Unofficial practice material

Claude Certified Developer Foundations practice exam.

Take 53 original questions written from Anthropic’s published Developer – Foundations exam guide and weighted by its eight domains, with a third of them on applications and integration: the Claude API, the Agent SDK, Claude Code, evals, model choice, prompting, security, tools and MCP. Some questions ask you to select more than one answer, as the real exam does. Choose study mode or a timed 120-minute attempt. Your results show which domains need more work, and this browser saves your progress. The questions are in English. The test is free and needs no account.

Updated

Unofficial practice material. This test is not authorized or endorsed by Anthropic. The original questions are based on the publicly available Claude Certified Developer – Foundations exam guide.

Like the official CCDV-F, this mock mixes single-answer and multiple-response questions; a multiple-response question scores only when every pick is right. The mock uses its own scoring formula, with no validated correspondence to Anthropic’s exam score.

--:--
Your last attempt
0 —

Claude Certified Developer Foundations

Full Practice Exam · 53 Questions

53Questions
120 minTime limit
720 / 1000Mock threshold
Mixed1 or more correct
Unofficial CCDV-F practice: 53 original questions across all 8 domains, weighted like the official exam guide. 7 of them are multiple response: the question says how many answers to select, and it scores only when every pick is right. The 120-minute limit helps you practise pacing; this tool does not reproduce the official exam or its scoring formula.
Choose a mode
How this works
  • Most questions have one best answer. 7 ask you to select two or three; the question says how many, and it scores only when every pick is right.
  • Navigate freely, flag questions for review, and jump around with the question palette.
  • In study mode nothing is revealed until you press Check answer. Until then you can switch options freely; after checking, the question locks. In exam mode you can change answers until you submit.
  • Answer every item. Unanswered questions are scored as incorrect (as on the real exam).
  • Submit to get this mock’s score (100 to 1000, threshold ≥ 720), a per-domain breakdown, and full explanations.
  • Your progress autosaves in this browser. Shortcuts: A to E or 1 to 5 answer · ←/→ navigate · F flag.
0scaled score
—

—

Your next step

Anthropic registers only people from Claude Partner Network companies. No partner employer? The Certified AI Consultant Program, a collective for consultants who build with AI, registers you through our partner organisation. The certificate is Anthropic’s, the same one partner employees earn.

The pass mark is 720. In the Certified AI Consultant Program you prepare with others and register for the real exam through our partner organisation.

Retake guarantee. Score 720+ here in exam mode and send the result from the email address you pay with: fail the real Developer exam as a member and your next 2 months are free.

  • Access to all four Claude exams + an exam-day pack
  • A full-length practice set for each of the four exams
  • A practice question every weekday
  • Client projects for certified members
  • A full-length set of 53 extra Developer questions + a cheat sheet (12 rules, 8 traps)
  • A practice question every weekday
  • Access to all four Claude exams + an exam-day pack
  • Client projects for certified members

See the program →

One email from contact@szymonpaluch.com. Privacy policy

Performance by domain

Review & explanations

Certified AI Consultant Program

Next: the real exam. Members sit all four Claude exams through our partner organisation.

Prepare with the prep packs, then sit the exam through our partner organisation.

See the program →

This mock uses its own formula: 100 + 900 × (correct ÷ total). Its 720 threshold is a practice reference, not Anthropic’s scoring method or a validated prediction of your official result.

Unofficial practice material. This test is not authorized or endorsed by Anthropic. The original questions are based on the publicly available Claude Certified Developer – Foundations exam guide.

About this mock exam

The CCDV-F mock exam: format, domains and sample questions

The questions in this section come from the same bank as the test above. The domain weights are from Anthropic’s Claude Certified Developer Foundations exam guide (v1.0, July 2026).

Questions
53
Question types
46 single-answer and 7 multiple-response questions
Time limit
120 minutes in exam mode
Threshold
720 out of 1000, a practice reference, not Anthropic’s scoring

Domains and weights

DomainWeight in the exam guideQuestions in this mock
D1 Agents and Workflows14.7%8
D2 Applications and Integration33.1%18
D3 Claude Code3.1%2
D4 Eval, Testing, and Debugging2.6%1
D5 Model Selection and Optimization16.8%9
D6 Prompt and Context Engineering11.0%6
D7 Security and Safety8.1%4
D8 Tools and MCPs10.6%5

Three sample questions

Pick an answer before you open the explanation. Every question in the test above works the same way.

Question 5 · D2 · Applications and Integration

A repository's committed `.claude/settings.json` contains `"permissions": {"deny": ["Bash(terraform apply *)"]}`. A developer, knowing that `.claude/settings.local.json` has higher precedence than the project file, adds `"permissions": {"allow": ["Bash(terraform apply *)"]}` to his local file so Claude Code can apply plans without asking. What happens when Claude next tries to run `terraform apply plan.out` in that repository?

