Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion ai/llms-txt.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -38,4 +38,3 @@ curl https://checklyhq.com/docs/detect/synthetic-monitoring/browser-checks/overv

- [Markdown Access](/ai/markdown-access)
- [Checkly Skills](/ai/skills)
- [Checkly Rules](/ai/rules)
1 change: 0 additions & 1 deletion ai/markdown-access.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -61,4 +61,3 @@ Based on this, how do I set up a browser check with a custom user agent?
## Additional resources

- [Checkly Skills](/ai/skills)
- [Checkly Rules](/ai/rules)
15 changes: 3 additions & 12 deletions ai/mcp-server.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -85,18 +85,9 @@ Create a major status page incident for the API outage, but do not notify subscr

## MCP, Skills, and CLI

MCP, Checkly Skills, and the Checkly CLI are complementary. The CLI can also read live Checkly data and remains the most capable path for scripted workflows and local Monitoring as Code projects.

Use the MCP Server when you want a quick, OAuth-based connection from a supported client without setting up the Checkly CLI in that environment. Use Checkly Skills with the CLI when your agent needs to create, edit, test, or deploy code from your local project.

| Use case | Recommended path |
| --- | --- |
| Ask quick, ad hoc questions from a supported client | MCP Server |
| Inspect live Checkly data without local CLI setup | MCP Server |
| Trigger existing deployed checks from chat | MCP Server or [Checkly CLI](/cli/overview) |
| Create or edit check code | [Checkly Skills](/ai/skills) with the [Checkly CLI](/cli/overview) |
| Test, deploy, or automate local Monitoring as Code projects | [Checkly CLI](/cli/overview) |
| Add reusable Checkly best practices to an agent | [Checkly Skills](/ai/skills) |
MCP, Checkly Skills, and the Checkly CLI are complementary. Use the MCP Server for a quick, OAuth-based connection from a supported client. Use Checkly Skills with the CLI when your agent needs to create, edit, test, or deploy code from your local project.

See [Skills, MCP, and the CLI](/ai/overview#skills-mcp-and-the-cli) for a full comparison of when to use each.

## Learn more

Expand Down
141 changes: 28 additions & 113 deletions ai/overview.mdx
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
---
title: 'AI Agents & Coding Assistants'
description: 'Use AI agents and coding assistants with Checkly Skills, rules, and the Checkly MCP Server.'
sidebarTitle: 'Agents & Checkly'
keywords: ['mcp', 'ai', 'rules', 'generate checks', 'agents', 'context']
description: 'Use AI agents and coding assistants with Checkly Skills and the Checkly MCP Server.'
sidebarTitle: 'Overview'
keywords: ['mcp', 'ai', 'generate checks', 'agents', 'context']
---

import AgentExamples from "/snippets/agent-example.mdx"
Expand Down Expand Up @@ -44,128 +44,43 @@ Provide the necessary Checkly context and let your AI agent of choice do the res

## Add Checkly context to your AI agent conversation

Install [Checkly Skills](/ai/skills), add [Checkly Rules](/ai/rules), or connect the [Checkly MCP Server](/ai/mcp-server) to give your AI agent enough context to perform Checkly-related tasks.
Install [Checkly Skills](/ai/skills) or connect the [Checkly MCP Server](/ai/mcp-server) to give your AI agent enough context to perform Checkly-related tasks.

<Columns cols={3}>
<Columns cols={2}>
<Card title="Checkly Skills" href="/ai/skills" cta="Get started">
Let your agents pull in all required Checkly context on demand.
For coding agents with repo and code access. Author Monitoring as Code with the Checkly CLI.
</Card>

<Card title="Checkly MCP Server" href="/ai/mcp-server" cta="Connect">
Give your agents live access to Checkly account data and remote actions.
</Card>

<Card title="Checkly Rules" href="/ai/rules" cta="Get started">
Include the entire Checkly context in commands or documentation.
For desktop or sandboxed agents. Live access to Checkly account data and remote actions.
</Card>
</Columns>

### Skills, MCP, and Rules

**Use Skills** when your AI agent supports the [Agent Skills](https://agentskills.io) standard. Skills load context on demand, keeping your agent's context window lean until Checkly-related tasks arise. This is the recommended approach for compatible agents.

**Use the MCP Server** when your agent needs live Checkly data or remote account actions, such as reading check status, inspecting test sessions, triggering existing checks, reading RCA, or managing status page incidents.

**Use Rules** when your agent doesn't support skills or when you want the Checkly context always available. Rules files are loaded at session start and provide consistent context throughout your conversation.


## When to use the Checkly MCP Server

The MCP concept is often used to enable LLMs to interact with external systems. It acts as a bridge between the AI model and the target system, translating natural language commands into actionable API calls or code snippets.

