Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

WorkbookAPI

NPM · WORKBOOKAPI-MCP

Check and calculate local Excel workbooks with AI agents. Files stay on your machine.

Available components

+3 this week 75 Trust /100

Last scanned (23 hours ago)

Scores higher than 51% of npm servers

Category Data and Analytics

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency19
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 833 tokens (~208/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 89% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 18 Nov 26 +1
    • Malware scan: unverified → pass ▲ security
    • Package version: 0.1.4 → 0.1.5 functional
  • 17 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.1.3 → 0.1.4 functional
  • 16 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.1.2 → 0.1.3 functional
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/workbookapi-mcp@0.1.5

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~833 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
calculate ~221

Use to calculate one scenario from a local workbook with changed constant inputs and selected cells, ranges or defined names as outputs. Returns full-precision numbers, strings, booleans, null for direct blanks and {error: code} for spreadsheet errors; named references to blanks return 0, dates are serial numbers in the workbook's date system and ranges are arrays of rows. Each call starts from the original workbook and includes compatibility warnings; formula cells cannot be inputs. Responses are capped at 20000 bytes including both copies; oversized results return an explicit error.

NameTypeReqDescription
inputsobjectyesSingle constant or blank cells Sheet!A1, or defined names referring to one cell, mapped to numbers, strings or booleans.
outputsarrayyesSheet!A1, Sheet!A1:B5 or defined names; at most 10,000 output cells total.
pathstringyesLocal workbook path (absolute recommended), at most 50 MiB; .xlsx, .xlsm, .xltx or .xltm.

No output schema declared.

No examples provided.

check_workbook ~183

Use before trusting a workbook's calculations to compare recalculated formulas with Excel's saved values. Returns compared/matching totals, up to 200 mismatches with formula, saved/recalculated values and cause, feature flags, skipped counts, engine (the first 8 lowercase hex characters of the loaded binary's SHA-256), the workbook's dateSystem ("1900" or "1904"), and load/recalculation milliseconds. Dates are serial numbers in the workbook's date system. Above the 20000-byte response budget, mismatch details are shortened with an explicit message and totals retained. Only eligible cached formulas are compared; a matching check does not cover skipped cells or unsupported features.

NameTypeReqDescription
pathstringyesLocal workbook path (absolute recommended), at most 50 MiB; .xlsx, .xlsm, .xltx or .xltm.

No output schema declared.

No examples provided.

describe_workbook ~190

Use to discover sheets, used ranges, defined names and the workbook's dateSystem ("1900" or "1904") before choosing inputs and outputs. Dates are serial numbers in the workbook's date system. Names include values up to 100 cells, or range address and dimensions for larger blocks (expression arrays have a null address). Pass sheet for referenced constant or blank inputs and terminal formula outputs. Lists are capped at 100 entries. Above the 20000-byte response budget including both copies, named values are omitted with valuesOmitted: true; discovery lists may be shortened with an explicit message. Static discovery can miss dynamic or structured references.

NameTypeReqDescription
pathstringyesLocal workbook path (absolute recommended), at most 50 MiB; .xlsx, .xlsm, .xltx or .xltm.
sheetstring–Sheet name for input/output candidate discovery.

No output schema declared.

No examples provided.

run_scenarios ~239

Use to compare many input sets for the same workbook and outputs in one call. Returns indexed rows with values or errors, warnings and elapsed milliseconds. Dates are serial numbers in the workbook's date system. Each scenario starts from the original workbook and all its outputs share one recalculation. Runs stop at 10,000 scenarios, 100,000 output values, 20000 bytes including both response copies, cancellation or the time budget (55 seconds, with a 60-second hard deadline), reporting completed count and truncation. An engine crash during a scenario adds an error row counted in completed and stops the run; a crash before scenarios start returns an error. Resume by sending scenarios.slice(completed); check truncationReason before retrying and reduce outputs for output limits.

NameTypeReqDescription
outputsarrayyesSheet!A1, Sheet!A1:B5 or defined names; at most 10,000 output cells total.
pathstringyesLocal workbook path (absolute recommended), at most 50 MiB; .xlsx, .xlsm, .xltx or .xltm.
scenariosarrayyes–

No output schema declared.

No examples provided.

Install

How do I install the WorkbookAPI MCP server?

WorkbookAPI runs locally as an npm package, launched with npx -y workbookapi-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · workbookapi-mcp

# add to Claude Code
claude mcp add com-workbookapi-mcp -- npx -y workbookapi-mcp
Common questions

What is the WorkbookAPI MCP server?

WorkbookAPI is an MCP server listed in the public MCP registry as com.workbookapi/mcp. Check and calculate local Excel workbooks with AI agents. Files stay on your machine. This page covers its npm package (workbookapi-mcp).

Is the WorkbookAPI MCP server safe to use?

WorkbookAPI scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the WorkbookAPI MCP server expose?

WorkbookAPI exposes 4 tools: check_workbook, describe_workbook, calculate, run_scenarios. Their descriptions and schemas cost roughly 833 tokens of context every time the server is loaded.

Is the WorkbookAPI MCP server still maintained?

WorkbookAPI is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the WorkbookAPI MCP server under?

WorkbookAPI declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the WorkbookAPI MCP server?

VerifyMCP ran 15 checks on WorkbookAPI, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about WorkbookAPI: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.