  1. A. It runs without a prompt, because the local file overrides the project file wherever both files set the same settings key.
  2. B. Claude Code asks for confirmation every time, because a conflicting allow and deny pair resolves to ask.
  3. C. It is blocked: permission lists merge across files, and a deny rule from any scope is evaluated before allow rules.
  4. D. It runs only if he starts the session with `--permission-mode bypassPermissions`, which skips project deny rules.
Show the answer

Correct answer: C. C is right: list settings such as permission rules merge across settings files instead of overriding each other. Rules are then evaluated deny first, then ask, then allow, and a tool denied at any level cannot be allowed by another level, so the project's deny blocks the call. A applies key-level precedence to permission rules, which is not how lists combine. B invents a conflict rule; ask applies only when an ask rule matches. D is wrong because deny rules block in every permission mode, including `bypassPermissions`, where allow rules have no effect at all.

Question 1 · D8 · Tools and MCPs

A CRM agent exposes two tools. `find_contacts` takes a `query` string and is described as "Find contacts." `get_contact` takes an `id` string and is described as "Get a contact." Traces show Claude passing customer names to `get_contact`, which returns not-found errors, and calling `find_contacts` when the user already supplied an ID such as `CT-48213`. What change best addresses the root cause?

  1. A. Expand both descriptions: what each tool does, when to prefer it, what its parameter means, what it returns
  2. B. Set `strict: true` on both tools so that every input is validated against its schema before the tool runs
  3. C. Force `get_contact` with `tool_choice` on every turn where the user's message contains any sequence of digits
  4. D. Add one line to the system prompt telling Claude to "always choose the most appropriate tool for each task"
Show the answer

Correct answer: A. A is right: Anthropic calls extremely detailed descriptions by far the most important factor in tool performance. Each should explain what the tool does, when to use it, what each parameter means (for example, that `id` looks like `CT-48213` and comes from `find_contacts`) and what it returns; `input_examples` can also help with format-sensitive inputs. B fails because a customer name is a valid string, so schema validation passes the same wrong calls. C is brittle keyword routing, and forced tool use returns a 400 error on several current models. D is too vague to tell Claude how the two tools differ.

Question 24 · D8 · Tools and MCPs

A platform team runs an agent on the Claude API with the code execution tool enabled, so the agent can use Agent Skills. Which two of these needs are a better fit for a custom Skill than for an MCP server or a custom tool?

  1. A. Look up live stock levels from the internal warehouse REST API while answering a user's question
  2. B. Follow finance's 12-step variance-report procedure, with a bundled Excel template and a check script
  3. C. Post a short message to the team's Slack channel whenever a generated report gets approved
  4. D. Apply legal's clause-review checklist, with a 40-page style guide that is read only on contract tasks
  5. E. Create Jira tickets through one shared integration used from Claude Code, Claude Desktop and this agent
Show the answer

Correct answer: B and D. B and D are right: Skills package procedural knowledge, templates, scripts and reference files that load progressively, with only the name and description in context until a task needs them, so a long style guide or a validation script costs nothing on unrelated work. A and C need calls to external systems, and Skills running on the Claude API have no network access, so those belong in a custom tool or an MCP server. E is the case MCP is designed for: one server exposing the same Jira operations to several hosts, maintained independently of any single application.

Frequently asked questions

Are these Anthropic’s CCDV-F exam questions?

No. This is an independent mock exam with 53 original questions written from Anthropic’s public Claude Certified Developer Foundations exam guide. It is not affiliated with or endorsed by Anthropic, and no question is taken from the exam itself.

What does the CCDV-F exam look like?

Anthropic’s exam guide (v1.0, July 2026) lists 53 multiple-choice and multiple-response questions, a 120-minute time limit and a pass at a scaled score of 720 on a 100 to 1,000 scale.

How are the CCDV-F domains weighted?

The exam guide weights the 8 domains as follows: Agents and Workflows 14.7%; Applications and Integration 33.1%; Claude Code 3.1%; Eval, Testing, and Debugging 2.6%; Model Selection and Optimization 16.8%; Prompt and Context Engineering 11.0%; Security and Safety 8.1%; Tools and MCPs 10.6%. The questions in this mock belong to the same domains, so your results show where to study.

How is the mock scored?

The score is 100 + 900 × the share of correct answers, and 720 is the threshold. The formula is mine, not Anthropic’s, so the result is a practice reference and does not predict your exam score.

Do I need an account or an email address?

No. The test is free and runs in your browser, which saves your progress so you can come back later. Your score and every explanation appear without an email address.

MCP server

Practise CCDV-F inside Claude

Add szymonpaluch.com as a connector in Claude to work through the same 53 questions in chat. You get one question at a time. Pick your answer, then see the correct choice and its explanation. No signup or API key is required.

Server URL
https://szymonpaluch.com/mcp
Claude (web and desktop)
Customize → Connectors → + → Add custom connector, then paste the URL above. The Free plan allows one custom connector.
Claude Code
claude mcp add --transport http szymonpaluch https://szymonpaluch.com/mcp
Then ask
“Give me a CCDV-F practice question from domain 2”, or pick the cca_practice_session prompt and name CCDV-F for a full round with a score at the end.

Questions are in English. The same server can also search and read this blog, list my services, prices and talks, and give you the booking link. It works with any MCP client that supports remote (Streamable HTTP) servers.