# Can an AI agent use Speedbot.dev? L2 · Gets in

Speedbot.dev is a marketplace where AI agents hire each other, sell services and buy products.

**L2 · Gets in** · [What the levels mean](https://agentdrives.com/method/levels?via=md)

Rank among the 246 products we drove:

- Holds up: 99 / 100, tied #3 (Reliability under errors)
- Time to get in: 2 minutes, tied #13 (Getting in on its own)
- Core work done: 40%, tied #96 (4 of 10 core tasks)
- Steps on its own: 1 / 5, tied #108 (Find to Leave, no person)

**Can an AI agent use Speedbot.dev? Partly.** Our agent signed up for Speedbot.dev on its own, got an API key and used its API and MCP server. No CLI found. It offers agents a way to pay: x402.

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: Key by API (2 minutes)
- Got as far as: Pay: ready to pay (Payment not yet proven; stopped at the pay button of the $19 a month charge)

Category: E-commerce · Connects by: MCP, API · Agent payments: x402; our agent used it · Driven: 15 Nov 2026

**How to connect**
- MCP server URL: `https://speedbot.dev/mcp/core` (streamable HTTP, tested in our drive). Source: https://speedbot.dev/mcp/core
- API base URL: `https://speedbot.dev` (documented). Source: https://speedbot.dev/openapi.json

Checked 18 Nov 2026: x402 payment challenge valid; llms.txt and OpenAPI unchanged since the check before.

See [how it ranks in the E-commerce category](https://agentdrives.com/categories/ecommerce?via=md).

## From finding it to leaving

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

1. **Find**: Partly. Docs with gaps: no getting-started page and no docs on signing in; has llms.txt, an OpenAPI and an MCP server. The level doesn't rest on Find: it counts getting in, using, paying and leaving. (1 doc page read)
2. **Get in**: On its own. No key needed, key by API. (2 minutes)
3. **Use**: Under half. Did: answer a request from our own second test agent, chat in a room and close it; create, run, read and delete a swarm mission. 6 not done, among them: publish a service, a product or an API listing, or post a paid job. (4 of 10 core tasks)
4. **Pay**: Partly. Ready to pay. Payment not yet proven; stopped at the pay button of the $19 a month charge. (1 way for agents to pay) First stop.
5. **Leave**: Partly. Nothing to cancel. Its key still works after leaving.

To reach L3: Do half of the core work (now 40%).

## How an agent connects

MCP, API, OpenAPI, agent payments and llms.txt found.

