AgentDrives

ReqRes

reqres.in

ReqRes is a hosted mock backend and test sandbox for developers and AI agents.

Can an AI agent use ReqRes? Yes, without signing up. Our agent got into ReqRes on its own in 3 minutes and did 7 of its 8 core tasks.

Visit ReqRes Follow changes

Category

API testing and mocking

Connects by

MCP, API

Agent payments

None found

Driven 26 Oct 2026

From finding it to leaving

What an agent managed without a person, at each step.

  1. Find

    On its own

    Docs it can act on: llms.txt, an OpenAPI and an MCP server.

    9 doc pages read

  2. Get in

    On its own

    Got in without signing up. Sign-up by API: stopped by robots.txt; Email and password: stopped by a CAPTCHA.

    3 minutes

  3. Use

    On its own

    Did: create collections and create, update, list and delete records, each read back; read seeded users and orders from the sandbox with no key.

    7 of 8 core tasks

  4. Pay

    Not reached

    Paying needs an account.

  5. Leave

    On its own

    Nothing to cancel, deletes what it made.

Getting in

3 of 6 ways in worked without a person.

How agents get past bot checks

The way that worked

No key needed3 minutes

  • An inboxNot needed
  • A browserNot needed
  • A personNot needed
  • Agent on a serverAPI, MCP, CLIPartlyWithout an account (no key needed) it gets an API key, makes its first API call and does 7 of its 8 core tasks. Payment wasn't tried.
  • Assistant in its own browserLike ChatGPT agentNoSigning up needs a person: it asks for a bot check.
  • Signed agentNot checkedNot checked: its robots.txt asks crawlers to stay off the sign-up page.

Every way in

Way inWhat happenedWhy
No key neededWorked
Runs locally, no accountWorked
Try first, claim laterWorked
Sign-up by APIStopped by robots.txt
Email and passwordStopped by a CAPTCHA
Company single sign-onNot triedNeeds a person's account
  • Crawlersrobots.txt asks crawlers to stay off sign-up and the API. Nothing to fix. It keeps these pages out of search and doesn't stop agents signing up.

What an agent can do with ReqRes

7 of 8 core tasks done, and 3 of 15 others. One task not tried isn't counted.

Core tasks

  • done there
  • tried, not done
  • offered, not tried
TaskResultThrough
Create a project (hosted backend)DoneAPIMCP
Create a collectionDoneAPIMCP
Create or update a record in a collectionDoneAPIMCP
List and read records with filtersDoneAPIMCP
List deterministic agent sandbox fixture data (users, orders)DoneAPI
Trigger a deliberate failure scenarioDoneAPI
Simulate a payment (create, confirm, decline, refund)DoneAPI
Run a scripted multi-step failure chainPartlyAPI
Read demo fixture users with no signup or keyBlockedAPI

  • Reliability

    90of 100

    Core tasks that worked on all 3 runs

  • Handles mistakes

    80of 100

    Clear errors, retries without duplicates, honest limits

  • Surface tested

    31of 100

    Documented routes, tools and commands run and checked

  • Docs accuracy

    93of 100

    Documented operations that behaved as the docs say

  • Docs completeness

    47of 100

    How fully the docs describe each operation

  • What it can't do, and why

    • Use the REST API, including the keyless demo users Robots.txt closes /api/ to AI agents.
    • Make a dashboard account A visible Cloudflare Turnstile on the sign-up form.
    • Filter records, change collections or delete a project Only offered over the closed REST API; MCP has no tool.
    • Run chains, trajectories, webhooks and 12 of 15 scenarios They need the $49/mo agent key.
    • Pay for a plan Plans are bought in the dashboard, which needs an account.
    • Create or revoke API keys Keys are managed only in the dashboard.

3 of 15 other tasks done

  • Read a keyless demo trajectory (sample benchmark run)Done
  • Download a scenario pack (chains, seeds, expected trajectories)Done
  • Complete an MFA challenge in the agent sandbox auth flowDone
  • Register a webhook on a sandbox payment eventPaid plan
  • List trajectories recorded from agent sandbox callsPaid plan
  • Diff two trajectories for divergencePaid plan
  • Register and log in a demo userBlocked
  • Authenticate an app's end users via magic-link loginBlocked
  • Manage app users (create, update, delete)Blocked
  • Execute a custom endpoint with a user-defined responseBlocked
  • Run automations on collection data changesBlocked
  • Browse collections and inspect request logs (Data Explorer)Blocked
  • Export stored objects from the Data ExplorerBlocked
  • Generate an API from a UI screenshot (Image to API)Blocked
  • Create and manage API keys with scoped permissionsBlocked
  • Run the sandbox offline via a self-hosted Docker imageBlocked
  • License ReqRes for commercial/company-wide useNot tried
  • Sponsor a placement on the siteNot tried

The plans they need

  • Run a scripted multi-step failure chainAgent Developer ($49/mo)
  • List trajectoriesAgent Developer ($49/mo)
  • Diff two trajectoriesAgent Developer ($49/mo)
  • Register a payments webhookAgent Developer / Agent Platform
  • 12 of 15 failure scenariosAgent Developer ($49/mo)

Paid-plan tasks don't count toward the level. The drive used the free plan (no-account MCP project and keyless sandbox).

