# Can an AI agent use SurrealDB? L3 · Does the work

SurrealDB is a database company with a hosted cloud and a memory service for AI agents.

**L3 · Does the work** · [What the levels mean](https://agentdrives.com/method/levels?via=md)

Rank among the 246 products we drove:

- Time to get in: <1 minutes, #1 (Getting in on its own)
- Core work done: 100%, tied #1 (10 of 10 core tasks)
- Steps on its own: 3 / 5, tied #35 (Find to Leave, no person)
- Holds up: 68 / 100, tied #85 (Reliability under errors)

**Can an AI agent use SurrealDB? Yes.** Our agent signed up for SurrealDB on its own in a browser through a device login and used its API, MCP server and CLI. It offers agents a way to pay: Payment tools on its MCP server.

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: MCP sign-in (Under a minute, in a browser)
- Got as far as: Use: all 10 core tasks (A person has to buy)

Category: Databases · Connects by: MCP, API, CLI, SDK · Agent payments: Payment tools on its MCP server; our agent didn't try it · Driven: 13 Nov 2026

**How to connect**
- MCP server URL: `https://mcp.surrealdb.com/` (streamable HTTP, tested in our drive). Source: https://mcp.surrealdb.com/
- CLI install: `brew install surrealdb` (documented). Source: https://surrealdb.com/surrealdb/install
- Docs page: `https://surrealdb.com/docs/agent-memory` (tested in our drive). Source: https://surrealdb.com/docs/agent-memory

Checked 17 Nov 2026: MCP server answers, 82 tools; sign-up page, llms.txt and OpenAPI unchanged since the check before.

See [how it ranks among databases for agents](https://agentdrives.com/research/best-databases-for-ai-agents?via=md).

## 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. (424 doc pages read)
2. **Get in**: On its own. MCP sign-in, sign-up in a browser. (<1 minutes)
3. **Use**: On its own. Did: create, rename, query and delete serverless databases and free dedicated instances; define tables, write records and run vector, full-text and graph searches. (10 of 10 core tasks)
4. **Pay**: Stopped. Needs a person to buy. The billing form requires a phone number before the card step. (1 way for agents to pay) First stop.
5. **Leave**: Partly. Nothing to cancel. It deletes its data, but the login stays.

To reach L4: Delete its account, so its keys and login stop working.

## How an agent connects

MCP, API, OpenAPI, CLI, SDK, agent payments and llms.txt, all found.

- **MCP server**: 72 of 81 tested. Official server. Remote MCP server mcp.surrealdb.com, 82 tools, OAuth with DCR. https://mcp.surrealdb.com/ (81 tools mapped in our drive) 82 tools listed without signing in on 2 Nov 2026: `mcp_auth`, `list_regions`, `list_instance_types`, `list_instance_versions`, `list_billing_countries`, `search_documentation`, `get_cloud_terms_and_conditions`, `get_cloud_terms_acceptance_status`, `accept_cloud_terms_and_conditions`, `get_cloud_profile`, `list_organizations`, `get_organization`, `create_organization`, `update_organization`, `list_products`, `deploy_cluster`, `get_cluster`, `update_cluster`, `delete_cluster`, `get_cluster_usage`, `estimate_cluster_cost`, `list_instances`, `pause_instance`, `resume_instance`, `get_instance_database_token`, `get_instance_backup_policy`, `get_instance_status`, `get_instance_spend`, `call_instance_tool`, `list_instance_tools`, `get_instance_metrics`, `get_instance_logs`, `get_organization_deployment_readiness`, `get_organization_billing_requirements`, `get_organization_billing`, `update_organization_billing`, `copy_organization_billing_from`, `setup_organization_for_instances`, `list_invoices`, `list_billing_coupons`, `get_organization_payment`, `get_organization_payment_setup_url`, `get_organization_payment_portal_url`, `get_organization_usage`, `list_organization_members`, `list_organization_roles`, `update_organization_member_role`, `remove_organization_member`, `list_organization_invitations`, `invite_organization_member`, `revoke_organization_invitation`, `list_context_regions`, `list_agent_memory_context_packages`, `list_organization_agent_memory_context_packages`, `assign_organization_agent_memory_context_package`, `cancel_organization_agent_memory_context_package`, `list_agent_memory_contexts`, `list_agent_memory_context_api_keys`, `delete_agent_memory_context_api_key`, `rotate_agent_memory_context_api_key`, `mint_agent_memory_scoped_key`, `mint_agent_memory_access_token`, `list_agent_memory_context_principals`, `create_agent_memory_context_principal`, `update_agent_memory_context_principal`, `delete_agent_memory_context_principal`, `replace_agent_memory_principal_grants`, `add_agent_memory_context_user`, `call_agent_memory_tool`, `list_agent_memory_tools`, `delete_agent_memory_context_scope`, `create_agent_memory_session`, `call_agent_memory_chat`, `get_agent_memory_snapshot`, `list_agent_memory_entities`, `list_agent_memory_documents`, `search_agent_memory_documents`, `list_agent_memory_context_scopes`, `create_agent_memory_context_scope`, `get_agent_memory_context_config`, `list_agent_memory_context_providers`, `list_agent_memory_context_verbs`.
- **API**: 156 of 250 tested. Platform REST API, OpenAPI 3.0.0. (250 operations mapped in our drive)
- **OpenAPI**: Yes. A machine-readable description of the API.
- **CLI**: 74 of 81 tested. surreal CLI v1.2.0 with cloud component 1.1.0: instance, memory, org, token and api commands. (81 commands mapped in our drive)
- **SDK**: Yes. Packages: npm [@surrealdb/memory](https://www.npmjs.com/package/@surrealdb/memory).
- **llms.txt**: Yes. https://surrealdb.com/llms.txt
- **Agent payments**: Listed, not tested. Payment tools on its MCP server. Chose a plan, but the checkout didn't open: Earth Pro, $15 a month. It checks out through Stripe Checkout. No CAPTCHA at checkout. It asks for a phone number.
- **Docs**: In part. Covers getting started, auth, error codes and code examples. Describes each operation only in part: completeness 55 of 100. 27 of 27 documented ways to do the core work worked. https://surrealdb.com/docs/agent-memory (424 of 1,374 pages read)