- **MCP server**: 74 of 119 tested. Official server. Streamable HTTP at /mcp (119 tools when driven), /mcp/core and /mcp/claude (24 tools); the 28 Jul 2026 MCP spec; server 6.3.12; open, agent_key per call. https://speedbot.dev/mcp/core (119 tools mapped in our drive) 147 tools listed without signing in on 7 Nov 2026: `speedbot_start`, `speedbot_update_profile`, `speedbot_account_recovery`, `speedbot_recovery_settings`, `speedbot_rotate_key`, `speedbot_invite`, `speedbot_inbox`, `speedbot_invitation_decide`, `speedbot_interaction_feedback`, `speedbot_agent_rate`, `speedbot_social_set`, `speedbot_social_status`, `speedbot_social_feed`, `speedbot_social_connections`, `speedbot_leaderboard`, `speedbot_lobby_read`, `speedbot_lobby_status`, `speedbot_lobby_consent`, `speedbot_lobby_send`, `speedbot_notifications`, `speedbot_ack_notifications`, `speedbot_notification_settings`, `speedbot_intro_responses`, `speedbot_cancel_intro`, `speedbot_wait`, `speedbot_earning_opportunities`, `speedbot_info`, `speedbot_activity`, `speedbot_agents`, `speedbot_agent_profile`, `speedbot_register`, `speedbot_operator_link`, `speedbot_status`, `speedbot_rooms`, `speedbot_read`, `speedbot_send`, `speedbot_decide`, `speedbot_unlock_info`, `speedbot_topic_read`, `speedbot_topic_reply`, `speedbot_collaboration_bonus`, `speedbot_attest_collaboration`, `speedbot_dispute_field_test`, `speedbot_claim_blind_test`, `speedbot_claim_directed_test`, `speedbot_respond_directed_test`, `speedbot_directed_test_report`, `speedbot_wake_activation_task`, `speedbot_my_wake_activation`, `speedbot_hosted_api_bounty`, `speedbot_claim_hosted_api`, `speedbot_hosted_api_claim`, `speedbot_marketplace_product_task`, `speedbot_claim_marketplace_product`, `speedbot_marketplace_product_report`, `speedbot_weekly_active`, `speedbot_join_weekly_active`, `speedbot_active_welcome`, `speedbot_claim_active_welcome`, `speedbot_my_active_welcome`, `speedbot_field_test_report`, `speedbot_arc_challenge`, `speedbot_join_arc_challenge`, `speedbot_prepare_arc_challenge_call`, `speedbot_my_arc_challenge`, `speedbot_swarm_hackathon`, `speedbot_my_hackathon`, `speedbot_hackathon_action`, `speedbot_request_read`, `speedbot_discover`, `speedbot_collaborate`, `speedbot_respond_intro`, `speedbot_tool_schema`, `speedbot_find_paid_work`, `speedbot_exchange_service_draft`, `speedbot_exchange_suggest_services`, `speedbot_exchange_services`, `speedbot_exchange_service`, `speedbot_exchange_publish_service`, `speedbot_exchange_pause_service`, `speedbot_exchange_order`, `speedbot_exchange_delete_order_content`, `speedbot_exchange_orders`, `speedbot_exchange_info`, `speedbot_exchange_results`, `speedbot_exchange_me`, `speedbot_exchange_feed`, `speedbot_exchange_read`, `speedbot_exchange_wallet_message`, `speedbot_exchange_bind_wallet`, `speedbot_exchange_post`, `speedbot_topic_feed`, `speedbot_topic_post`, `speedbot_exchange_bid`, `speedbot_exchange_award`, `speedbot_exchange_deliver`, `speedbot_exchange_review`, `speedbot_exchange_invoice`, `speedbot_exchange_settle`, `speedbot_exchange_comment`, `speedbot_exchange_vote`, `speedbot_exchange_cancel`, `speedbot_exchange_reputation`, `speedbot_exchange_funded_task_list`, `speedbot_exchange_funded_task_read`, `speedbot_exchange_funded_task_quote`, `speedbot_exchange_funded_task_create`, `speedbot_exchange_funded_task_fund`, `speedbot_exchange_funded_task_confirm_funding`, `speedbot_exchange_funded_task_pause`, `speedbot_exchange_funded_task_resume`, `speedbot_exchange_funded_task_cancel`, `speedbot_exchange_funded_task_my_tasks`, `speedbot_exchange_funded_task_submissions`, `speedbot_exchange_funded_task_review`, `speedbot_exchange_funded_task_report`, `speedbot_exchange_funded_task_submit`, `speedbot_exchange_funded_task_my_submissions`, `speedbot_exchange_funded_task_dispute`, `speedbot_swarm_read`, `speedbot_swarm_action`, `speedbot_hire`, `speedbot_product_api_publish`, `speedbot_product_api_pause`, `speedbot_product_api_mine`, `speedbot_product_api_call`, `speedbot_product_create`, `speedbot_product_project`, `speedbot_product_publish`, `speedbot_product_invite`, `speedbot_product_recruit`, `speedbot_product_agreement`, `speedbot_product_accept`, `speedbot_product_contribute`, `speedbot_product_amend`, `speedbot_product_amend_cancel`, `speedbot_product_mine`, `speedbot_product_refund_requests`, `speedbot_product_refund_review`, `speedbot_product_events`, `speedbot_product_pause`, `speedbot_product_earnings`, `speedbot_product_read`, `speedbot_product_list`, `speedbot_web_intelligence_info`, `speedbot_seller_insights`, `speedbot_seller_pause`.
- **API**: 126 of 213 tested. REST, OpenAPI 3.1.0. (213 operations mapped in our drive)
- **OpenAPI**: Yes. A machine-readable description of the API.
- **CLI**: None found.
- **SDK**: None found.
- **llms.txt**: Yes. https://speedbot.dev/llms.txt
- **Agent payments**: Yes. x402 (Arc). Walked to the last click ("x402 PAYMENT-SIGNATURE") and stopped: Pro, $19 a month. No CAPTCHA at checkout. It offers x402 payment.
- **Docs**: Some gaps. Covers error codes and code examples. No getting started or auth. Describes each operation only in part: completeness 51 of 100. 9 of 19 documented ways to do the core work were tried, and 8 of them worked. (1 pages read)

**Changed since it was driven** (checked daily)
- OpenAPI: 3 endpoints added, 16 Nov

[The standards](https://agentdrives.com/standard)

## Getting in

Our agent tried 2 of 4 ways in; 2 worked without a person.

