Coralogix MCP for AI. Control observability, logs, and dashboards from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Coralogix lets you manage your entire observability stack from a natural conversation. You can ingest logs with specific metadata, set system reliability goals using SLOs, create or update Grafana dashboards, and track deployment versions—all without leaving your chat window.
What AI agents can do with Coralogix Automation
Get rules
Get all parsing rules
Get tco overrides
Get all TCO policy overrides
List custom enrichments
List custom enrichments
Send arrays of log objects directly to Coralogix while specifying severity levels and metadata.
Programmatically create, list, or delete SLOs, ensuring your system's reliability metrics are always monitored.
Retrieve, create, or delete entire groups of log parsing rules to restructure how Coralogix interprets incoming data.
Search for existing hosted Grafana dashboards or generate and update full dashboard configurations.
Manage Total Cost of Ownership (TCO) policy overrides to save money on long-term log retention.
Mark specific versions or deployments using version tags, tying system behavior directly back to code changes.
Ask an AI about this
Waiting for input…
What AI agents can do with Coralogix MCP: 17 Tools Available
These tools allow you to interact with every core function of Coralogix—from setting SLOs and managing costs to ingesting logs and building dashboards.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Coralogix on VinkiusGet Rules
Get all parsing rules
Get Tco Overrides
Get all TCO policy overrides
List Custom Enrichments
List custom enrichments
List Slos
List all SLOs
Search Grafana Dashboards
Search hosted Grafana dashboards
Create Rule Group
Create a parsing rule group
Create Slo
Create a Service Level Objective (SLO)
Create Tco Override
Create a TCO policy override
Send Logs
Provide an array of log objects. Send logs to Coralogix
Create Version Tag
Create a version tag
Delete Custom Enrichment
Delete a custom enrichment
Delete Rule Group
Delete a parsing rule group
Delete Slo
Delete an SLO
Delete Tco Override
Delete a TCO policy override
Get Grafana Home
Get hosted Grafana home dashboard
Get Rule Group
Get a specific parsing rule group
Create Grafana Dashboard
Create or update a hosted Grafana dashboard
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Coralogix integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Coralogix, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coralogix. 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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 17 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The Overhead of Manual Observability Management, Solved with Vinkius AI Gateway
Today, keeping an eye on system health is a painful cycle of context switching. You open your log viewer to see errors, then jump to Grafana to check the dashboard metrics, and finally switch tabs again to update a parsing rule in a separate console just because the log format changed. It’s clicking through five different systems every time you try to answer one simple question: 'Why is this slow?'
With this MCP, that entire manual process collapses into a single conversation. You tell your agent what needs fixing—'Check SLOs for payment service and fix parsing rules if they are wrong.' The agent executes the checks, reads the data, and reports back. You get answers instantly; you don't get more tabs to click.
Coralogix MCP Gives You Total Observability Control
The manual steps that disappear are the constant logins, the regex testing in a separate utility window, and the need to copy dashboard IDs between systems. Before, every change required multiple tickets and approvals just to confirm the scope of the rule group.
Now, you own the entire lifecycle. You don't just read about system health; you actively manage it by calling `create_slo` or marking a deployment using `create_version_tag`. It’s direct control over your infrastructure state.
What your AI can actually do with this
You're already watching logs in Coralogix, but managing the underlying rules, costs, and metrics still requires jumping between consoles. This MCP lets you take control of those core observability functions using only natural language commands. You can send application logs with custom severity levels and metadata instantly. Want to update your dashboards? You can search for existing Grafana views or create entirely new ones on the fly.
Need to keep an eye on costs? Programmatically manage Total Cost of Ownership overrides, ensuring you're not paying too much just because a log volume spiked overnight. If your workflow needs this kind of deep control over logging and metrics, connecting through Vinkius is the simplest way to get it working with any AI client.
019ea5e6-62de-7180-9fb2-21ada17470da 
Here's how it actually works
The bottom line is that your AI client handles all the API calls so you don't have to leave your chat window or open multiple consoles.
First, subscribe your AI client to this MCP and provide your Coralogix API Key and Domain.
Next, you tell the agent what needs doing—for example, 'List all SLOs' or 'Search for K8s dashboards'.
The agent executes the request against Coralogix and returns structured data, letting you act on it immediately.
Who is this actually for?
This MCP is built for the SRE and DevOps engineer who gets frustrated having to switch between five different dashboards just to check a deployment tag, review cost overruns, and update a parsing rule. It’s for anyone whose job involves understanding system health from massive streams of data.
