Skip to content
ProductArena

How MotherDuck’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score37/100

Agent-ready 56.4 × 0.30 = 16.92

API quality 30.0 × 0.20 = 6.00

Openness 16.2 × 0.20 = 3.24

Built-in AI 56.2 × 0.15 = 8.43

Automation 15.0 × 0.15 = 2.25

(16.92 + 6.00 + 3.24 + 8.43 + 2.25) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 36.84 ÷ 1.00 = 36.8

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready56.4/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://motherduck.com/llms.txt“PROBE llms.txt: HTTP 200 at https://motherduck.com/llms.txt # MotherDuck MotherDuck is a modern serverless data warehouse built on DuckDB. It's faster and significantly less expen”
  • [probe] https://motherduck.com/llms.txt“PROBE runtime (recorded 2026-09-06): MotherDuck publishes an agentskills.io-conformant discovery manifest at /.well-known/agent-skills/index.json (schema schemas.agentskills.io/discovery/0.2.0) listing machine-readable skills with digests, alongside /.well-known/mcp.json and an every-page-as-markdown convention — agent-oriented docs as a first-class surface.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“official MCP server documented at https://motherduck.com/docs/sql-reference/mcp/”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Run Python jobs on a schedule for ingest, transformation, and operational tasks”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“you can securely save your credentials locally”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“If you are using Python or CLI and don't want to authenticate every session, you can securely save your credentials locally.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“You can limit MotherDuck's ability to interact with your local environment using SaaS Mode”
  • [claimed-docs] https://motherduck.com/docs/integrations/transformation/dbt.md“dbt-duckdb is the adapter which allows dbt to use DuckDB and MotherDuck.”
  • [probe] https://motherduck.com/docs/concepts/architecture-and-capabilities/“PROBE runtime (recorded 2026-09-06): the engine under MotherDuck ran FULLY keyless on a laptop — `duckdb -c` built a 1,000,000-row table and ran an aggregate GROUP BY (4 regions × 250,000 rows with summed revenue) in one command, a REAL analytical roundtrip with zero accounts or configuration.”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Analyze your data with natural language using the remote MCP Server”
  • [claimed-docs] https://github.com/motherduckdb/mcp-server-motherduck“Local MCP server for DuckDB and MotherDuck”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“For local DuckDB databases, custom configurations, or self-hosted scenarios, use the local MCP server”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“use the **local MCP server** (mcp-server-motherduck)”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“The remote MCP server exposes both read-only and read-write tools.”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“With the remote MCP server, your agent can: - Execute read-only and read-write SQL against your databases”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“official MCP server documented at https://motherduck.com/docs/sql-reference/mcp/”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”

Use an official CLIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Install the DuckDB CLI and connect directly to MotherDuck”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“you can securely save your credentials locally”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“If you are using Python or CLI and don't want to authenticate every session, you can securely save your credentials locally.”
  • [probe] https://duckdb.org/docs/installation/“official CLI documented at https://duckdb.org/docs/installation/”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [probe] https://motherduck.com/openapi.json“PROBE openapi: HTTP 200 at https://motherduck.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://motherduck.com/docs/getting-started/“Connect to MotherDuck using official drivers and APIs for various programming languages.”
  • [claimed-docs] https://motherduck.com/docs/concepts/architecture-and-capabilities.md“DuckDB SDKs: Python, Node.js, Go, Rust, R, Java”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”
  • [probe] https://motherduck.com/llms.txt“PROBE runtime (recorded 2026-09-06): MotherDuck publishes an agentskills.io-conformant discovery manifest at /.well-known/agent-skills/index.json (schema schemas.agentskills.io/discovery/0.2.0) listing machine-readable skills with digests, alongside /.well-known/mcp.json and an every-page-as-markdown convention — agent-oriented docs as a first-class surface.”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“With the remote MCP server, your agent can: - Execute read-only and read-write SQL against your databases”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“To restrict your AI assistant to read-only access, see Restricting to read-only access”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“The remote MCP server exposes both read-only and read-write tools.”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“With the remote MCP server, your agent can: - Execute read-only and read-write SQL against your databases”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“You can limit MotherDuck's ability to interact with your local environment using SaaS Mode”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/sharing-data.md“Sharing data with specific preset roles or accounts in your organization. This is popular with data application builders that need to isolate tenants.”
  • [claimed-docs] https://motherduck.com/docs/integrations/cloud-storage/amazon-s3.md“Secrets are scoped to your user account and are not shared with other users in your organization.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”

