Cookie Debugging logo

Cookie Debugging

OrganizationPopular
ChromeDevTools
cookie-debugging

Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party cookie/SameSite/Partitioned cookie warnings.

Overview

PublisherChromeDevTools
Repositorychrome-devtools-mcp
Skill namecookie-debugging
Stars
52.3K
Forks
4.2K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ChromeDevTools on GitHub. Read the source before you install it.

Installation

Install the Cookie Debugging AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ChromeDevTools/chrome-devtools-mcp.git /tmp/chrome-devtools-mcp
mkdir -p .claude/skills
cp -r /tmp/chrome-devtools-mcp/skills/cookie-debugging .claude/skills/cookie-debugging
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cookie Debugging in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cookie Debugging on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cookie Debugging is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Core Concepts

HttpOnly vs Client-Side Storage

Cookies marked HttpOnly cannot be accessed or modified by client-side JavaScript (cookieStore or document.cookie). However, the browser automatically attaches active HttpOnly cookies to outgoing HTTP request headers (Cookie).

  • To inspect current HttpOnly values: Look at the Cookie request header of any outgoing HTTP request via get_network_request.
  • To inspect how cookies were created or configured: Look at the Set-Cookie response header of login/auth responses.
  • To inspect non-HttpOnly cookies: Use evaluate_script with the modern cookieStore API (async () => await cookieStore.getAll()).

Session Strategy: Live Tab vs Isolated Context

Choose the right session environment to avoid state contamination (e.g., residual analytics or auth tokens):

StrategyWhen to UseSetup / Teardown
Live Tab (Active Page)Diagnosing an active user session, live 401/403 error, or current state.Operates directly on the currently selected page.
Clean-Slate (isolatedContext)Testing cookie consent banners, first-time visits, or zero-cookie guarantees.Call new_page with a unique isolatedContext (e.g. "consent-audit-1"). When finished, call close_page.

Client-Side Capabilities & Limitations

ActionClient JavaScript (cookieStore / document.cookie)DevTools Network & Context Tools
Read Non-HttpOnlyasync () => await cookieStore.getAll()get_network_request (Request Cookie)
Read HttpOnly❌ Blocked by browser securityget_network_request (Request Cookie)
Inspect Attributes (Domain, Path, SameSite, Expires)async () => await cookieStore.getAll()get_network_request (Response Set-Cookie)
Modify / Delete Non-HttpOnlyasync () => await cookieStore.set(...)N/A
Modify / Delete HttpOnlySilent failure in JavaScript✅ Use new_page(isolatedContext: ...) for clean state

[!WARNING] Attempting to clear an HttpOnly cookie via JavaScript (cookieStore.delete or document.cookie = "...; max-age=0") will silently fail. To test in an unauthenticated or fresh state, always spawn a new isolated context using new_page with isolatedContext.


Workflow Patterns

1. Diagnosing Authentication Failures & Redirects (401 / 403)

When an authenticated page request fails, returns 401/403, or redirects to login:

  1. List Recent Requests: Call list_network_requests with includePreservedRequests: true.
  2. Find the Target Request: Locate the failing request (401/403) or redirect (302/307).
  3. Inspect Outgoing Cookie Header: Call get_network_request with the reqid.
    • Verify if the Cookie header was attached and whether required tokens (e.g. SESSION_ID, auth_token) were sent.
  4. Trigger Active Inspection (If no recent request exists):
    • If the cookie was set in a previous session and no network call is listed, trigger a request:
      • Use navigate_page with reload: true, OR
      • Call evaluate_script with () => fetch(window.location.href)
    • Then call get_network_request on the new request to inspect the active Cookie header.
  5. Trace the Setting Request: If the cookie is missing or rejected:
    • Check earlier login/handshake responses for Set-Cookie directives:
      • Path mismatch: e.g., Path=/api when the request is to /.
      • Domain mismatch: e.g., Domain=api.example.com preventing cookies on sub.example.com.
      • Secure flag on HTTP: Secure cookies are never sent over unencrypted http://.
      • SameSite blocking: SameSite=Strict cookies are omitted on cross-site navigations.
      • Expiration: Check if Expires or Max-Age elapsed.