Surface audit: 87 documented operations, 29 run, 27 passed, 2 not as documented, 58 blocked (sandbox or plan limits).

How an agent connects

MCP, API, OpenAPI and llms.txt found.

The standards

  • MCP server

    All tested

    Official server. 7 tools, no auth.

    reqres.in/mcp

    In the MCP registry as in.reqres/reqres.

    7 tools across its docs

    7 tools listed without signing in

  • API

    20 tested

    REST, 64 operations in openapi.json; /api/ closed to AI agents by robots.txt.

    75 operations across its docs

  • OpenAPI

    Yes

    3.0.3; payments sandbox routes missing.

  • CLI

    None found

  • SDK

    None found

  • llms.txt

    Yes

    reqres.in/llms.txt

  • Agent payments

    None found

    The checkout wasn't reached: Lite, $5 a month.

  • Docs

    Some gaps

    Covers getting started, auth, error codes and code examples.

    7 of 13 documented ways to do the core work worked when tried.

    9 pages read

MCP tools

  • create_project
  • list_collections
  • create_collection
  • list_records
  • create_record
  • update_record
  • delete_record

Read without signing in on 31 Oct 2026

Tips for agent builders

From this drive

8 tips
  1. Use the MCP server at https://reqres.in/mcp (no auth): create_project returns the keys; pass the manage key as the api_key argument of every tool.
  2. Wrap fields in {"data": {...}} only on REST; MCP create_record takes the fields in data directly.
  3. For error-handling tests call /agent/v1/scenarios/rate-limited, validation-error and malformed-json; filter on the X-Agent-Sandbox-Intentional header.
  4. Agent sandbox calls are byte-deterministic at a given seed and X-World-Version: pin both in assertions.
  5. Payments sandbox: send an Idempotency-Key on every POST; attach a payment method with POST /sim/payments/v1/payment_intents/{id} before /confirm.
  6. The free agent sandbox allows 100 calls a day per IP; check /agent/v1/health for remaining_today.
  7. On x86-64 the self-hosted image has no amd64 build: its app is plain Node (Cmd node selfhosted/server.js in /app, no native modules), so the unpacked layers run with a local node and PORT set; without DATABASE_URL chains and trajectories fail.
  8. For scripted failure chains without a paid key, run the self-hosted image's app (node selfhosted/server.js) and send X-Agent-Chain: flaky-then-recover with an X-Agent-Run-Id; reset with DELETE /agent/v1/chains/{name}/state.

For the team behind ReqRes

Our agent didn't reach Pay. Prove ReqRes is yours, then see where each issue is, read your safety findings and ask for a free drive after a fix. How to fix each one comes with the Audit.

8 things to fix for agents

Agent blockers: 2 foundAgent surfaces: 10 issues foundSafety review: 2 issues found

  1. FindClear
  2. Get inClear
  3. UseClear
  4. PayNot reached
  5. LeaveClear

Claim ReqRes, freeWhat a drive covers

Where ReqRes fits

Category
Tasks
Vendors
Standards
Steps

Every earlier drive is in the history. Data under CC BY 4.0.

JSONMarkdownAtomJSON Feed

Found an error? or read how corrections work.

Questions people ask about ReqRes

Can an AI agent sign up for ReqRes on its own?
Our agent got into ReqRes without signing up. Its ways in: No key needed, in 3 min; Runs locally, no account, in 4 min; Try first, claim later, in 2 min.
Does ReqRes have an MCP server, and can an agent connect to it?
Yes. ReqRes has an official MCP server. The server lists 7 tools. A new agent can get in on its own: in the drive of 26 Oct 2026, our agent got working access without signing up. Through the MCP server, 4 of our agent's 4 attempts worked.
How does an AI agent get a ReqRes API key?
In the drive of 26 Oct 2026, our agent got its ReqRes API key over the API, without a browser or a person. No API to create, rotate or revoke keys: dashboard only.
Can an AI agent delete its ReqRes account?
Not applicable: our agent used ReqRes without an account, and it deletes what it made.

Cite this page

The page as a reference, in plain text, APA and BibTeX.

Cite this
Plain
AgentDrives, “ReqRes: AI agent test drive”, 26 October 2026, https://agentdrives.com/tools/reqres. CC BY 4.0.
APA
AgentDrives. (2026, October 26). ReqRes: AI agent test drive. https://agentdrives.com/tools/reqres
BibTeX
@misc{agentdrives_reqres_2026,
  author = {{AgentDrives}},
  title = {ReqRes: AI agent test drive},
  year = {2026},
  month = oct,
  url = {https://agentdrives.com/tools/reqres},
  note = {Agent test drive, CC BY 4.0},
}

Something wrong on this page?

Tell us what's wrong. We check it against the drive and correct the page, with the date.