D2B – Spreadsheets for AI Agents

D2B launched a spreadsheet platform that gives AI agents typed, row-identified, versioned tables and returns results to humans as Excel in the original formatting, with every number traceable to its source. The service exposes an MCP endpoint at https://d2b.dev/mcp/ and Python and CLI clients, storing transforms content-addressed with a queryable DAG, snapshots, named versions, an op log, undo, and diffs between any two versions. Billing is metered in ops (one op = one write-side data operation such as row writes, transform runs, commits or version operations) and GB-months, with reads currently not billed and no LLM charge when calling from your own agent with your own LLM.

Take spreadsheets made for people in at the door, hand your agent typed, row-identified, versioned, governed tables, and return the result to humans as Excel in its original formatting. Not just answers — every number traceable to where it came from. claude mcp add d2b --transport http https://d2b.dev/mcp/ \ --header "Authorization: Bearer $D2B PAT" Codex / Cursor / VS Code / Claude Desktop → docs.d2b.dev/ja/mcp Letting an LLM write and run Python in a sandbox gets you an answer, but not how it got there — you can't trace it or run it again. D2B records the same work as transforms with lineage, so a changed input recomputes and every version can be restored. python from d2b import D2BClient client = D2BClient api key="d2b pat ...", base url="https://d2b.dev" wb = client.workbooks.create title="monthly-sales" "id" 1 a spreadsheet made for people in → typed tables raw kept, lineage from day one client.sources.upload wb, "sales 2026-06.xlsx", wait=True 2 logic as a transform — {{ arg }} bindings keep lineage client.transforms.create wb, name="agg/monthly", kind="sql", artifact name="product sales", template='CREATE TABLE "{{ artifact name }}" AS ' 'SELECT product, sum amount AS revenue FROM "{{ src }}" GROUP BY 1', args={"src": "sales"}, 3 back to humans as Excel, 4 a named, revertible version xlsx = client.export.tables wb, tables= "product sales" client.versions.commit wb, "2026-06" A foundation that survives an agent's mistakes: concurrent writes are caught, any number can be traced and rolled back, permissions hold at the data layer, and results go back to people as Excel. Transforms are stored content-addressed; the DAG is queryable upstream and down. Snapshots, named versions, an op log and undo — plus a diff between any two versions: unified diffs of the transforms, rows touched, and every artifact the change reaches. An agent can find out why a number moved, fix it, and compare. Every table is typed with row ids; writes require expected version, so concurrent edits are never silently overwritten. A per-table row JSON Schema is available at runtime for constrained decoding. mask / deny are enforced in the data layer — the same policy applies to SQL, export and MCP, with no side door. Audited. xlsx / csv, write-back into the original workbook's formatting, live per-row Excel formulas, export = branch → re-import = 3-way merge. Round trips on Excel users' own terms. Pull transforms SQL / Python , sheets, charts and opted-in base tables as CSV into a repository, review them in a pull request, push them back. Reviewing the SQL an AI wrote before it counts becomes an ordinary workflow. transforms/ sheets/ charts/ data/ plus d2b.json the merge-base hashes . git diff / PR. Transforms the chat agent wrote show up in the same place. Only what changed: re-run, PUT, 3-way merge. Refused when both sides moved --force overrides . The git sha becomes a named version. d2b pull --workbook WB --data customers transforms/ sheets/ charts/ data/ + d2b.json git add -A && git commit -m "pull from D2B" d2b push --dry-run d2b push --commit "$ git rev-parse --short HEAD " d2b github-workflow .github/workflows/d2b.yml push on merge, scheduled pull → PR Billing is metered in ops data operations and GB-months. Calls from your own agent with your own LLM carry no LLM charge — LLM usage is added only when you use D2B's built-in agent. Capability is identical on every plan. 1 op = one write-side data operation row writes, transform runs, commits, version operations . Reads are currently not billed. Mint a PAT and run one claude mcp add. Five minutes with the CLI or an SDK.