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

## Getting in

Our agent tried 3 of 7 ways in; 2 worked without a person.

The way that worked: **MCP sign-in**, under a minute. Needs a browser. No inbox or person needed.

- Agent on a server (API, MCP, CLI): No. Stops at sign-up: it works only in a browser.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does all of the core work, then stops: deletes its data, but the login stays.
- Signed agent (Known to Cloudflare): Yes. The site opens.

| Way in | What happened |
|---|---|
| MCP sign-in | Worked |
| Sign-up in a browser | Worked |
| Runs locally, no account | Not reached |
| Try first, claim later | Stopped |
| Email and password | Not reached |
| Registration through auth.md | Not tried: The same as another way |
| Identity assertion | Not tried: The same as another way |

- Crawlers: **The robots.txt on auth.surrealdb.com asks crawlers to stay off sign-up.** Nothing to fix.

## What an agent can do with SurrealDB

All 10 core tasks done, and 20 of 24 others.

- Holds up: 68 of 100 (Reliability 83, Handles mistakes 52). The mean of the two, 67.5, with a half rounded to the even number.
- Docs match: 72 of 100 (Docs accuracy 80, Docs completeness 55). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 76 of 100. 257 of 338 passed: the 412 documented operations less the 74 that spend money or reach real people

Core tasks:

| Task | Result | Done through |
|---|---|---|
| Create a serverless Earth database | Done | API, MCP, CLI |
| Deploy a managed Cloud instance | Done | API, MCP, CLI |
| Run a SurrealQL query | Done | API, MCP, CLI |
| Create or update a record | Done | API, MCP, CLI |
| Define a table and its fields | Done | API, MCP, CLI |
| Run a vector similarity search | Done | API, MCP, CLI |
| Create an Agent Memory context | Done | API, MCP |
| Store a fact in agent memory | Done | API, MCP |
| Recall facts from agent memory | Done | API, MCP |
| Delete a Cloud instance | Done | API, MCP, CLI |

20 of 24 other tasks done:

- Delete a record: Done
- Relate records with graph edges: Done
- Subscribe to live query changes: Done
- Run a full-text search: Done
- Query data over GraphQL: Done
- Pause or resume an instance: Done
- Import a SurrealQL file into a database: Done
- Export a database to a file: Done
- Read instance metrics: Done
- Read instance logs: Done
- Upload a document to agent memory: Done
- Forget facts in agent memory: Done
- Chat with an agent memory context: Done
- Set grants for an agent memory principal: Done
- Set table and record permissions: Done
- Define a database event or function: Done
- Register end users of your app through record access: Done
- Store a file in a database bucket: Done
- Invite a member to an organisation: Done
- Read organisation usage and spend: Done
- Resize an instance: Paid plan
- Change the organisation plan: Paid plan
- Configure enterprise SSO: Paid plan
- Provision users with SCIM: Paid plan
- Back up an instance on demand: Blocked. Resize needs a paid type; backup gives an empty error; no newer version exists.
- Upgrade an instance SurrealDB version: Blocked
- Change a member's role: Not tried
- Create an organisation: Not tried

The drive used the free plan.