Build against official SDKsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://motherduck.com/docs/concepts/architecture-and-capabilities.md“DuckDB SDKs: Python, Node.js, Go, Rust, R, Java”
  • [claimed-docs] https://motherduck.com/docs/getting-started/“Connect to MotherDuck using official drivers and APIs for various programming languages.”
  • [probe] https://motherduck.com/openapi.json“PROBE openapi: HTTP 200 at https://motherduck.com/openapi.json — contains "openapi" key”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“official MCP server documented at https://motherduck.com/docs/sql-reference/mcp/”
  • [probe] https://duckdb.org/docs/installation/“official CLI documented at https://duckdb.org/docs/installation/”
  • [probe] https://motherduck.com/docs/concepts/architecture-and-capabilities/“PROBE runtime (recorded 2026-09-06): the engine under MotherDuck ran FULLY keyless on a laptop — `duckdb -c` built a 1,000,000-row table and ran an aggregate GROUP BY (4 regions × 250,000 rows with summed revenue) in one command, a REAL analytical roundtrip with zero accounts or configuration.”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 118.4 ÷ 210 × 100 = 56.4

API quality30.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://motherduck.com/openapi.json“PROBE openapi: HTTP 200 at https://motherduck.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://motherduck.com/docs/getting-started/“Connect to MotherDuck using official drivers and APIs for various programming languages.”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://motherduck.com/openapi.json“PROBE openapi: HTTP 200 at https://motherduck.com/openapi.json — contains "openapi" key”
  • [probe] https://motherduck.com/llms.txt“PROBE runtime (recorded 2026-09-06): MotherDuck publishes an agentskills.io-conformant discovery manifest at /.well-known/agent-skills/index.json (schema schemas.agentskills.io/discovery/0.2.0) listing machine-readable skills with digests, alongside /.well-known/mcp.json and an every-page-as-markdown convention — agent-oriented docs as a first-class surface.”
  • [probe] https://motherduck.com/llms.txt“PROBE llms.txt: HTTP 200 at https://motherduck.com/llms.txt # MotherDuck MotherDuck is a modern serverless data warehouse built on DuckDB. It's faster and significantly less expen”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

  • [claimed-docs] https://motherduck.com/docs/getting-started.md“Develop and iterate locally, then share and scale in the cloud when you need it.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“You can limit MotherDuck's ability to interact with your local environment using SaaS Mode”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“To restrict your AI assistant to read-only access, see Restricting to read-only access”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck.md“You can limit MotherDuck's ability to interact with your local environment using \`SaaS Mode\`”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://motherduck.com/openapi.json“PROBE openapi: HTTP 200 at https://motherduck.com/openapi.json — contains "openapi" key”

API quality = 21.0 ÷ 70 × 100 = 30.0

Openness16.2/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Connect to MotherDuck using official drivers and APIs for various programming languages.”
  • [claimed-docs] https://motherduck.com/docs/concepts/architecture-and-capabilities.md“DuckDB SDKs: Python, Node.js, Go, Rust, R, Java”
  • [claimed-docs] https://motherduck.com/docs/getting-started/mcp-getting-started.md“The MotherDuck remote MCP Server lets you analyze your data using natural language and generate interactive visualizations, all without writing SQL.”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“With the remote MCP server, your agent can: - Execute read-only and read-write SQL against your databases”
  • [probe] https://motherduck.com/openapi.json“PROBE openapi: HTTP 200 at https://motherduck.com/openapi.json — contains "openapi" key”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”
  • [claimed-docs] https://motherduck.com/docs/about-motherduck/billing/monitoring-usage.md“MotherDuck provides SQL views and a billing dashboard to help you understand your compute and storage consumption.”

Export all of my data in open formats and leaveweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://motherduck.com/docs/getting-started.md“Upload a local DuckDB database file to MotherDuck cloud storage.”
  • [claimed-docs] https://motherduck.com/docs/getting-started.md“Develop and iterate locally, then share and scale in the cloud when you need it.”
  • [claimed-docs] https://motherduck.com/docs/concepts/architecture-and-capabilities.md“DuckDB SDKs: Python, Node.js, Go, Rust, R, Java”
  • [claimed-docs] https://motherduck.com/docs/getting-started/“Load your data from other databases and object storage”
  • [probe] https://motherduck.com/docs/concepts/architecture-and-capabilities/“PROBE runtime (recorded 2026-09-06): the engine under MotherDuck ran FULLY keyless on a laptop — `duckdb -c` built a 1,000,000-row table and ran an aggregate GROUP BY (4 regions × 250,000 rows with summed revenue) in one command, a REAL analytical roundtrip with zero accounts or configuration.”

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [community] https://hn.algolia.com/api/v1/items/43782406“User confusion about product scope: "Will this be available in duckdb -ui? Is mother duck editor features available on-prem? My understanding is that mother duck is a data warehouse sass."”
  • [claimed-docs] https://motherduck.com/docs/getting-started.md“Develop and iterate locally, then share and scale in the cloud when you need it.”
  • [probe] https://motherduck.com/llms.txt“PROBE llms.txt: HTTP 200 at https://motherduck.com/llms.txt # MotherDuck MotherDuck is a modern serverless data warehouse built on DuckDB. It's faster and significantly less expen”

