# MotherDuck L4 · Runs on its own MotherDuck is a cloud database service built on DuckDB. **Can an AI agent use MotherDuck? Yes, without signing up.** Our agent got into MotherDuck on its own in 2 minutes and did all 10 of its core tasks. Category: Data warehouses · Connects by: MCP, API, CLI · Agent payments: None found · Driven: 26 Oct 2026 **How to connect** - MCP server URL: `https://api.motherduck.com/mcp` (streamable HTTP, tested in our drive). Source: https://api.motherduck.com/mcp - API base URL: `https://api.motherduck.com` (documented). Source: https://motherduck.com/openapi.json - Docs page: `https://motherduck.com/docs/getting-started/` (tested in our drive). Source: https://motherduck.com/docs/getting-started/ **Level 4: Runs on its own.** An agent does the core work and can stop paying on its own. - Got in by: Try first, claim later (2 minutes, no account) - Got as far as: Use: all 10 core tasks (No payment made) - To reach L5: Pay without a person. [What the levels mean](https://agentdrives.com/method/levels?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. (596 doc pages read) 2. **Get in**: On its own. Try first, claim later, MCP sign-in, sign-up in a browser. (2 minutes) 3. **Use**: On its own. Did: run queries and create databases and tables; build a chart (Dive) and embed it in a page. (10 of 10 core tasks) 4. **Pay**: Not reached. Its robots.txt closes the payment page. 5. **Leave**: On its own. Nothing to cancel, deletes its account. ## Getting in 4 of 5 ways in worked without a person. The way that worked: **Try first, claim later**, 2 minutes. No inbox, browser or person needed. - Agent on a server (API, MCP, CLI): Partly. Without an account (try first, claim later) it gets an API key, makes its first API call and does all of the core work, then stops at payment: paying takes a checkout page in a browser. - Assistant in its own browser (Like ChatGPT agent): Not checked. Sign-up wasn't tried in this drive. - Signed agent: Not checked. Not checked: its robots.txt asks crawlers to stay off the sign-up page. | Way in | What happened | |---|---| | Try first, claim later | Worked | | Email and password | Worked | | CLI code login | Worked | | Sign-in for apps (OAuth, MCP) | Worked | | Sign-up by API | Not tried: The same as another way | - Crawlers: **robots.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 MotherDuck All 10 core tasks done, and 20 of 23 others. - Reliability: core tasks that worked on all 3 runs: 70 of 100 - Handles mistakes: clear errors, retries without duplicates, honest limits: 72 of 100 - Surface tested: documented routes, tools and commands run and checked: 97 of 100 - Docs accuracy: documented operations that behaved as the docs say: 99 of 100 - Docs completeness: how fully the docs describe each operation: 75 of 100 Core tasks: | Task | Result | Done through | |---|---|---| | Run a SQL query against a MotherDuck database | Done | MCP, CLI | | Create a database | Done | MCP, CLI | | List databases and read their schema | Done | MCP | | Create a table | Done | MCP, CLI | | Generate an interactive visualization (Dive) from a natural-language question | Done | MCP, CLI | | Embed a Dive in an external application | Done | API | | Build and deploy a scheduled Python data pipeline (Flight) | Done | MCP, CLI | | Trigger a Flight run on demand | Done | MCP, CLI | | Read Flight run history and logs | Done | MCP, CLI | | Build a managed Iceberg/DuckLake lakehouse on cloud object storage | Done | MCP, CLI | 20 of 23 other tasks done: - Query a table as of a past time or snapshot version (time travel): Done - Create and manage a read-only data share of a database: Done - Scope a share to specific tables and mask or filter rows/columns: Done - Restore a database from a snapshot: Done - Create a named long-lived backup snapshot: Done - Write a Guide capturing org metric definitions and query conventions for AI agents: Done - Read and browse existing Guides by topic: Done - Update or edit a Guide's content: Done - Ask a natural-language documentation question (ask_docs_question): Done - Search the catalog for databases, tables, shares and Guides: Done - Auto-fix a broken SQL query (FixIt): Done - Visualize result-set columns instantly (Column Explorer): Done - Run SQL AI functions (prompt, embedding) over data: Done - Scale read workloads with read-scaling replicas: Done - View consolidated query history across the organization: Done - Ingest data from cloud storage, databases, or SaaS sources: Done - Resize compute instance type/size: Done - Create a service account for programmatic access: Done - Restrict a connection to read-only database access: Done - Assign role-based access control to users: Done - Set up AWS PrivateLink or IP allowlisting for network access: Paid plan - Read Apache Iceberg tables via REST catalog: Blocked. Needs an outside catalog and cloud credentials the account lacked. - Invite an internal user to the organization: Not tried - Purchase via AWS Marketplace private offer: Not tried The plans they need: - Set up AWS PrivateLink or