.11417), not direct copies of PyRCA
source code, per the private API's models/pyrca_adapter.py.
Citing RCA-MCP
@software{rcamcp2026,
title = {RCA-MCP: An MCP Server for Causal Root Cause Analysis},
author = {davetj},
year = {2026},
url = {https://github.com/dave1362/rca-mcp-connector},
note = {v4.1.13}
}Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityFmaintenanceProvides 30+ unified reasoning operations including systematic thinking, mental models, debugging approaches, statistical analysis, interactive notebooks, and advanced problem-solving frameworks for enhanced decision-making and complex reasoning tasks.Last updated9952MIT
- AlicenseBqualityDmaintenanceProvides 10 structured reasoning strategies (Chain of Thought, ReAct, Tree of Thoughts, etc.) for complex problem-solving with session persistence, branching, and tool integration capabilities.Last updated31226MIT
- AlicenseBqualityDmaintenanceAbout AI/ML-powered diagnostic engine for SRE Observability on Konflux and OpenShift. It uses the Model Context Protocol (MCP) and 40+ tools to analyze logs, metrics, and traces, enabling automated RCA and predictive analysis.Last updated37Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI agents to perform structured root cause analysis from clinical incidents and construct learner-ready lesson plans for medical education.Last updated21Apache 2.0
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Multi-Agent AI Validation: X-Z-CS Trinity. 13 tools FREE. Auditable reasoning. v0.5.54
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dave1362/rca-mcp-connector'
If you have feedback or need assistance with the MCP directory API, please join our Discord server