Openness = 16.2 ÷ 100 × 100 = 16.2

Built-in AI56.2/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Generate interactive, shareable dashboards from natural language prompts”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Build a Dive with a chart of our top 10 products by sales volume. Use MotherDuck's brand colors”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Add a filter for the US region only”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“you iterate conversationally ("add a filter for US region", "switch to a bar chart") and the Viewer updates in place.”
  • [claimed-docs] https://motherduck.com/docs/getting-started/mcp-getting-started.md“The MotherDuck remote MCP Server lets you analyze your data using natural language and generate interactive visualizations, all without writing SQL.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“you can refine it through conversation: "Add a filter for the US region only"”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“You iterate conversationally (_"add a filter for US region"_, _"switch to a bar chart"_) and the Viewer updates in place.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Change the chart to a stacked bar chart”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Run Python jobs on a schedule for ingest, transformation, and operational tasks”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“Read and write Guides — markdown documents that capture your org's metric definitions, join conventions, and domain context, so agents produce accurate SQL without repetitive prompting”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“With the remote MCP server, your agent can: - Execute read-only and read-write SQL against your databases”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 7 (quality) × 0.6 (partial) = 12.6 of 30 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Generate interactive, shareable dashboards from natural language prompts”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Build a Dive with a chart of our top 10 products by sales volume. Use MotherDuck's brand colors”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Add a filter for the US region only”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“you iterate conversationally ("add a filter for US region", "switch to a bar chart") and the Viewer updates in place.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“you can refine it through conversation: "Add a filter for the US region only"”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“You iterate conversationally (_"add a filter for US region"_, _"switch to a bar chart"_) and the Viewer updates in place.”
  • [claimed-docs] https://motherduck.com/docs/getting-started/mcp-getting-started.md“The MotherDuck remote MCP Server lets you analyze your data using natural language and generate interactive visualizations, all without writing SQL.”
  • [claimed-docs] https://motherduck.com/docs/getting-started/“Analyze your data with natural language using the remote MCP Server”

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Generate interactive, shareable dashboards from natural language prompts”
  • [claimed-docs] https://motherduck.com/docs/getting-started/“Analyze your data with natural language using the remote MCP Server”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Build a Dive with a chart of our top 10 products by sales volume. Use MotherDuck's brand colors”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“you iterate conversationally ("add a filter for US region", "switch to a bar chart") and the Viewer updates in place.”
  • [claimed-docs] https://motherduck.com/docs/getting-started/mcp-getting-started.md“The MotherDuck remote MCP Server lets you analyze your data using natural language and generate interactive visualizations, all without writing SQL.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“you can refine it through conversation: "Add a filter for the US region only"”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“You iterate conversationally (_"add a filter for US region"_, _"switch to a bar chart"_) and the Viewer updates in place.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/ai-and-motherduck/dives/“Change the chart to a stacked bar chart”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”
  • [probe] https://motherduck.com/docs/sql-reference/mcp/“PROBE runtime (recorded 2026-09-06): a keyless JSON-RPC initialize POST to the hosted remote MCP server https://api.motherduck.com/mcp returned HTTP 401 with WWW-Authenticate Bearer resource_metadata=https://api.motherduck.com/.well-known/oauth-protected-resource/mcp — the managed MCP endpoint is live and speaks the MCP OAuth flow.”
  • [probe] https://motherduck.com/llms.txt“PROBE runtime (recorded 2026-09-06): MotherDuck publishes an agentskills.io-conformant discovery manifest at /.well-known/agent-skills/index.json (schema schemas.agentskills.io/discovery/0.2.0) listing machine-readable skills with digests, alongside /.well-known/mcp.json and an every-page-as-markdown convention — agent-oriented docs as a first-class surface.”

Built-in AI = 50.6 ÷ 90 × 100 = 56.2

Automation15.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Load your data from other databases and object storage”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“Execute read-only and read-write SQL against your databases”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/loading-data-into-motherduck.md“Load a DuckDB database into MotherDuck: Upload a local DuckDB database file to MotherDuck cloud storage.”
  • [claimed-docs] https://motherduck.com/docs/key-tasks/loading-data-into-motherduck.md“Learn to load a table from your PostgreSQL or MySQL database into MotherDuck.”
  • [claimed-docs] https://motherduck.com/docs/integrations/cloud-storage/amazon-s3.md“You can safely store your Amazon S3 credentials in MotherDuck for convenience by creating a SECRET object”
  • [claimed-docs] https://motherduck.com/docs/sql-reference/mcp.md“With the remote MCP server, your agent can: - Execute read-only and read-write SQL against your databases”
  • [probe] https://github.com/motherduckdb/mcp-server-motherduck“PROBE runtime (recorded 2026-09-06): the official mcp-server-motherduck (pypi, via uvx) completed a FULL keyless stdio initialize handshake (serverInfo mcp-server-motherduck 1.0.8) against an in-memory DuckDB, then executed a REAL analytical SQL query through MCP tools/call execute_query — an aggregate GROUP BY returning 2 rows with counts and sums — the complete agent path with no MotherDuck account.”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Run Python jobs on a schedule for ingest, transformation, and operational tasks”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://motherduck.com/docs/getting-started/“Run Python jobs on a schedule for ingest, transformation, and operational tasks”

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 12.0 ÷ 80 × 100 = 15.0