Files
PaperClipAI/packages/google-sheets-mcp-server/src/tools.test.ts
T
DottaandPaperclip 7b35de65aa feat(mcp) [split 1/8]: add fixture demo servers (#9556)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Governed MCP access spans contracts, runtime enforcement, adapters,
UI surfaces, and operator verification
> - The parity reference PR #9534 is too large for effective automated
or human review
> - The feature therefore needs a linear stack whose individual diffs
stay below the 100-file review limit
> - This pull request is split 1/8 and focuses on fixture and demo MCP
servers
> - The benefit is a standalone, testable review boundary while
preserving byte-for-byte parity at the top of the stack

## Linked Issues or Issue Description

- Related parity reference: #9534
- Problem: Developers need deterministic local MCP fixtures and visible
demo servers without pulling in the governed production runtime.
- Proposed solution: Adds the Google Sheets and KV demo MCP packages,
fixture catalog/servers, smoke harness, guide, and the root
smoke/typecheck registration hunks.
- Alternatives considered: keeping #9534 as one 403-file review, or
rewriting the feature to manufacture seams; both were rejected in favor
of path extraction plus compile-driven boundary moves.
- Roadmap alignment: this advances the existing governed MCP/tool-access
work already represented by #9534; it does not introduce a separate
roadmap initiative.
- Stack position: base branch is `master`.
- Merge policy: merge bottom-up, in order, only after the complete
eight-PR stack has been reviewed and the top-of-stack parity gate
remains empty.
- Requested review: QA for fixture and smoke coverage; Greptile on every
PR.

## What Changed

- Adds the Google Sheets and KV demo MCP packages, fixture
catalog/servers, smoke harness, guide, and the root smoke/typecheck
registration hunks.
- Keeps this PR below 100 changed files and independently typecheckable.
- Preserves the final tree from #9534 when combined with the other seven
stack levels.

## Verification

- `pnpm typecheck`
- `pnpm --filter @paperclipai/google-sheets-mcp-server test` — 27 tests
passed
- `pnpm --filter @paperclipai/kv-demo-mcp-server test` — 12 tests passed

## Risks

- The new packages add dependencies that are intentionally not committed
to `pnpm-lock.yaml`, per repository policy.
- Stack risk: merging out of order can expose incomplete layers;
mitigate by following the documented bottom-up merge policy.
- Parity risk: later edits to an intermediate branch can drift from
#9534; mitigate by re-running the empty top-of-stack diff before merge.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex, exact model ID `gpt-5.4`; runtime-managed context
window; medium reasoning with repository, shell, Git, GitHub CLI, and
code-execution tools enabled.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] Internal references are omitted except the execution-plan link
explicitly required for this coordinated split stack
- [x] My branch name describes the change and contains no internal
Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge


## Stack Coordination

- Internal execution plan:
[PAP-13874](/PAP/issues/PAP-13874#document-plan)
- Parity reference: #9534
- Stack: #9556 → #9557 → #9558 → #9559 → #9560 → #9561 → #9562 → #9563
- Merge bottom-up only after full-stack review and an empty parity diff
at #9563.