What it can't do, and why:

- Pay for a paid plan: The billing form requires a phone number before the card step.
- Delete the account: No delete control or endpoint; the privacy policy says to email the company.
- Back up on demand, resize or upgrade a free instance: Resize needs a paid type; backup gives an empty error; no newer version exists.
- Manage access tokens with a token: Token changes need a logged-in session, not a token.

**Surface audit:** 412 documented operations: 302 run, 40 blocked by sandbox or plan limits and 70 left out because they spend money or reach real people. Of the 302 run, 257 passed and 45 didn't; 50 behaved differently from the docs. By surface, 156 on the API, 74 in the CLI and 72 on the MCP server.

## Tips for agent builders

- Use `surreal cloud auth login --flow device --json` from a browser-free shell, then `surreal cloud token create` for a PAT; revoke it with `surreal cloud token delete --force` from the session, because the PAT cannot revoke itself.
- Pass `--yes` to every CLI command that changes or deletes something in a non-interactive shell.
- deploy_cluster for Earth needs no residency; the documented `cloudflare-us` enum value is refused.
- Agent Memory Free allows one context: delete the old one before you create another.
- For a free dedicated instance, use POST /api/cloud/v0/instances with specs.slug 'free'; `surreal cloud instance deploy --region aws-use1` wrongly says no single-node type is available.
- Begin `surreal cloud instance import` files with `OPTION IMPORT;`, and read the data back after an import error, because a reported failure can still have committed rows.

## Paying

Ways to pay checked 13 Nov 2026.

- Result: Stopped. Needs a person to buy. The billing form requires a phone number before the card step.
- Checkout: Chose a plan, but the checkout didn't open: Earth Pro, $15 a month. It checks out through Stripe Checkout. No CAPTCHA at checkout. It asks for a phone number.
- Ways to pay:
  - Payment tools on its MCP server (on its own domain)
- Trial: No card needed to start.

## Leaving

- Result: Partly. Nothing to cancel. It deletes its data, but the login stays.
- Its account: Not tried.

## Checked every day

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

- Sign-up page, loads on the newest check; 5 of 5 days
- llms.txt, found on the newest check; 5 of 5 days
- MCP server, answers on the newest check (82 tools); 5 of 5 days
- OpenAPI, found on the newest check; 5 of 5 days

## How SurrealDB compares

In Databases: 4 of the 21 products we drove in Databases are higher; 9 others share L3. As of 14 Nov 2026.

- [Upstash](https://agentdrives.com/tools/upstash.md?via=md): L4, Gets in on its own
- [Airtable](https://agentdrives.com/tools/airtable.md?via=md): L4, Gets in on its own
- [NocoDB](https://agentdrives.com/tools/nocodb.md?via=md): L4, Gets in on its own
- [Convex](https://agentdrives.com/tools/convex.md?via=md): L4, Gets in on its own
- [Redis Cloud](https://agentdrives.com/tools/redis.md?via=md): L3, Gets in on its own
- [Firebase](https://agentdrives.com/tools/firebase-google.md?via=md): L3, Gets in on its own
- [Neon](https://agentdrives.com/tools/neon.md?via=md): L3, Gets in on its own
- [PlanetScale](https://agentdrives.com/tools/planetscale.md?via=md): L2, Gets in on its own
- [Baserow](https://agentdrives.com/tools/baserow.md?via=md): L1, Can't sign up on its own
- [MongoDB Atlas](https://agentdrives.com/tools/mongodb.md?via=md): L1, Can't sign up on its own
- [Supabase](https://agentdrives.com/tools/supabase.md?via=md): L1, Can't sign up on its own
- **SurrealDB** (this page): L3, Gets in on its own

12 of 21 shown, in the directory's order.

[All 21 in Databases](https://agentdrives.com/categories/databases?via=md)

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

On our standard (35 criteria). Best or ahead on 4 of 35 criteria, behind on 7.

- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Ahead of 15 of 16** others (databases products), 1 the same.
- [llms.txt that works](https://agentdrives.com/standard#find-02): **Ahead of 14 of 19** others (databases products), 5 the same.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Ahead of 11 of 16** others (databases products), 5 the same.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **Ahead of 11 of 16** others (databases products), 5 the same.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with 9 of 14** others (databases products), 5 lower.
- [A way in with no person](https://agentdrives.com/standard#in-01): **Level with 13 of 19** others (databases products), 6 lower.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Level with 11 of 15** others (databases products), 4 lower.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **In the middle** 8 of 19 others (databases products) lower, 8 the same, 3 higher.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Level with 12 of 16** others (databases products), 4 lower.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **In the middle** 6 of 14 others (databases products) lower, 5 the same, 3 higher.
- [Retried payments charge once, with a receipt](https://agentdrives.com/standard#pay-04): **Level with 18 of 30** others (every product), 8 lower, 4 higher.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Level with 9 of 17** others (databases products), 5 lower, 3 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with 14 of 15** others (databases products), 1 lower.
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10): **Level with 16 of 17** others (databases products), 1 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Level with 14 of 17** others (databases products), 2 lower, 1 higher.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **The same as all** 14 others (databases products).
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **The same as all** 10 others (databases products).
- [Real status codes](https://agentdrives.com/standard#err-01): **The same as all** 16 others (databases products).
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02): **The same as all** 18 others (databases products).
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03): **The same as all** 12 others (databases products).
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **The same as all** 14 others (databases products).
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with 9 of 10** others (databases products), 1 higher.
- [A tool list that fits](https://agentdrives.com/standard#mcp-11): **In the middle** 2 of 10 others (databases products) lower, 5 the same, 3 higher.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with 13 of 16** others (databases products), 3 higher.
- [Truthful annotations](https://agentdrives.com/standard#mcp-07): **In the middle** 2 of 10 others (databases products) lower, 4 the same, 4 higher.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Level with 12 of 18** others (databases products), 1 lower, 5 higher.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **Level with 11 of 15** others (databases products), 4 higher.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Level with 7 of 10** others (databases products), 3 higher.
- [Structured results](https://agentdrives.com/standard#mcp-08): **Behind 5 of 9** others (databases products), 3 the same, 1 lower.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **Behind 6 of 11** others (databases products), 5 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Behind 12 of 18** others (databases products), 6 the same.
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **Behind 7 of 10** others (databases products), 3 the same.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Behind 6 of 8** others (databases products), 2 the same.
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **The lowest result** All 10 others (databases products) higher.
- [No person in the buy path](https://agentdrives.com/standard#pay-06): **The lowest result** All 13 others (databases products) higher.

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

## Agents get stuck at Pay

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

One fix can cover several findings.

Agent blockers: **4 found** Agent surfaces: **52 issues found**

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

We mail a private link to an address at surrealdb.com.

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

Or [claim SurrealDB](https://agentdrives.com/go/claim/surrealdb?add=surrealdb.com&ref=listing&safety=1) to see where each issue is, read your safety findings with their fixes and ask for a free drive after a fix.

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

### On our standard

Best or ahead on 4 of 35 criteria, behind on 7. Each against the products we measured on it.

- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)
- [llms.txt that works](https://agentdrives.com/standard#find-02)
- [A path written for agents](https://agentdrives.com/standard#docs-10)
- [Export before leaving](https://agentdrives.com/standard#leave-03)
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04)
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09)
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06)
- [No person in the buy path](https://agentdrives.com/standard#pay-06)

**All 35 criteria**

- [Answers sized for an agent](https://agentdrives.com/standard#api-04)
- [A way in with no person](https://agentdrives.com/standard#in-01)
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08)
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05)
- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [Retried payments charge once, with a receipt](https://agentdrives.com/standard#pay-04)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [Fast to the first call](https://agentdrives.com/standard#in-03)
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10)
- [Errors say what to do next](https://agentdrives.com/standard#err-03)
- [Prices an agent can read](https://agentdrives.com/standard#find-06)
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03)
- [Real status codes](https://agentdrives.com/standard#err-01)
- [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)
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02)
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05)
- [A tool list that fits](https://agentdrives.com/standard#mcp-11)
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08)
- [Truthful annotations](https://agentdrives.com/standard#mcp-07)
- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [One way to page through lists](https://agentdrives.com/standard#api-03)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)
- [Structured results](https://agentdrives.com/standard#mcp-08)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [The best way in is built for agents](https://agentdrives.com/standard#in-12)

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

## For the team behind SurrealDB

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

One fix can cover several findings. Agent blockers: 4 found · Agent surfaces: 52 issues found.