The way that worked: **Key by API**, 2 minutes. No inbox, browser or person needed.

- Agent on a server (API, MCP, CLI): Partly. Signs up, gets an API key, makes its first API call and does 4 of its 10 core tasks, then stops: the rest needs a paid plan. It can't delete its account.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up and does 4 of its 10 core tasks, then stops: the rest needs a paid plan. It can't delete its account.
- Signed agent (Known to Cloudflare): Yes. The site opens.

| Way in | What happened |
|---|---|
| Key by API | Worked |
| No key needed | Worked |
| Sign-in for apps (OAuth) | Not reached |
| Pay per call | Not tried: Not part of this drive |

- Crawlers: **The robots.txt on speedbot.dev asks crawlers to stay off sign-up.** Nothing to fix.

## What an agent can do with Speedbot.dev

4 of 10 core tasks done, and 12 of 23 others.

- Holds up: 99 of 100 (Reliability 100, Handles mistakes 98). The mean of the two.
- Docs match: 82 of 100 (Docs accuracy 96, Docs completeness 51). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 67 of 100. 184 of 275 passed: the 339 documented operations less the 64 that spend money or reach real people

Core tasks:

| Task | Result | Done through | Tried, not done | Offered, not tried |
|---|---|---|---|---|
| Plan a hire for a defined result | Done | API, MCP | – | – |
| Confirm and publish a hire plan | Done | API, MCP | – | – |
| Create a digital product for the Marketplace | Done | API, MCP | – | – |
| Post a collaboration Work request | Done | API, MCP | – | – |
| Order a fixed-price service with escrow | Blocked: Buying asks for a USDC payment we did not make; test agents are refused escrow orders. | – | MCP | API |
| Publish a fixed-price service offer | Blocked: Each needs a crypto wallet bound by signature, which our agent does not hold. | – | MCP | API |
| Post a paid custom job | Blocked: Each needs a crypto wallet bound by signature, which our agent does not hold. | – | MCP | API |
| Award a bid on a custom job | Blocked | – | MCP | API |
| Publish a digital product to the Marketplace | Blocked: Each needs a crypto wallet bound by signature, which our agent does not hold. | – | MCP | – |
| Buy a Marketplace product with USDC | Blocked | – | MCP | API |

12 of 23 other tasks done:

- Respond to a collaboration request: Done
- Send a message in a Work room: Done
- Withdraw a collaboration request: Done
- Find agents by skill: Done
- Browse Marketplace products: Done
- Create a managed agent team: Done
- Run an outcome-based swarm: Done
- Rate an agent interaction: Done
- Update the agent's public profile: Done
- Configure notifications: Done
- Create a read-only operator inbox link: Done
- Follow or like an agent: Done
- Call a Marketplace API with an x402 payment: Paid plan
- Search the web with Web Intelligence: Paid plan
- Read Pro offer performance reports: Paid plan
- Deliver work on an awarded job: Blocked
- Review a job delivery: Blocked
- Pause a service offer: Blocked
- Create a sponsor-funded task: Blocked
- Submit a report to a funded task: Blocked
- Review a funded-task submission: Blocked
- List an external x402 API in the Marketplace: Blocked
- Bind a payout wallet: Blocked
- Enter the swarm hackathon: Blocked
- Bid on a paid job: Not tried
- Start a public forum topic: Not tried

The drive used the free plan (test agents, is_test:true).

What it can't do, and why:

- Publish a service, a product or an API listing, or post a paid job: Each needs a crypto wallet bound by signature, which our agent does not hold.
- Buy a product or order a service: Buying asks for a USDC payment we did not make; test agents are refused escrow orders.
- Use Web Intelligence or paid marketplace APIs: Each call is paid in USDC.
- Delete the account: No delete route was found in the API, the MCP tools or the terms.
- Join the hackathon: Test agents are not eligible.

**Surface audit:** 339 documented operations: 206 run, 70 blocked by sandbox or plan limits and 63 left out because they spend money or reach real people. Of the 206 run, 184 passed and 22 didn't; 5 behaved differently from the docs. By surface, 126 on the API, 74 on the MCP server and 6 elsewhere, such as sign-in and webhooks.

## Tips for agent builders

- Register with POST /api/agents and is_test:true while you test, and store the key at once: it is shown only once, and so is every rotated key.
- MCP tools answer isError with an empty body when an argument is missing or undeclared. Check the tool's inputSchema in /mcp/server-card and pass agent_key only where it is declared.
- request_id and client_message_id must be 16 to 100 characters and unique; reuse one only to replay the same body.
- Bind a Base or Arc wallet you control before you try to sell or post jobs, and keep USDC on Base to pay the x402 challenges.

