Coralogix unveiled the official Coralogix MCP (Model Context Protocol) Server, which enables third-party AI agents to connect directly to Coralogix’s observability data, including logs, metrics, traces, SIEM, and real user monitoring (RUM), across production, staging, and other environments.
The MCP Server is available to Coralogix’s 4000+ customers, allowing them to enhance their AI agents with access to detailed observability data, dramatically reducing mean time to resolution (MTTR), streamlining agent workflows, and minimizing engineering overhead.
MCP is an open standard developed by Anthropic, the company behind Claude, that provides a simple way to connect tools, data, and services to AI models and systems. By utilizing Coralogix’s MCP Server, AI agents can directly access detailed information about a customer’s applications and infrastructure. This interaction trains the AI agent, enhancing its capabilities and effectiveness.
Last quarter, Coralogix introduced Olly, the advanced AI observability assistant. Olly is an SRE agent that can fully analyze production systems, understands the full context of logs, metrics, and traces, and surfaces RCA and business impact. Today’s MCP Server announcement brings that same deep Coralogix context to builders: it exposes a secure MCP endpoint so developers can stream live telemetry into their own AI agents, IDEs, or chat-ops workflows; and shape the experience to suit their needs.
Agents generally lack direct access to specific observability data, which limits the AI’s utility for this purpose. What makes Coralogix’s MCP Server unique is its ability to surface observability data that is highly specific to each customer. It can search through data to find custom attributes and entities that reflect the customer's unique setup, leading to more accurate results when AI agents access logs, metrics, and traces. Customers can also use natural language prompts to locate key metrics or events.
By integrating with tools developers already use, such as the widely used AI code editor Cursor or IDEs, the MCP Server enables AI agents to not only detect issues in real time but also assist in diagnosing and resolving them all within the same workflow. This “closing the loop” capability streamlines operations and reduces the need to switch between multiple tools.
“Adding the MCP server to our current AI capabilities will enable teams to create custom AI-driven observability experiences,” said Liran Hason, VP of AI at Coralogix. “Now, our customers can easily equip their AI agents with direct access to production observability data. Publishing an official MCP Server also allows our customers to rely on a trusted MCP source and ensure they get the best and most reliable observability capabilities for their agents.”
The Latest
As AI moves from generating responses to performing actions, the need for trust increases exponentially. And as organizations enlist AI agents for increasingly sophisticated business processes, trust is going to be the single most important theme for spurring adoption. What can organizations do to build trustworthy AI agents? ...
I've spent a lot of time in the channel, and one thing I keep coming back to is this: a partner program is only as good as what it looks like in the field. Many programs look great on paper, but when a partner is in front of a customer navigating a complex hybrid environment or trying to make the case for AI-powered observability, the gap between what a vendor promises and what it actually delivers becomes very clear, very fast ...
Enterprises today operate in a real-time environment where uninterrupted access to trusted data has become a baseline expectation for users, applications and automated systems. Traditional DataOps models, built on manual effort and human triage, cannot keep pace with this always active demand. AI agents are emerging as the operational backbone, ensuring consistent data availability, reinforcing trustworthiness and enabling a level of scale that manual processes cannot achieve ...
For decades, trust in the digital workplace rested on familiar signals. We trusted faces on video calls, voices on the phone, and emails that appeared to come from people we knew. These cues felt human and intuitive. They anchored how decisions were made, approvals were granted, and access was authorized. AI-powered deepfakes have quietly broken that model ...
Cloud migration was supposed to be a one-way door. For most enterprises, it turns out it isn't. Cloud data repatriation is a real and growing trend. A new survey ... finds that 89% of organizations plan to expand their on-premises infrastructure footprint over the next two years — and 75% have already moved at least some workloads back from public cloud in the past 24 months. The findings point to a broad rethinking of where data belongs ...
Over the past few years, large language models (LLMs) have revolutionized the software industry. Given their ability to excel at multi-step reasoning, LLMs have helped enterprises streamline workflows and adapt to the unknown. However, employing such models comes with sky-high costs, latency issues, and limited flexibility. In the realm of IT operations, it is generally wiser to employ smaller, domain-specific models instead ...
For years, DevOps teams operated under a simple assumption: collect enough telemetry, and you can find and fix any problem. That assumption is breaking down. Modern enterprises now operate across microservices, hybrid cloud environments, APIs, Kubernetes, and highly automated delivery pipelines. Releases happen continuously, dependencies shift constantly, and failures spread faster than teams can diagnose them ...
New Relic surveyed IT and engineering leaders from the media and entertainment (M&E) sector to understand what's working — and where challenges persist with their observability practices. The findings reveal how M&E organizations are navigating rising platform complexity, audience expectations, and AI-driven change. Below are five takeaways that stand out ...
Let me start with something I've seen play out more times than I can count. A team hits a wall with the cloud. Costs creep up, then spike. Performance starts to feel inconsistent. Someone in finance asks a simple question like "why did this double?" and nobody has a clean answer ... Maybe this isn't the right place for everything. That realization feels like a breakthrough, like you've identified the problem. In reality, you've just identified the starting line ...
In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ...