# Grafana Cloud MCP connector

Connect Grafana Cloud to Elaichi and Claude, ChatGPT, Cursor, or the Elaichi Agent can search your dashboards, query Prometheus metrics and Loki logs, and update dashboards as you, with every call recorded.

Source: https://elaichi.ai/connectors/grafana/

## Facts

| | |
| --- | --- |
| Application | Grafana Cloud |
| Category | Observability |
| AI tools | 62 |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Grafana Cloud builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | grafana.com/docs/grafana-cloud/account-management/support |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Grafana Cloud is connected

- Show the Prometheus error rate for checkout over the last hour
- Find dashboards in the Payments folder that mention latency
- Pull Loki logs for the api service with status 500 today

## Connect Grafana Cloud in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Grafana Cloud.
2. Optionally set Share with, then press Connect.
3. Approve it in Grafana Cloud. Grafana Cloud's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Grafana Cloud tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Grafana Cloud MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Grafana Cloud MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Grafana Cloud MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Grafana Cloud to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Grafana Cloud tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Grafana Cloud through Elaichi

### Check a service's error rate during an incident

SRE. Ask for the Prometheus error rate of a service over the last hour and get the numbers back without opening a query editor. Follow up with a histogram for latency while the call is still going.

### Pull the logs behind a customer complaint

Support. Give the service name and the time window from the ticket and get the matching Loki logs, grouped by pattern, so the reply to the customer is based on what actually happened.

### Find the dashboard nobody can locate

Platform. Search dashboards and folders by name or keyword, get a summary of what each one shows, and send a deep link to the person who asked.

### Catch a dashboard up after a deploy

Engineering. Read the queries behind each panel, then update the dashboard when a metric name or label changed in the release, instead of editing panels one at a time.

### Get a weekly usage number in plain words

Product. Ask for the metric behind sign-ups or orders over the past seven days and get a figure from Prometheus, without learning a query language first.

### Organize dashboards and confirm datasources

Operations. Create a folder for a new team, list which datasources are wired up in Grafana Cloud, and check what each one points at before onboarding starts.

## Elaichi vs Zapier MCP vs Composio for Grafana Cloud

All three can connect Grafana Cloud to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Grafana Cloud tools | Allow or restrict single Grafana Cloud tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Grafana Cloud call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Grafana Cloud to Claude?

Connect Grafana Cloud in Elaichi first. It signs in over OAuth, so you approve the connection on the Grafana Cloud screen and come straight back, with no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude can now search your Grafana Cloud dashboards and run queries as you.

### Does Grafana Cloud work with ChatGPT and Cursor as well as Claude?

Yes. Once Grafana Cloud is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Grafana Cloud once and every client you use picks it up.

### What can an AI agent actually do with my Grafana Cloud data?

An agent connected to Grafana Cloud through Elaichi can search dashboards and folders, summarize what a dashboard shows, read the queries behind its panels, and send a link to it. It can query Prometheus metrics and Loki logs for a service and a time window, list which datasources exist, create folders, and update a dashboard. Short, concrete asks such as a service name and a time range work better than long sentences.

### Does connecting Grafana Cloud give the AI access to every dashboard and datasource?

No. Every call to Grafana Cloud runs as the person who signed in, so the agent sees only the dashboards, folders and datasources that person's Grafana Cloud permissions already allow. Elaichi can narrow that further for a team or a role, but it can never widen what Grafana Cloud itself permits.

### Can my team share one Grafana Cloud connection?

Yes. One person connects Grafana Cloud in Elaichi and shares it with a team, and nobody else handles a token or a credential. Each teammate still signs in to Elaichi as themselves, so every query against Grafana Cloud is logged under the name of the person who ran it.

### Can I stop an agent from changing dashboards in Grafana Cloud?

Yes. Restrictions in Elaichi apply per action, so you can allow searching and querying Grafana Cloud while blocking dashboard updates and folder creation. A restricted action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt, however it is worded, can reach it.

### What happens to a Grafana Cloud connection when someone leaves?

Offboarding a person in Elaichi ends their access to Grafana Cloud through every client at once. A Grafana Cloud connection that was shared with a team keeps working for everyone else. If you want it gone entirely, disconnecting Grafana Cloud once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.

### Does the Grafana Cloud MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Grafana Cloud is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Grafana Cloud?

Yes. Both let Claude, ChatGPT or Cursor use Grafana Cloud. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Grafana Cloud call.

### How is Elaichi different from Composio for Grafana Cloud?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Grafana Cloud: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 62 Grafana Cloud tools

Every tool below is callable through https://api.elaichi.ai/mcp once Grafana Cloud is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Search dashboards** (Search). Search for dashboards by query string.
- **Search folders** (Search). Search for folders by query string.
- **Generate deeplink** (Generate). Generate deeplink URLs for dashboards, panels, and Explore queries.
- **Get dashboard by uid** (Get). Retrieve the complete dashboard JSON by UID.
- **Get dashboard summary** (Get). Get a compact summary of a dashboard without the full JSON.
- **Get dashboard property** (Get). Extract specific parts of a dashboard using JSONPath expressions.
- **Get dashboard panel queries** (Get). Retrieve panel queries with template variable substitution.
- **Update dashboard** (Update). Create or update a dashboard using full JSON or targeted patch operations.
- **Create folder** (Create). Create a Grafana folder.
- **List datasources** (List). List all configured data sources. Supports filtering by type and pagination.
- **Get datasource** (Get). Get detailed information about a data source by UID or name.
- **List prometheus metric names** (List). Discover available metrics with regex filtering and pagination.
- **List prometheus metric metadata** (List). List metadata about currently scraped metrics.
- **List prometheus label names** (List). List label names with optional series selector and time range filtering.
- **List prometheus label values** (List). Get values for a specific label.
- **Query prometheus** (Search). Execute PromQL instant or range queries.
- **Query prometheus histogram** (Search). Query histogram percentiles.
- **List loki label names** (List). List available label names in logs.
- **List loki label values** (List). Get unique values for a specific label.
- **Query loki logs** (Search). Execute LogQL queries for log entries or metric values.
- **Query loki stats** (Search). Get statistics about log streams.
- **Query loki patterns** (Search). Detect and analyze common log patterns.
- **List pyroscope label names** (List). List available label names in profiles.
- **List pyroscope label values** (List). List values for a specific label.
- **List pyroscope profile types** (List). List available profile types.
- **Query pyroscope** (Search). Query profiles or metrics from Pyroscope.
- **List clickhouse tables** (List). List available tables with metadata.
- **Describe clickhouse table** (Describe). Get column schema for a table.
- **Query clickhouse** (Search). Execute SQL queries against ClickHouse datasources.
- **List cloudwatch namespaces** (List). List available AWS namespaces.
- **List cloudwatch metrics** (List). List metrics for a namespace.
- **List cloudwatch dimensions** (List). List dimension keys for a metric.
- **Query cloudwatch** (Search). Query AWS CloudWatch metrics.
- **Query elasticsearch** (Search). Execute Lucene or Query DSL searches against Elasticsearch datasources.
- **Alerting manage rules** (Action). List, filter, and manage alert rules. With write scope, supports creating and updating rules.
- **Alerting manage routing** (Action). View alerting routing configuration, notification policies, contact points, and time intervals.
- **Get annotations** (Get). Fetch annotations filtered by dashboard UID, time range, or tags.
- **Get annotation tags** (Get). Get annotation tags with optional filtering.
- **Create annotation** (Create). Create a new annotation on a dashboard or panel.
- **Update annotation** (Update). Update properties of an existing annotation.
- **List incidents** (List). List incidents with optional status filtering.
- **Get incident** (Get). Get full incident details by ID.
- **Create incident** (Create). Create a new incident.
- **Add activity to incident** (Add). Add a note to an incident’s timeline.
- **List oncall schedules** (List). List OnCall schedules with optional team filtering.
- **Get oncall shift** (Get). Get detailed shift information.
- **Get current oncall users** (Get). Get users currently on-call for a schedule.
- **List oncall teams** (List). List OnCall teams.
- **List oncall users** (List). List OnCall users with optional filtering.
- **List alert groups** (List). List alert groups with filtering by state, team, time range, and labels.
- ...and 12 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.