# SheetShift

> Convert and clean tables: CSV, JSON, dedupe, stats. Free.

- name: io.github.everyai-com/sheet-shift
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 89/100 flags: duplicate-repo
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Fsheet-shift
- tools: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Fsheet-shift/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "sheet-shift": {
      "type": "http",
      "url": "https://sheet-shift.magicteams.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-94% +updated-18d-ago -duplicate-repo(15 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list carries no ttlMs, so clients re-fetch it

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,137 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 8 tool changes in 30 days
- fail `stability.rug_pull`: 8 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 1,137 tokens to load them all
- tool set hash: 7fafac1f0f5d1e05a17b83b2be810588
- tools last changed: 2026-10-10T11:18:28.935Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.everyai-com/sheet-shift.svg)](https://protogrid.dev/servers/io.github.everyai-com/sheet-shift)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-10 `split_column` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Split a column into multiple columns by a delimiter. Use when you need to divide a single column into multiple columns based on a specific delimiter. Do NOT use when you need to convert data types or clean data; use convert_table or clean_table instead.
  - after: Split one column into several columns on a delimiter (e.g. 'full name' on a space), inserted in place; short rows are padded with empty cells. Returns the table in the same format. Use when one column packs several values. Do NOT use to clean or change format; use clean_table or convert_table.
- 2026-10-10 `column_stats` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Calculate statistics over one column in a table. Use when needing summary statistics for a single column; NOT for multi-column analysis. Use 'convert_table' for transformations.
  - after: Compute one statistic over a single column: sum, avg, min or max (numeric, rounded to 2 dp, blanks ignored), count of non-empty cells, or the sorted distinct values. Use for quick answers like 'total of the price column'. Do NOT use to reshape the table; use split_column or convert_table.
- 2026-10-10 `clean_table` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Clean a table string by trimming cells, dropping empty rows, and deduplicating rows. Use when preparing data for analysis; NOT for transforming data types. Use convert_table to change data types.
  - after: Clean a table: trim whitespace in cells, drop fully empty rows, and optionally remove duplicate rows; returns the table in the same format with before/after row counts. Use when preparing messy pasted data. Do NOT use to change format; use convert_table.
- 2026-10-10 `convert_table` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Convert a table string between CSV, TSV, JSON and Markdown. Use when you need to change the table format. Do NOT use when you need to clean the table; use clean_table instead.
  - after: Convert a table from CSV, TSV or JSON into CSV, TSV, JSON (array of objects) or a Markdown table. Cell values are kept as text. Use when the user wants the same table in another format. Do NOT use to trim, dedupe or drop rows; use clean_table.
- 2026-10-06 `split_column` changed (title, description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Split one column on a delimiter into new columns.
  - after: Split a column into multiple columns by a delimiter. Use when you need to divide a single column into multiple columns based on a specific delimiter. Do NOT use when you need to convert data types or clean data; use convert_table or clean_table instead.
- 2026-10-06 `column_stats` changed (title, description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Sum/avg/min/max/count/distinct over one column (name or 0-based index).
  - after: Calculate statistics over one column in a table. Use when needing summary statistics for a single column; NOT for multi-column analysis. Use 'convert_table' for transformations.
- 2026-10-06 `clean_table` changed (title, description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Trim cells, drop empty rows, dedupe rows in a table string.
  - after: Clean a table string by trimming cells, dropping empty rows, and deduplicating rows. Use when preparing data for analysis; NOT for transforming data types. Use convert_table to change data types.
- 2026-10-06 `convert_table` changed (title, description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Convert a table string between CSV, TSV, JSON and Markdown.
  - after: Convert a table string between CSV, TSV, JSON and Markdown. Use when you need to change the table format. Do NOT use when you need to clean the table; use clean_table instead.

Full history: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Fsheet-shift/changes

## Remotes

- https://sheet-shift.magicteams.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.942029)

## Packages

_none_

## Tools (4)

- `clean_table`: Clean a table: trim whitespace in cells, drop fully empty rows, and optionally remove duplicate rows; returns the table in the same format with before/after row counts. Use when preparing messy pasted data. Do NOT use to change format; use convert_table.
- `column_stats`: Compute one statistic over a single column: sum, avg, min or max (numeric, rounded to 2 dp, blanks ignored), count of non-empty cells, or the sorted distinct values. Use for quick answers like 'total of the price column'. Do NOT use to reshape the table; use split_column or convert_table.
- `convert_table`: Convert a table from CSV, TSV or JSON into CSV, TSV, JSON (array of objects) or a Markdown table. Cell values are kept as text. Use when the user wants the same table in another format. Do NOT use to trim, dedupe or drop rows; use clean_table.
- `split_column`: Split one column into several columns on a delimiter (e.g. 'full name' on a space), inserted in place; short rows are padded with empty cells. Returns the table in the same format. Use when one column packs several values. Do NOT use to clean or change format; use clean_table or convert_table.