You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/codacy-guardrails/codacy-guardrails-faq.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,16 +4,16 @@
4
4
Please have a look at our [documentation](codacy-guardrails-getting-started.md)
5
5
6
6
## Does Guardrails only work with AI-generated code?
7
-
No — while Guardrails does scan and auto-fix AI code as part of the agent flow, it scans any code shown in your IDE in real-time, regardless of how it was written.
7
+
No. While Guardrails does scan and autofix AI code as part of the agent flow, it scans any code shown in your IDE in real-time, regardless of how it was written.
8
8
9
-
## How is Guardrails different from Codacy’s traditional analysis?
9
+
## How's Guardrails different from Codacy’s traditional analysis?
10
10
Guardrails is IDE-first and real-time. It complements Codacy’s platform analysis by catching issues earlier in the development cycle.
11
11
12
12
## Does Guardrails work offline?
13
13
Yes, local scanning via Codacy CLI works offline. API-based features (like querying metrics) require connectivity.
14
14
15
15
## Which AI security and quality standards can I enforce with Guardrails?
16
-
Codacy Guardrails detects and auto-remediates security risks and quality issues in JavaScript, TypeScript, Python, and Java, including:
16
+
Codacy Guardrails detects and autoremediates security risks and quality issues in JavaScript, TypeScript, Python, and Java, including:
17
17
18
18
19
19
- SAST vulnerabilities
@@ -29,7 +29,7 @@ Codacy Guardrails detects and auto-remediates security risks and quality issues
29
29
Configuring and enforcing coding standards at scale across all IDEs in your organization requires a Codacy Team or Business subscription.
30
30
31
31
## Is my data secure?
32
-
Codacy Guardrails is not a large language model, but an IDE extension that uses an MCP Server to communicate with existing AI coding agents owned by the user.
32
+
Codacy Guardrails isn't a large language model, but an IDE extension that uses an MCP Server to communicate with existing AI coding agents owned by the user.
33
33
34
34
## When I change some analysis configuration in the UI, is it automatically applied to Guardrails?
35
35
We're still working on this feature but in order to update the new tool configuration. you should run the command in your repository:
@@ -50,7 +50,7 @@ Check our [Team and Organization plans](https://www.codacy.com/pricing) to unloc
50
50
51
51
52
52
- Central configuration and enforcement of AI coding standards across teams and projects
53
-
- Query and auto-fix existing problems across your codebase from the AI chat panel
53
+
- Query and autofix existing problems across your codebase from the AI chat panel
54
54
- Generate custom security and code quality reports using AI prompts
55
55
- Full access to the Codacy Cloud platform including:
56
56
@@ -65,6 +65,6 @@ Check our [Team and Organization plans](https://www.codacy.com/pricing) to unloc
65
65
Guardrails is supported on MacOS, Linux, and Windows (via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install))
66
66
67
67
## Can I use Guardrails without an AI copilot?
68
-
Codacy Guardrails is designed to be installed from our IDE extension for VS Code, Cursor and Windsurf. but as long as you have an AI code generator that is compatible with the MCP protocol you can also add Guardrails into your MCP configuration manually.
68
+
Codacy Guardrails is designed to be installed from our IDE extension for VS Code, Cursor and Windsurf. but as long as you have an AI code generator that's compatible with the MCP protocol you can also add Guardrails into your MCP configuration manually.
69
69
70
70
Without an AI coding agent, you instead need to use the Codacy IDE extension without the MCP Server.
@@ -191,12 +191,12 @@ Or open the general settings.json file directly, which according to your OS shou
191
191
192
192
Make sure you update the value of `CODACY_ACCOUNT_TOKEN` with your [API token](../codacy-api/api-tokens.md).
193
193
194
-
a. Above the MCP Server configuration in **Settings.json** file, you can Click in the command **Start**
194
+
a. Above the MCP Server configuration in **Settings.json** file, you can Click in the command **Start**
195
195
196
196