You use this MCP to quickly check TCO overrides or delete old SLOs during an incident response, keeping your focus on the fix, not the console.
You automate complex tasks like creating new parsing rule groups and linking them to specific deployment tags without writing a single script.
You send application logs directly from your code editor or chat environment, verifying dashboard configurations as part of testing.
What Changes When You Connect
Stop context switching. Instead of jumping between the log view, Grafana, and a separate cost dashboard to check an SLO, you manage all these elements in one conversation with your agent.
Pinpoint deployment impact instantly. When something breaks, use create_version_tag to mark the release, then query logs using send_logs to see exactly what changed when the system started acting up.
Save money on log retention without manual effort. Use get_tco_overrides and create_tco_override to programmatically manage how long certain data streams are kept, optimizing your costs instantly.
Build complex dashboards faster. You can search for existing views with search_grafana_dashboards or tell the agent to build a whole new dashboard using create_grafana_dashboard, skipping manual setup time.
Maintain system health goals easily. Defining and checking SLOs is critical; you can use list_slos and create_slo to keep your reliability metrics accurate without needing platform admin access.
See it in action
Diagnosing a performance regression
A developer notices slow query times. They ask their agent: 'What happened after the v2.3 release?' The agent uses create_version_tag to mark that deployment, then sends logs using send_logs, letting them immediately see all high-latency errors correlated with the specific version.
Adjusting logging costs
The SRE team is over budget due to excessive retention on certain log types. They instruct their agent to 'Apply a cheaper storage rule for logs older than 90 days.' The MCP executes create_tco_override, saving the company money without manual console work.
Building a new service dashboard
A team needs visibility into microservice health. Instead of manually configuring Grafana, they ask their agent to 'Create a dashboard for Payment-Service metrics.' The MCP uses create_grafana_dashboard and populates the view instantly.
Auditing compliance requirements
An auditor requires proof of system reliability goals. Instead of exporting data, they ask the agent to 'List all active SLOs.' The MCP calls list_slos and provides a clean, structured list for immediate review.
The honest tradeoffs
Trying to manually configure every rule
A user tries to update a parsing rule by navigating through the GUI, copying regex patterns from old documentation, and pasting them into the new form. This takes 45 minutes and is prone to copy/paste errors.
Just ask your agent: 'Update the Nginx logs group with this new pattern.' The MCP handles the create_rule_group or update process in seconds, guaranteeing syntax correctness.
Forgetting which dashboard to use
A developer spends time building a complex Grafana visualization that turns out to be redundant because another team already built a better version of it.
Before you start, ask the agent to search_grafana_dashboards first. This instantly checks if someone else already created or updated the view you need.
Overcomplicating log ingestion
The user manually formats a massive JSON file with logs and has to figure out which fields are missing before uploading it.
Simply use send_logs and provide the structured array of logs. The MCP handles the necessary formatting and metadata tagging required by Coralogix.
When It Fits, When It Doesn't
Use this MCP if your job requires deep, cross-domain control over observability data: you need to manage SLOs and dashboards and log rules from one place. It's perfect for SRE teams whose day involves reacting to alerts while simultaneously optimizing costs and tracking deployments.
Don't use it if all you need is simple viewing, like just looking at a raw stream of logs; those tools are fine on their own. But if your process requires changing the underlying structure—like creating an SLO or modifying parsing rules—you need this MCP. If your goal is simply to delete old data without tracking its history, look for a dedicated data retention tool instead of using delete_tco_override.
Questions you might have
How do I use the Coralogix MCP to check my current SLO status? +
You simply ask your agent to list all Service Level Objectives. The agent uses list_slos and returns a comprehensive list, showing which services are meeting their reliability goals right now.
Can the Coralogix MCP help me create dashboards? +
Yes, it can. You tell your agent what you need, and they use create_grafana_dashboard to build or update a dashboard configuration for you directly from the chat.
Does Coralogix MCP handle log ingestion? +
It does. Use send_logs to provide an array of logs and metadata, sending them instantly into your Coralogix account without needing a separate upload tool.
What is the difference between get_rules and create_rule_group in Coralogix MCP? +
get_rules just shows you what rules are active. You use create_rule_group when you need to build a new, structured collection of parsing rules for incoming data.
If I update my code, how do I track it with the Coralogix MCP? +
Use the create_version_tag tool. This marks the system with your specific version name, allowing you to correlate any log spike or performance drop directly back to that exact deployment.
We've already built the connector for Coralogix. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 17 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.