excel-mcp-server
[ tools: 6 ][ checks: 11 ][ latency: 4ms ]
87/100(B)
npx -y @negokaz/excel-mcp-server
check breakdown
✓Tools exposed — Server exposed 6 tools.
• excel_copy_sheet
• excel_create_table
• excel_describe_sheets
• excel_format_range
• excel_read_sheet
• excel_write_to_sheet
✓Input schemas valid — All tools have a valid JSON-Schema input definition.
!Input schema quality — 6 schema-quality issue(s) across 6 tool(s).
excel_copy_sheet: inputSchema.additionalProperties is not set to false (extra args pass through silently)
excel_create_table: inputSchema.additionalProperties is not set to false (extra args pass through silently)
excel_describe_sheets: inputSchema.additionalProperties is not set to false (extra args pass through silently)
excel_format_range: inputSchema.additionalProperties is not set to false (extra args pass through silently)
excel_read_sheet: inputSchema.additionalProperties is not set to false (extra args pass through silently)
excel_write_to_sheet: inputSchema.additionalProperties is not set to false (extra args pass through silently)
→ Declare `required` for every schema that has properties, so agents know which params are mandatory.
→ Give every property a `description` and a concrete `type` (avoid bare `{}` placeholders).
→ Set `additionalProperties: false` on the top-level inputSchema so models can't silently pass extra, unvalidated arguments.
!Output schemas — No tools declare an outputSchema.
→ Optional: declare outputSchema for tools with structured results so agents can validate/parse output reliably.
✓Duplicate tool names — All tool names are unique.
✓Tool naming — All tool names use spec-legal characters.
!Descriptions — 2 description issue(s) found.
excel_create_table: description adds nothing beyond the tool name ("Create a table in the Excel sheet")
excel_write_to_sheet: description adds nothing beyond the tool name ("Write values to the Excel sheet")
→ Descriptions are the model's only guide to when/how to call a tool — treat them as prompt engineering.
→ Describe every tool and every parameter, including units, formats, and constraints.
→ Each tool's description should say something the name doesn't, and should be unique to that tool.
!Tool annotations — Annotation coverage 80% (24/30 hint fields set).
Some tools set a few hints but not all of title/readOnlyHint/destructiveHint/idempotentHint/openWorldHint.
→ Add annotations: title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint.
→ These let clients gate risky calls and give agents/users a friendly display name — optional but valuable.
!Tool titles — 6 of 6 tool(s) have no title.
• excel_copy_sheet: no top-level title (or annotations.title)
• excel_create_table: no top-level title (or annotations.title)
• excel_describe_sheets: no top-level title (or annotations.title)
• excel_format_range: no top-level title (or annotations.title)
• excel_read_sheet: no top-level title (or annotations.title)
• excel_write_to_sheet: no top-level title (or annotations.title)
→ Declare a top-level `title` on each tool — it gives clients a friendly display name distinct from the machine-readable `name`.
→ `annotations.title` (the older location) is also accepted, but the top-level `title` field is now the spec-preferred place for it.
!Server instructions — No top-level instructions declared.
→ Declare instructions to guide agents on when/how to use this server.
→ Return a non-empty `instructions` string in your InitializeResult — most SDKs let you set this alongside serverInfo.
✓Handshake + list latency — tools/list responded in 4ms.
add the badge
Paste into your README:
[](https://scoremcp.dev/servers/excel-mcp-server)