197
197
198
-
b. Make sure you have Agent mode enabled: [vscode://settings/chat.agent.enabled](vscode://settings/chat.agent.enabled)
198
+
b. Make sure you have Agent mode enabled: [vscode://settings/chat.agent.enabled](vscode://settings/chat.agent.enabled)
199
199
200
-
c. Open the Copilot chat and switch the mode to `Agent`. You can check that the MCP server was enabled correctly by clicking on the `Select tools` icon, which should list all the available Codacy tools.
200
+
c. Open the Copilot chat and switch the mode to `Agent`. You can check that the MCP server was enabled correctly by clicking on the `Select tools` icon, which should list all the available Codacy tools.
201
201
202
202

Copy file name to clipboardExpand all lines: docs/codacy-guardrails/codacy-guardrails-how-to-configure-rules.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,9 +7,9 @@ However, when an API token is used, Codacy automatically retrieves the current r
7
7
You can configure your rules in one of two ways:
8
8
9
9
10
-
- Using [built-in scanner configuration files](#using-configuration-files) – for version-controlled setups.
10
+
- Using [built-in scanner configuration files](#using-configuration-files)–for version-controlled setups.
11
11
12
-
- Using the [Codacy UI](#using-the-codacy-ui) – for quick, manual adjustments.
12
+
- Using the [Codacy UI](#using-the-codacy-ui)–for quick, manual adjustments.
13
13
14
14
!!! note
15
15
If you're already using a configuration file, please we recommend you can follow the first way. Otherwise, the second way is the best for you, so you can configure directly in the Codacy platform.
@@ -132,5 +132,5 @@ Select the coding standards that you want to follow or stop following and click
Copy file name to clipboardExpand all lines: docs/codacy-guardrails/codacy-guardrails-how-to-use.md
+8-8Lines changed: 8 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
## Write secure, compliant AI code
4
4
5
-
a. Let's run an prompt to create a webserver in Java
5
+
a. Let's run an prompt to create a webserver in Java
6
6
7
7
```text
8
8
Create a lightweight webserver in Java.
@@ -14,15 +14,15 @@ In response, it generated a compact, readable Java class using ServerSocket and
14
14
15
15

16
16
17
-
b. There's a call from MCP tool to analyse the code that was generated. Click in **Run tool**
17
+
b. There's a call from MCP tool to analyse the code that was generated. Click in **Run tool**
18
18
19
-
Codacy Guardrails starts analyzing it automatically using the Codacy CLI embedded in the agent’s flow. No configs, no extra steps – it just works.
19
+
Codacy Guardrails starts analyzing it automatically using the Codacy CLI embedded in the agent’s flow. No configurations, no extra steps–it just works.
20
20
21
-
It found an issue with PMD - the package name is not correctly declared - and it will try to fix that with the right declaration.
21
+
It found an issue with PMD - the package name isn't correctly declared - and it will try to fix that with the right declaration.
22
22
23
23

24
24
25
-
c. After a new analysis, It shows us that it has 0 issues in the code
25
+
c. After a new analysis, It shows us that it has 0 issues in the code
26
26
27
27

28
28
@@ -31,7 +31,7 @@ c. After a new analysis, It shows us that it has 0 issues in the code
31
31
Once your repository is connected to Codacy, you can go beyond traditional static analysis and start interacting with your codebase using simple natural language prompts.
32
32
33
33
34
-
a. Let's run a quick example with the prompt:
34
+
a. Let's run a quick example with the prompt:
35
35
36
36
```text
37
37
Can you list all security issues in my repository?
@@ -40,12 +40,12 @@ Can you list all security issues in my repository?
40
40

41
41
42
42
43
-
b. Right after running this prompt, there is a MCP tool call to search all security issues in my repository. Click in **Run tool**
43
+
b. Right after running this prompt, there is a MCP tool call to search all security issues in my repository. Click in **Run tool**
44
44
45
45

46
46
47
47
It will search for all open security issues in my repository. And it will list all of them, showing the **title**, **priority**, **status** and the **link to the issue**,
48
48
49
49

50
50
51
-
It turned security from a checklist into a dialogue — and that changes everything.
51
+
It turned security from a checklist into a dialogue—and that changes everything.
0 commit comments