2. Cookie Banner & Consent Conformance Testing

To verify that no non-essential or tracking cookies are set before consent or when declining:

  1. Start Clean: Open a fresh isolated context with a dedicated name:
    json
    {"url": "<PAGE_URL>", "isolatedContext": "consent-test-1"}
  2. Record Baseline Cookies: Before interacting with the banner, run evaluate_script with async () => await cookieStore.getAll().
  3. Inspect Premature Network Requests & Issues:
    • Call list_network_requests to ensure no third-party tracking beacons fired before consent.
    • Call list_console_messages with types: ["issue"] to check for tracking warnings.
  4. Interact with Consent Banner:
    • Capture snapshot with take_snapshot to locate the "Decline" or "Reject All" button uid.
    • Click the button with click.
  5. Verify Cookie Difference:
    • Run evaluate_script with async () => await cookieStore.getAll() after clicking to assert that only strictly necessary or consent-state cookies exist.
  6. Test Consent Revocation (Lifecycle Audit):
    • When auditing consent withdrawal or preference changes:
      • Locate and click the "Cookie Settings", "Manage Preferences", or footer privacy trigger (take_snapshot $\rightarrow$ click).
      • Deselect non-essential categories or click "Revoke All" / "Save Preferences".
      • Re-query cookieStore.getAll() to verify previously accepted non-essential cookies were cleared or expired.
      • Call list_network_requests on subsequent actions to ensure tracking beacons are no longer fired.
  7. Teardown Context: Call close_page when the audit is complete to prevent leftover cookies from affecting subsequent tasks.

3. Auditing Cookie Security, SameSite & CHIPS (Partitioned Cookies)

  1. Fast-Track: Native DevTools Issues (Recommended):
    • Call list_console_messages with:
      json
      {
        "types": ["issue"],
        "includePreservedMessages": true
      }
    • Check for CookieIssue entries, such as:
      • SameSiteNoneInsecure: SameSite=None without Secure.
      • ThirdPartyCookiePhaseout: Third-party cookie blocked or restricted.
      • SchemefulSameSite: Cross-scheme cookie issues.
      • PartitionedCookies: Invalid CHIPS partitioning attributes.
  2. Deep Audit: Lighthouse Third-Party Cookies:
    • Run lighthouse_audit with mode: "navigation" and outputDirPath: "/tmp/lh-report".
    • Extract the specific cookie audit without loading the full report into context:
      bash
      node -e "const r=require('/tmp/lh-report/report.json'); const a=r.audits['third-party-cookies']; console.log(JSON.stringify({score: a?.score, displayValue: a?.displayValue, items: a?.details?.items}))"

4. Client-Side Cookie Inspection & Manipulation

For client-accessible, non-HttpOnly cookies (e.g., UI preferences, non-sensitive feature flags):

  1. Read Cookies & Attributes:
    • Use the modern asynchronous Cookie Store API:
      js
      async () => await cookieStore.getAll();
    • Fallback for insecure HTTP origins: () => document.cookie.
  2. Set / Modify Cookie:
    • Set client cookie via cookieStore:
      js
      async () =>
        await cookieStore.set({
          name: 'theme',
          value: 'dark',
          expires: Date.now() + 86400000,
          sameSite: 'lax',
        });
  3. Delete Cookie:
    • Clear client cookie:
      js
      async () => await cookieStore.delete('theme');

Troubleshooting

  • cookieStore is undefined: cookieStore requires a Secure Context (https://, localhost, or 127.0.0.1). On non-secure HTTP origins, use () => document.cookie or test over HTTPS.
  • evaluate_script returns empty / unresolved Promise: cookieStore methods are asynchronous. Always wrap calls with async () => await cookieStore.getAll().
  • Cookie not visible in JavaScript: The cookie is marked HttpOnly. Trigger a network request and call get_network_request to view it in the Cookie request header.
  • JavaScript deletion did not remove cookie: The cookie is HttpOnly or requires matching Path and Domain parameters. Use a fresh isolatedContext with new_page for a clean slate.
  • Cookie set in response but not sent in requests:
    • Verify if page is http:// while cookie specifies Secure.
    • Check if Domain restricts subdomains.
    • Check list_console_messages(types: ["issue"]) for browser rejection reasons.
  • Residual cookies contaminating audits: Always use new_page with a unique isolatedContext when running compliance tests, and call close_page when done.

Frequently asked questions

What does the Cookie Debugging AI skill do?

Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party cookie/SameSite/Partitioned cookie warnings.

Why use Cookie Debugging on TypingMind?

Because you install it once and use it with any model. Cookie Debugging is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cookie Debugging in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ChromeDevTools/chrome-devtools-mcp/tree/main/skills/cookie-debugging. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cookie Debugging?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cookie Debugging?

As many as you like. As long as a model supports skills, you can use Cookie Debugging with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cookie Debugging AI skill free?

Yes. It is published on GitHub by ChromeDevTools under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