IP allowlisting: Enterprise Paid-plan tasks don't count toward the level. The drive used the no-card trial (Business, 7 days) on the web account; Free Plan on the CLI account. What it can't do, and why: - Pay for a plan: Buying is a card form in the web app; no billing API or agent payment. - Connect an Iceberg catalog: Needs an outside catalog and cloud credentials the account lacked. - Keep a terminal-made account past 72 hours: A person must claim it first. **Surface audit:** 194 documented operations, 187 run, 186 passed, 2 not as documented, 1 blocked (sandbox or plan limits), 3 not run for time, 5 left out to stay safe. ## How an agent connects MCP, API, OpenAPI, CLI and llms.txt found. Agent surfaces: API tested · MCP tested · CLI tested · SDK tested · Docs tested · Agent payments none found. Issues found: 3. - **MCP server**: All tested. Official server. Remote server, 47 tools when driven (SQL, schema, Dives, Flights, Guides, docs Q&A) Sign-in needed to see its tools. https://api.motherduck.com/mcp (41 tools across its docs) - **API**: All tested. REST admin API, 10 operations (users, tokens, ducklings, embed sessions); data work is SQL. (10 operations across its docs) - **OpenAPI**: Yes. 3.0.3, 10 operations. - **CLI**: All tested. MotherDuck CLI v1.5.6-2026-10-707: new, login (device flow), query, dive, flight, guide. (35 commands across its docs) - **SDK**: 94 tested. (101 methods across its docs) - **llms.txt**: Yes. https://motherduck.com/llms.txt - **Agent payments**: None found. The checkout: Chose a plan; the checkout didn't open: Business, $250 a month; Checkout: Stripe Checkout; No CAPTCHA at checkout. - **Docs**: No gaps in what we read. Covers getting started, auth, error codes and code examples. 12 of 12 documented ways to do the core work worked when tried. https://motherduck.com/docs/getting-started/ (596 of 743 pages read) [The standards](https://agentdrives.com/standard) ## Tips for agent builders - Install the MotherDuck CLI from https://install.motherduck.com and run 'motherduck new -o json' to get an account and token with no browser; delete it with DELETE /v1/users/ when done. - On an existing account, use 'motherduck login --headless' then 'motherduck login --device-code=' after a person confirms the code. - Use the remote MCP server at https://api.motherduck.com/mcp with 'Authorization: Bearer ' (protocol 2025-11-25); call get_dive_guide or get_flight_guide before writing Dives or Flights. - The MCP 'query' tool refuses CALL, SHOW ALL ROLES and EXPLAIN ANALYZE as not read-only: send them through query_rw. - Find your username with GET /v1/users before calling /v1/users/{username}/... (the email's local part with '-' turned into '_'). - Create scoped tokens with POST /v1/users/{username}/tokens (ttl >= 300, token_type read_scaling for read-only). ## How MotherDuck compares In Data warehouses: 1st of 2 Data warehouses products our agent got into on its own. - [ClickHouse Cloud](https://agentdrives.com/tools/clickhouse.md?via=md): L4, Gets in on its own - **MotherDuck** (this page): L4, Gets in on its own - [Databricks](https://agentdrives.com/tools/databricks.md?via=md): L1, Can't sign up on its own - [Firebolt](https://agentdrives.com/tools/firebolt.md?via=md): L1, Can't sign up on its own - [Snowflake](https://agentdrives.com/tools/snowflake.md?via=md): L1, Can't sign up on its own - [Starburst](https://agentdrives.com/tools/starburst.md?via=md): L1, Can't sign up on its own - [Tinybird](https://agentdrives.com/tools/tinybird.md?via=md): L1, Can't sign up on its own [All 7 in Data warehouses](https://agentdrives.com/categories/data-warehouses?via=md) Sorted by level, then work done, then time to the first call. [How we rank](https://agentdrives.com/method?via=md#order) On our standard (29 criteria: against other data warehouses products where we measured 5 or more, otherwise against every product we measured): - [Export before leaving](https://agentdrives.com/standard#leave-03): **The best result** All 6 others (data warehouses products) lower. - [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Ahead of most** 5 of 6 others (data warehouses products) lower, 1 the same. - [All validation problems at once](https://agentdrives.com/standard#err-04): **Ahead of most** 29 of 35 others (every product) lower, 6 the same. - [Structured results](https://agentdrives.com/standard#mcp-08): **Ahead of most** 26 of 36 others (every product) lower, 10 the same. - [A path written for agents](https://agentdrives.com/standard#docs-10): **Ahead of most** 4 of 6 others (data warehouses products) lower, 2 the same. - [A person can claim what the agent made](https://agentdrives.com/standard#in-09): **Ahead of most** 5 of 9 others (every product) lower, 4 the same. - [The best way in is built for agents](https://agentdrives.com/standard#in-12): **In the middle** 3 of 6 others (data warehouses products) lower, 3 the same. - [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with most** 4 of 6 others (data warehouses products) the same, 2 lower. - [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Level