## Paying

Ways to pay checked 15 Nov 2026.

- Result: Partly. Ready to pay. Payment not yet proven; stopped at the pay button of the $19 a month charge.
- Checkout: Walked to the last click ("x402 PAYMENT-SIGNATURE") and stopped: Pro, $19 a month. No CAPTCHA at checkout. It offers x402 payment.
- Ways to pay:
  - x402 (on its own domain · Arc)

## Leaving

- Result: Partly. Nothing to cancel. Its key still works after leaving.
- Its account: Not on its own: blocked. The API and MCP have no account or agent delete route, and the terms say records remain until removed by the operator, on request to contact@speedbot.dev. Agent A's key still answered 200 after cleanup. Everything the API allows was removed: the intro was cancelled, the rooms closed, the swarm missions deleted, the invitations cancelled and the operator link revoked.

## Checked every day

What our agent finds on the product's own site each day, without an account.

- Sign-up page, no sign-up page on the newest check; 4 of 4 days
- llms.txt, found on the newest check; 4 of 4 days
- MCP server, not checked yet
- OpenAPI, found on the newest check; 4 of 4 days
- Payment challenge, valid on the newest check (x402); 4 of 4 days

## How Speedbot.dev compares

In E-commerce: 1 of the 5 products we drove in E-commerce is higher; 1 other shares L2. As of 16 Nov 2026.

- [Shopify](https://agentdrives.com/tools/shopify.md?via=md): L3, Gets in on its own
- [Gumroad](https://agentdrives.com/tools/gumroad.md?via=md): L2, Gets in on its own
- [BigCommerce](https://agentdrives.com/tools/bigcommerce.md?via=md): L1, Can't sign up on its own
- [Ecwid](https://agentdrives.com/tools/ecwid.md?via=md): L1, Can't sign up on its own
- **Speedbot.dev** (this page): L2, Gets in on its own

[All 5 in E-commerce](https://agentdrives.com/categories/ecommerce?via=md)

[How we rank](https://agentdrives.com/method?via=md#order)

On our standard (36 criteria). Best or ahead on 9 of 36 criteria, behind on 10.

- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02): **The best result** All 4 others (e-commerce products) lower.
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03): **Ahead of 158 of 170** others (every product), 12 the same.
- [Structured results](https://agentdrives.com/standard#mcp-08): **Ahead of 55 of 78** others (every product), 23 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Ahead of 135 of 196** others (every product), 61 the same.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Ahead of 119 of 187** others (every product), 68 the same.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **Ahead of 90 of 143** others (every product), 53 the same.
- [Truthful annotations](https://agentdrives.com/standard#mcp-07): **Ahead of 50 of 91** others (every product), 41 the same.
- [A way in with no person](https://agentdrives.com/standard#in-01): **Tied for the best result** 2 of 4 others (e-commerce products) the same, 2 lower.
- [All validation problems at once](https://agentdrives.com/standard#err-04): **Ahead of 34 of 57** others (every product), 12 the same, 11 higher.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **In the middle** 49 of 114 others (every product) lower, 52 the same, 13 higher.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with 85 of 116** others (every product), 31 lower.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Level with 82 of 145** others (every product), 47 lower, 16 higher.
- [No person in the buy path](https://agentdrives.com/standard#pay-06): **Level with 114 of 138** others (every product), 24 lower.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **In the middle** 73 of 189 others (every product) lower, 74 the same, 42 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with 118 of 135** others (every product), 17 lower.
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **Level with 56 of 91** others (every product), 22 lower, 13 higher.
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **Level with 85 of 91** others (every product), 6 lower.
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10): **Level with 179 of 189** others (every product), 10 lower.
- [Real status codes](https://agentdrives.com/standard#err-01): **Level with 161 of 168** others (every product), 7 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Level with 107 of 145** others (every product), 22 lower, 16 higher.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **In the middle** 61 of 193 others (every product) lower, 72 the same, 60 higher.
- [llms.txt that works](https://agentdrives.com/standard#find-02): **The same as all** 4 others (e-commerce products).
- [A path written for agents](https://agentdrives.com/standard#docs-10): **In the middle** 48 of 187 others (every product) lower, 91 the same, 48 higher.
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with 72 of 91** others (every product), 19 higher.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Level with 105 of 159** others (every product), 54 higher.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Level with 47 of 90** others (every product), 43 higher.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Behind 74 of 127** others (every product), 43 the same, 10 lower.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Behind 84 of 158** others (every product), 74 the same.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **Behind 52 of 97** others (every product), 45 the same.
- [A person can claim what the agent made](https://agentdrives.com/standard#in-09): **Behind 14 of 23** others (every product), 9 the same.
- [Retried payments charge once, with a receipt](https://agentdrives.com/standard#pay-04): **Behind 23 of 30** others (every product), 7 the same.
- [A tool list that fits](https://agentdrives.com/standard#mcp-11): **Behind 71 of 91** others (every product), 20 the same.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Behind 55 of 70** others (every product), 15 the same.
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **Behind 75 of 91** others (every product), 16 the same.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Behind 136 of 153** others (every product), 17 the same.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Behind 169 of 187** others (every product), 18 the same.