The [Checkly MCP Server](/ai/mcp-server) connects MCP-compatible clients to Checkly over Streamable HTTP. It exposes tools for account context, check status and results, test sessions, result assets, root cause analyses, environment variables, status pages, incidents, and triggering existing checks.

**Use the MCP Server for live Checkly account operations. Use Skills and the Checkly CLI for Monitoring as Code authoring.**

<Tip>
The MCP server runs remotely and cannot access your local filesystem. When you need to create, edit, test, or deploy check code, use [Checkly Skills](/ai/skills) with the [Checkly CLI](/cli/overview).
</Tip>

## Markdown access

Every page in the Checkly documentation is available as markdown. This makes it easy to feed specific documentation pages into AI assistants like Claude, ChatGPT, Cursor, or any other AI tool.

<Tip>
Use [Checkly Skills](/ai/skills) to automatically provide your agent with up-to-date, agent-optimized documentation.
</Tip>

### .md endpoints

Append `.md` to any documentation URL to get the markdown version of that page.

**Example:**

- **HTML:** `https://www.checklyhq.com/docs/what-is-checkly/`
- **Markdown:** `https://www.checklyhq.com/docs/what-is-checkly.md`

The markdown version includes the full page content in plain markdown, code blocks, links preserved as markdown links, and tables formatted as markdown tables.

```bash
# Fetch documentation content with curl
curl https://www.checklyhq.com/docs/what-is-checkly.md

# Pipe directly to your clipboard
curl https://www.checklyhq.com/docs/what-is-checkly.md | pbcopy
```

### Content negotiation

You can also request markdown by setting the `Accept` header to `text/markdown`:

```bash
curl -H "Accept: text/markdown" https://www.checklyhq.com/docs/what-is-checkly/
```

This is useful when integrating with tools or scripts that set request headers programmatically.
### Skills, MCP, and the CLI

<Tip>
Modern coding agents set [these headers automatically when querying documentation](https://www.checklyhq.com/blog/state-of-ai-agent-content-negotation/).
</Tip>
**Use Skills for a CLI-first workflow.** Skills are built for coding agents that have access to your repository and can run commands. The agent edits your Checkly constructs and tests, then uses the [Checkly CLI](/cli/overview) to test and deploy them. Skills load context on demand, keeping your agent's context window lean until Checkly-related tasks arise. This is the recommended approach for agents that support the [Agent Skills](https://agentskills.io) standard.

### Copy as Markdown button

Every documentation page includes a **Copy as Markdown** button at the top of the page. Click it to copy the full page content as markdown to your clipboard.

This is the fastest way to grab documentation for a specific topic and paste it into your AI assistant's context.

```text
Here is the Checkly Browser Checks documentation:

[paste markdown content]

Based on this, how do I set up a browser check with a custom user agent?
```
**Use the MCP Server in desktop or sandboxed environments.** Some agents, like Claude Desktop, ChatGPT, or a sandboxed assistant, can't access your repository or filesystem. The [Checkly MCP Server](/ai/mcp-server) connects these clients to Checkly over Streamable HTTP and gives them live data and remote account actions, such as reading check status, inspecting test sessions, triggering existing checks, reading RCA, or managing status page incidents.

| Use case | Recommended path |
| --- | --- |
| Ask quick, ad hoc questions from a supported client | [MCP Server](/ai/mcp-server) |
| Inspect live Checkly data without local CLI setup | [MCP Server](/ai/mcp-server) |
| Trigger existing deployed checks from chat | [MCP Server](/ai/mcp-server) or [Checkly CLI](/cli/overview) |
| Create or edit check code | [Checkly Skills](/ai/skills) with the [Checkly CLI](/cli/overview) |
| Test, deploy, or automate local Monitoring as Code projects | [Checkly CLI](/cli/overview) |
| Add reusable Checkly best practices to an agent | [Checkly Skills](/ai/skills) |

## LLMs.txt
## Feed documentation to your agent

Every Checkly documentation page is available as markdown, and an `llms.txt` index lists them all. Both make it easy to pull the exact docs your agent needs into its context.