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-07-14 12:56:21 -05:00

166 lines
6.4 KiB
TypeScript

import { describe, expect, it, vi } from "vitest";
import { createToolDefinitions } from "./tools.js";
import type { GoogleSheetsClient } from "./google-client.js";
import type { ToolResult } from "./tools.js";
function makeClient(): GoogleSheetsClient {
return {
listSpreadsheets: vi.fn().mockResolvedValue([
{ spreadsheetId: "sheet-1", title: "Budget", spreadsheetUrl: "https://docs.google.com/spreadsheets/d/sheet-1" },
]),
getSpreadsheetInfo: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
title: "Budget",
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/sheet-1",
sheets: [{ sheetId: 0, title: "Sheet1", index: 0, rowCount: 100, columnCount: 20 }],
}),
readValues: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
range: "Sheet1!A1:B2",
values: [["name", "amount"], ["paper", 12]],
}),
searchRows: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
range: "Sheet1!A1:B2",
query: "paper",
matches: [{ rowIndex: 2, values: ["paper", 12] }],
}),
appendRows: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
range: "Sheet1!A:B",
updatedRange: "Sheet1!A3:B3",
updatedRows: 1,
updatedCells: 2,
}),
updateValues: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
range: "Sheet1!A2:B2",
updatedRange: "Sheet1!A2:B2",
updatedRows: 1,
updatedCells: 2,
}),
addSheetTab: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
sheet: { sheetId: 7, title: "New", index: 1, rowCount: 100, columnCount: 26 },
}),
clearValues: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
range: "Sheet1!A2:B2",
updatedRange: "Sheet1!A2:B2",
}),
deleteRows: vi.fn().mockResolvedValue({
spreadsheetId: "sheet-1",
sheetId: 0,
deletedRows: 2,
}),
};
}
function tools(client = makeClient()) {
return createToolDefinitions({
client,
allowedSpreadsheetIds: ["sheet-1"],
secretRedactions: ["secret-client@example.test", "-----BEGIN PRIVATE KEY-----\nabc\n-----END PRIVATE KEY-----"],
});
}
function getTool(name: string, client?: GoogleSheetsClient) {
const tool = tools(client).find((candidate) => candidate.name === name);
if (!tool) throw new Error(`Missing tool ${name}`);
return tool;
}
function responseText(response: ToolResult) {
const block = response.content.find((entry) => entry.type === "text");
return block?.type === "text" ? block.text : "";
}
describe("Google Sheets MCP tools", () => {
it("annotates tools with read, write, and destructive MCP risk hints", () => {
const byName = new Map(tools().map((tool) => [tool.name, tool]));
expect(byName.get("read_values")?.annotations).toMatchObject({ readOnlyHint: true });
expect(byName.get("append_rows")?.annotations).toMatchObject({ readOnlyHint: false, destructiveHint: false });
expect(byName.get("delete_rows")?.annotations).toMatchObject({ readOnlyHint: false, destructiveHint: true });
});
it("lists only allowlisted spreadsheets", async () => {
const client = makeClient();
const response = await getTool("list_spreadsheets", client).execute({});
expect(client.listSpreadsheets).toHaveBeenCalledWith(["sheet-1"]);
expect(responseText(response)).toContain("Budget");
});
it("allows calls for allowlisted spreadsheet IDs", async () => {
const client = makeClient();
const response = await getTool("read_values", client).execute({
spreadsheetId: "sheet-1",
range: "Sheet1!A1:B2",
});
expect(client.readValues).toHaveBeenCalledWith("sheet-1", "Sheet1!A1:B2");
expect(response.isError).toBeUndefined();
expect(responseText(response)).toContain("paper");
});
it("rejects calls outside the spreadsheet allowlist before calling Google", async () => {
const client = makeClient();
const response = await getTool("read_values", client).execute({
spreadsheetId: "sheet-2",
range: "Sheet1!A1:B2",
});
expect(response.isError).toBe(true);
expect(responseText(response)).toContain("not in the configured allowlist");
expect(client.readValues).not.toHaveBeenCalled();
});
it.each([
["get_spreadsheet_info", { spreadsheetId: "sheet-1" }, "getSpreadsheetInfo"],
["read_values", { spreadsheetId: "sheet-1", range: "Sheet1!A1:B2" }, "readValues"],
["search_rows", { spreadsheetId: "sheet-1", range: "Sheet1!A1:B2", query: "paper" }, "searchRows"],
["append_rows", { spreadsheetId: "sheet-1", range: "Sheet1!A:B", values: [["pen", 5]] }, "appendRows"],
["update_values", { spreadsheetId: "sheet-1", range: "Sheet1!A2:B2", values: [["pen", 6]] }, "updateValues"],
["add_sheet_tab", { spreadsheetId: "sheet-1", title: "New" }, "addSheetTab"],
["clear_values", { spreadsheetId: "sheet-1", range: "Sheet1!A2:B2" }, "clearValues"],
["delete_rows", { spreadsheetId: "sheet-1", sheetId: 0, startIndex: 1, endIndex: 3 }, "deleteRows"],
])("runs happy path for %s", async (toolName, input, clientMethod) => {
const client = makeClient();
const response = await getTool(toolName, client).execute(input);
expect(response.isError).toBeUndefined();
expect(client[clientMethod as keyof GoogleSheetsClient]).toHaveBeenCalled();
});
it("surfaces malformed Google range errors as tool errors", async () => {
const client = makeClient();
vi.mocked(client.readValues).mockRejectedValueOnce(new Error("Unable to parse range: Sheet1!bad"));
const response = await getTool("read_values", client).execute({
spreadsheetId: "sheet-1",
range: "Sheet1!bad",
});
expect(response.isError).toBe(true);
expect(responseText(response)).toContain("Unable to parse range");
});
it("does not echo service-account key material in tool errors", async () => {
const client = makeClient();
vi.mocked(client.readValues).mockRejectedValueOnce(
new Error("Auth failed for secret-client@example.test using -----BEGIN PRIVATE KEY-----\nabc\n-----END PRIVATE KEY-----"),
);
const response = await getTool("read_values", client).execute({
spreadsheetId: "sheet-1",
range: "Sheet1!A1:B2",
});
expect(response.isError).toBe(true);
expect(responseText(response)).not.toContain("secret-client@example.test");
expect(responseText(response)).not.toContain("PRIVATE KEY");
expect(responseText(response)).toContain("[REDACTED]");
});
});