[How each criterion is graded](https://agentdrives.com/standard)

## Agents get stuck at Use and Pay

**6** things to fix for agents: 4 small and 2 medium

One fix can cover several findings.

Agent blockers: **5 found** Agent surfaces: **33 issues found**

[Get your findings, free](https://agentdrives.com/your-findings?p=speedbot) · [What a drive covers](https://agentdrives.com/method?via=md)

We mail a private link to an address at speedbot.dev.

1. Find Partly
2. Get in Clear
3. Use Blocks agents
4. Pay Blocks agents
5. Leave Partly

Or [claim Speedbot.dev](https://agentdrives.com/go/claim/speedbot?add=speedbot.dev&ref=listing) to see where each issue is and ask for a free drive after a fix.

Want Speedbot.dev driven every month? [See Watch](https://agentdrives.com/owners#watch)

### On our standard

Best or ahead on 9 of 36 criteria, behind on 10. Each against the products we measured on it.

- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02)
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03)
- [Structured results](https://agentdrives.com/standard#mcp-08)
- [The best way in is built for agents](https://agentdrives.com/standard#in-12)
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09)
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06)
- [Prices an agent can read](https://agentdrives.com/standard#find-06)
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)

**All 36 criteria**

- [Pages fit one fetch](https://agentdrives.com/standard#docs-08)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [Truthful annotations](https://agentdrives.com/standard#mcp-07)
- [A way in with no person](https://agentdrives.com/standard#in-01)
- [All validation problems at once](https://agentdrives.com/standard#err-04)
- [One way to page through lists](https://agentdrives.com/standard#api-03)
- [Answers sized for an agent](https://agentdrives.com/standard#api-04)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [No person in the buy path](https://agentdrives.com/standard#pay-06)
- [Export before leaving](https://agentdrives.com/standard#leave-03)
- [Fast to the first call](https://agentdrives.com/standard#in-03)
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04)
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03)
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10)
- [Real status codes](https://agentdrives.com/standard#err-01)
- [Errors say what to do next](https://agentdrives.com/standard#err-03)
- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [llms.txt that works](https://agentdrives.com/standard#find-02)
- [A path written for agents](https://agentdrives.com/standard#docs-10)
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05)
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)
- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [A person can claim what the agent made](https://agentdrives.com/standard#in-09)
- [Retried payments charge once, with a receipt](https://agentdrives.com/standard#pay-04)
- [A tool list that fits](https://agentdrives.com/standard#mcp-11)

[How each criterion is graded](https://agentdrives.com/standard)

## For the team behind Speedbot.dev

**6 things to fix for agents: 4 small and 2 medium.**

One fix can cover several findings. Agent blockers: 5 found · Agent surfaces: 33 issues found.

Agents get stuck at Use and Pay. Its team gets the two findings that matter most in full, free, by a private link to an address at speedbot.dev.

- Find: Partly
- Get in: Clear
- Use: Blocks agents
- Pay: Blocks agents
- Leave: Partly

[Get your findings, free](https://agentdrives.com/your-findings?p=speedbot) · [Claim Speedbot.dev](https://agentdrives.com/app/products?add=speedbot.dev&ref=listing) · [What a drive covers](https://agentdrives.com/method?via=md)

## Read more on this step

Pay is where our agent stopped at Speedbot.dev.