The [llms.txt standard](https://llmstxt.org/) provides a machine-readable index of all available documentation pages. Checkly publishes an `llms.txt` file at [`checklyhq.com/llms.txt`](https://www.checklyhq.com/llms.txt) that lists every documentation page with its markdown URL and a short description.

```txt llms.txt (first 15 lines)
# Checkly Docs

## Docs

- [Changing your email or password in Checkly](https://checklyhq.com/docs/admin/changing-your-email-password.md): Learn how to change your email address or password in your Checkly account
- [Creating an API key in Checkly](https://checklyhq.com/docs/admin/creating-api-key.md): Learn how to create and manage user and service API keys for the Checkly API and CLI
- [Adding team members to your Checkly account](https://checklyhq.com/docs/admin/team-management/adding-team-members.md): Learn how to invite team members to join your Checkly account and manage team collaboration
- [Using Microsoft Entra ID for Single Sign-on in Checkly](https://checklyhq.com/docs/admin/team-management/microsoft-azure-ad.md): This page illustrates the standard procedure to follow in order to get started with Microsoft Entra ID SSO (formerly Azure AD) on Checkly.
- [Multi-Factor Authentication in Checkly](https://checklyhq.com/docs/admin/team-management/multi-factor-authentication.md): Learn how to set up and manage multi-factor authentication for enhanced account security
- [Using Okta for Single Sign-on in Checkly](https://checklyhq.com/docs/admin/team-management/okta.md): This page illustrates the standard procedure to follow in order to get started with Okta SSO on Checkly.
- [Role Based Access Control in Checkly](https://checklyhq.com/docs/admin/team-management/rbac.md): Checkly roles and permissions for team members
- [Removing team members from your Checkly account](https://checklyhq.com/docs/admin/team-management/removing-team-members.md): Learn how to remove team members from your Checkly account and understand how it affects your billing
- [Using SAML for Single Sign-On in Checkly](https://checklyhq.com/docs/admin/team-management/saml-sso.md): Learn how to set up SAML-based SSO for your Checkly account with supported identity providers
- [Using SCIM provisioning in Checkly](https://checklyhq.com/docs/admin/team-management/scim-provisioning.md): Learn how to set up SCIM provisioning for Checkly using your identity provider
- [Team management in Checkly](https://checklyhq.com/docs/admin/team-management.md): Manage your team and collaborate effectively in Checkly
```

Use the `llms.txt` file to crawl and index the entire Checkly documentation. Every link in the file points to [the `.md` version of the page](/ai/markdown-access#md-endpoints), so you can fetch each URL directly to get the markdown content.

```bash
# Fetch the llms.txt index
curl https://www.checklyhq.com/llms.txt
<Columns cols={2}>
<Card title="Markdown Access" href="/ai/markdown-access" cta="Learn more">
Append `.md` to any docs URL, request markdown with content negotiation, or copy a page as markdown.
</Card>

# Fetch a specific page from the index
curl https://checklyhq.com/docs/detect/synthetic-monitoring/browser-checks/overview.md
```
<Card title="llms.txt" href="/ai/llms-txt" cta="Learn more">
A machine-readable index of every documentation page for crawling and indexing.
</Card>
</Columns>
130 changes: 0 additions & 130 deletions ai/rules.mdx

This file was deleted.

2 changes: 1 addition & 1 deletion ai/skills.mdx
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
title: 'Checkly Skills'
description: 'Official Checkly skills to give any AI agent on-demand best practices, context, and product capabilities.'
sidebarTitle: 'Agent Skills'
sidebarTitle: 'Skills'
---

import AgentExamples from "/snippets/agent-example.mdx"
Expand Down
4 changes: 2 additions & 2 deletions cli/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -67,8 +67,8 @@ Checks, Browser Checks and all other constructs.
<Card title="Checkly Skills" href="/ai/skills">
Install Checkly Skills and let AI agents generate Checkly monitoring code for you.
</Card>
<Card title="Checkly Rules" href="/ai/rules">
Include the Checkly Rules in your conversations to generate Checkly monitoring code for you.
<Card title="Checkly MCP Server" href="/ai/mcp-server">
Connect desktop or sandboxed agents to live Checkly account data and actions.
</Card>
</Columns>

Expand Down
30 changes: 20 additions & 10 deletions docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -349,19 +349,25 @@
"group": "AI",
"pages": [
"ai/rocky-ai",
"ai/overview",
{
"group": "MCP Server",
"group": "Agent Resources",
"pages": [
"ai/mcp-server",
"ai/mcp-server/setup",
"ai/mcp-server/tools",
"ai/mcp-server/security-and-permissions",
"ai/mcp-server/troubleshooting"
"ai/overview",
{
"group": "MCP Server",
"pages": [
"ai/mcp-server",
"ai/mcp-server/setup",
"ai/mcp-server/tools",
"ai/mcp-server/security-and-permissions",
"ai/mcp-server/troubleshooting"
]
},
"ai/skills",
"ai/markdown-access",
"ai/llms-txt"
]
},
"ai/skills",
"ai/rules"
}
]
},
{
Expand Down Expand Up @@ -1321,6 +1327,10 @@
}
},
"redirects": [
{
"source": "/ai/rules",
"destination": "/ai/overview"
},
{
"source": "/detect/synthetic-monitoring/api-checks/set-up-and-tear-down",
"destination": "/detect/synthetic-monitoring/api-checks/setup-and-teardown"
Expand Down
Loading