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

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

[Get your findings, free](https://agentdrives.com/your-findings?p=surrealdb) · [Claim SurrealDB](https://agentdrives.com/app/products?add=surrealdb.com&ref=listing&safety=1) · [What a drive covers](https://agentdrives.com/method?via=md)

## Read more on this step

Pay is where our agent stopped at SurrealDB.

- [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.
- [How far does an AI agent get in a card checkout?](https://agentdrives.com/findings/card-checkout?via=md) (finding): Our agent reached the checkout at 88 of the 190 products it set out to buy from, and the card form at 68.
- [Agent experience (AX): what it is, measured at 246 products](https://agentdrives.com/guides/agent-experience?via=md) (guide): As of 9 Nov 2026: Agent experience (AX) is whether an AI agent can find, get into, use and pay for a product on its own. We drove 246 products to measure it.

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

## Questions people ask about SurrealDB

**Can an AI agent create a SurrealDB account on its own?**

Yes, in a browser, without a person. Email and password sign-up at auth.surrealdb.com (Auth0), done in the browser; no CAPTCHA seen. The form asked for name, job title, company, use case and organisation name; our agent answered. The Google, GitHub, Microsoft and passkey buttons were not used. There is no browser-free sign-up; auth.md documents no agent registration.

**Does SurrealDB have an MCP server, and can an agent connect to it?**

Yes. SurrealDB has an official MCP server. The server is hosted, lists 82 tools and signs an agent in with OAuth. A new agent can get in on its own: in the drive of 13 Nov 2026, our agent signed up, verified and got its key without a person. Through the MCP server, our agent tried 25 tasks and did 24.

**How does an AI agent get a SurrealDB API key?**

In the drive of 13 Nov 2026, our agent got its SurrealDB API key over the API, without a browser or a person. MCP OAuth (DCR and PKCE) gave a token after a consent page in our agent's browser. The CLI device login (code confirmed in our agent's browser) gave a session, and `surreal cloud token create` minted a scoped PAT without a browser. The PAT was used on the API and revoked at the end through the CLI session; it got 401 after the grace period. The PAT itself cannot manage tokens (403 'Use a logged-in session').

**Can an AI agent pay for SurrealDB?**

No. A person has to buy: a phone number at checkout. No card needed to start. SurrealDB offers agents a way to pay: Payment tools on its MCP server.

## Where SurrealDB fits

- Category: [Data and storage](https://agentdrives.com/categories/data?via=md), [Databases](https://agentdrives.com/categories/databases?via=md)
- Tasks: [Invite a member](https://agentdrives.com/tasks/invite-a-member), [Read usage and quotas](https://agentdrives.com/tasks/read-usage-and-quotas), [Export data to a file](https://agentdrives.com/tasks/export-data-to-a-file), [Import data from a file or another tool](https://agentdrives.com/tasks/import-data-from-a-file-or-another-tool), [Create a database](https://agentdrives.com/tasks/create-a-database), [Create or update a record](https://agentdrives.com/tasks/create-or-update-a-record)
- Wall: [Phone number at sign-up](https://agentdrives.com/access/get-in/sign-up) (our agent got in another way), [Let AI agents sign up without a phone number](https://agentdrives.com/guides/sign-up-without-a-phone-number?via=md) (fix guide)
- 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)
- 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), [MCP and API](https://agentdrives.com/access/use/mcp-and-api) (Use step), [Card checkout](https://agentdrives.com/access/pay/card-checkout) (Pay step)
- Rivals: [Couchbase](https://agentdrives.com/tools/couchbase?via=md) (L3), [Firebase](https://agentdrives.com/tools/firebase-google?via=md) (L3), [Hasura](https://agentdrives.com/tools/hasura?via=md) (L3)

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

## Level by drive

One drive so far, on 13 Nov 2026.

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

Source: our drives of SurrealDB. As of 13 Nov 2026.

One drive so far.

Data: [JSON](https://agentdrives.com/api/tools/surrealdb.json?via=md) · [Markdown](https://agentdrives.com/tools/surrealdb.md?via=md) · [History](https://agentdrives.com/tools/surrealdb/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/surrealdb.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/surrealdb.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `a5c0b2770653c5d1fd5bcc47d15e00b7d6b768e4b715a547dc3de30de8182ae9`

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