with most** 4 of 6 others (data warehouses products) the same, 2 lower. - [One way to page through lists](https://agentdrives.com/standard#api-03): **In the middle** 35 of 87 others (every product) lower, 42 the same, 10 higher. - [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with most** 61 of 85 others (every product) the same, 24 lower. - [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of most** 27 of 47 others (every product) lower, 5 the same, 15 higher. - [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with most** 3 of 4 others (data warehouses products) the same, 1 lower. - [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Level with most** 3 of 4 others (data warehouses products) the same, 1 lower. - [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **In the middle** 20 of 65 others (every product) lower, 30 the same, 15 higher. - [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **Level with most** 61 of 65 others (every product) the same, 4 lower. - [Real status codes](https://agentdrives.com/standard#err-01): **The same as all** 5 others (data warehouses products). - [Errors a program can read](https://agentdrives.com/standard#err-02): **In the middle** 1 of 4 others (data warehouses products) lower, 2 the same, 1 higher. - [Errors say what to do next](https://agentdrives.com/standard#err-03): **In the middle** 1 of 4 others (data warehouses products) lower, 2 the same, 1 higher. - [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **The same as all** 5 others (data warehouses products). - [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **Level with most** 39 of 65 others (every product) the same, 10 lower, 16 higher. - [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with most** 5 of 6 others (data warehouses products) the same, 1 higher. - [Truthful annotations](https://agentdrives.com/standard#mcp-07): **Behind most** 34 of 65 others (every product) higher, 13 the same, 18 lower. - [A tool list that fits](https://agentdrives.com/standard#mcp-11): **Behind most** 33 of 65 others (every product) higher, 16 the same, 16 lower. - [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with most** 44 of 65 others (every product) the same, 1 lower, 20 higher. - [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Behind most** 16 of 31 others (every product) higher, 11 the same, 4 lower. - [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Level with most** 3 of 5 others (data warehouses products) the same, 2 higher. - [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **In the middle** 3 of 6 others (data warehouses products) the same, 3 higher. - [A request id on every answer](https://agentdrives.com/standard#err-07): **Behind most** 3 of 5 others (data warehouses products) higher, 2 the same. [How each criterion is graded](https://agentdrives.com/standard) ## For the team behind MotherDuck **5 things to fix for agents.** Agent blockers: 1 found · Agent surfaces: 2 issues found. Safety review: 2 issues found. Our agent didn't reach Pay. Prove MotherDuck 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. - Find: Clear - Get in: Clear - Use: Clear - Pay: Not reached - Leave: Clear [Claim MotherDuck, free](https://agentdrives.com/app/products?add=motherduck.com&ref=listing) · [What a drive covers](https://agentdrives.com/method?via=md) ## Where MotherDuck fits - Category: [Data and storage](https://agentdrives.com/categories/data?via=md), [Data warehouses](https://agentdrives.com/categories/data-warehouses?via=md) - Tasks: [Set a member's role or permissions](https://agentdrives.com/tasks/set-a-member-s-role-or-permissions), [Create a database](https://agentdrives.com/tasks/create-a-database), [Search the account's content](https://agentdrives.com/tasks/search-the-account-s-content), [List databases and read their schema](https://agentdrives.com/tasks/list-databases-and-read-their-schema), [Query a database over a REST or GraphQL API](https://agentdrives.com/tasks/query-a-database-over-a-rest-or-graphql-api), [Create a table](https://agentdrives.com/tasks/create-a-table) - Wall: [Card before the first use](https://agentdrives.com/access/pay/card-checkout) (our agent got in another way) - 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), [Leave](https://agentdrives.com/access/leave) - Rivals: [ClickHouse Cloud](https://agentdrives.com/tools/clickhouse?via=md) (L4), [Databricks](https://agentdrives.com/tools/databricks?via=md) (L1), [Firebolt](https://agentdrives.com/tools/firebolt?via=md) (L1) Data: [JSON](https://agentdrives.com/api/tools/motherduck.json?via=md) · [Markdown](https://agentdrives.com/tools/motherduck.md?via=md) · [History](https://agentdrives.com/tools/motherduck/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/motherduck.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/motherduck.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) **Found an error?** [Tell us on this page](https://agentdrives.com/tools/motherduck?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).