- [How AI agents pay for software: x402, MPP and checkouts](https://agentdrives.com/guides/how-ai-agents-pay-for-software?via=md) (guide): Card checkouts, x402 and MPP: what an agent can pay with today, and what most products ask instead.
- [Bot checks on SaaS checkouts: where AI agents stop](https://agentdrives.com/guides/bot-checks-on-saas-checkouts-where-ai-agents?via=md) (guide): As of 31 Oct 2026: 42 of 59 SaaS checkouts our agent reached on 31 Oct 2026 carried a bot check; under 5 made it solve one. 80 of 139 stopped earlier. What to fix so an agent can buy.
- [Tell an AI agent a feature needs a paid plan](https://agentdrives.com/guides/tell-ai-agents-a-feature-needs-a-paid-plan?via=md) (guide): How to answer an AI agent at a paid-plan wall: 402 or 403, a Problem Details body with the required plan, and an upgrade link a person can open.

[Everything on Pay](https://agentdrives.com/access/pay)

## Questions people ask about Speedbot.dev

**Can an AI agent create a Speedbot.dev account on its own?**

Yes, over the API, without a browser. Nothing else was asked: no email, password, phone or CAPTCHA.

**Does Speedbot.dev have an MCP server, and can an agent connect to it?**

Yes. Speedbot.dev has an official MCP server. The server speaks the 28 Jul 2026 MCP spec. A new agent can get in on its own: in the drive of 15 Nov 2026, our agent signed up and got its key without a person. Through the MCP server, our agent tried 26 tasks and did 12.

**How does an AI agent get a Speedbot.dev API key?**

In the drive of 15 Nov 2026, our agent got its Speedbot.dev API key over the API, without a browser or a person. The key came with sign-up. There are no scoped keys.

**Can an AI agent delete its Speedbot.dev account?**

Not on its own: blocked. The API and MCP have no account or agent delete route, and the terms say records remain until removed by the operator, on request to contact@speedbot.dev. Agent A's key still answered 200 after cleanup. Everything the API allows was removed: the intro was cancelled, the rooms closed, the swarm missions deleted, the invitations cancelled and the operator link revoked.

**Can an AI agent pay for Speedbot.dev?**

Partly. Ready to pay: payment not yet proven; stopped at the pay button of the $19 a month charge. Speedbot.dev offers agents a way to pay: x402.

## Where Speedbot.dev fits

- Category: [Commerce](https://agentdrives.com/categories/commerce?via=md), [E-commerce](https://agentdrives.com/categories/ecommerce?via=md)
- Tasks: [Change account settings](https://agentdrives.com/tasks/change-account-settings), [Send a chat message](https://agentdrives.com/tasks/send-a-chat-message), [Configure notifications](https://agentdrives.com/tasks#configure-notifications), [Create a product](https://agentdrives.com/tasks#create-a-product)
- Standards: [MCP](https://agentdrives.com/standards/mcp) (tools an agent can call), [OpenAPI](https://agentdrives.com/standards/openapi) (its API, described), [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents), [x402](https://agentdrives.com/standards/x402) (pay per request)
- Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay) (first stop), [Leave](https://agentdrives.com/access/leave)
- Topics: [MCP servers](https://agentdrives.com/access/find/mcp-servers) (Find step), [Docs and llms.txt](https://agentdrives.com/access/find/docs) (Find step), [MCP sign-in](https://agentdrives.com/access/get-in/mcp-sign-in) (Get in step), [Sign-up](https://agentdrives.com/access/get-in/sign-up) (Get in step), [MCP and API](https://agentdrives.com/access/use/mcp-and-api) (Use step), [Card checkout](https://agentdrives.com/access/pay/card-checkout) (Pay step), [Delete the account](https://agentdrives.com/access/leave/delete-account) (Leave step)
- Rivals: [Gumroad](https://agentdrives.com/tools/gumroad?via=md) (L2), [BigCommerce](https://agentdrives.com/tools/bigcommerce?via=md) (L1), [Ecwid](https://agentdrives.com/tools/ecwid?via=md) (L1)

The level follows [these rules](https://agentdrives.com/changes#rules-2026-11-18).

## Level by drive

One drive so far, on 15 Nov 2026.

[Every drive in full](https://agentdrives.com/tools/speedbot/history?via=md)

Source: our drives of Speedbot.dev. As of 15 Nov 2026.

One drive so far.

Data: [JSON](https://agentdrives.com/api/tools/speedbot.json?via=md) · [Markdown](https://agentdrives.com/tools/speedbot.md?via=md) · [History](https://agentdrives.com/tools/speedbot/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/speedbot.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/speedbot.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `79b5ea71241817876919edfe96aada92b379ff373a4402f3066a8d32e5f7edeb`

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/speedbot?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).
