# sift (pypi · sift-cli)

Runs a command, keeps every byte on disk, returns only the lines that matter

- Trust score: 89/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `sift-cli`: 89/100 (this document), [markdown](https://verifymcp.io/servers/slymnysr-sift/sift-cli.md), [page](https://verifymcp.io/servers/slymnysr-sift/sift-cli)

## Channel facts

- Registry: `pypi`
- Package: `sift-cli`
- Version: `1.1.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to slymnysr/sift).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 43 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1857 tokens (~265/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the sift MCP server?

sift runs locally as a PyPI package, launched with uvx sift-cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add slymnysr-sift -- uvx sift-cli
```

### Cursor

```json
{
  "mcpServers": {
    "slymnysr-sift": {
      "command": "uvx",
      "args": [
        "sift-cli"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "slymnysr-sift": {
      "command": "uvx",
      "args": [
        "sift-cli"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add slymnysr-sift -- uvx sift-cli
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "slymnysr-sift": {
      "type": "local",
      "command": [
        "uvx",
        "sift-cli"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add slymnysr-sift --command uvx --arg sift-cli
```

### Hermes

```yaml
mcp_servers:
  slymnysr-sift:
    command: "uvx"
    args: ["sift-cli"]
```

### Netclaw

```json
{
  "McpServers": {
    "slymnysr-sift": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "sift-cli"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add slymnysr-sift -t stdio -c uvx -a sift-cli
```

### Other

```json
{
  "mcpServers": {
    "slymnysr-sift": {
      "command": "uvx",
      "args": [
        "sift-cli"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 88, +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.

### 2026-10-19 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 85, +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.

### 2026-10-13 (score 84, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-12 (score 69, −12)

- [security regression] Malware scan: pass → unverified

### 2026-10-07 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 37. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (7)

### `run` (~205 tokens)

Run a command

Run a shell command and return only the lines that mattered instead of all of its output. Every byte is kept on disk and never enters the conversation, so a 5,000-line test run costs a few dozen lines of context -- and goes on costing nothing on every later turn, because tool results are re-sent with the rest of the transcript. The lines shown are the command's own, byte for byte; each gap states how many lines it stands for, and `peek` with the returned handle brings any range back in full. Prefer this over a plain shell tool whenever the output may be long or noisy. When you already know what you are looking for -- a symbol, a test name, an error code -- pass it as `keep` and every line containing it comes back whatever else was chosen.

Input parameters:

- `background` (boolean)
- `budget`
- `command` (string, required)
- `cwd`
- `keep`
- `timeout`

Output parameters:

- `result` (string)

### `follow` (~254 tokens)

Follow a background run

Return what a background command has printed since the last time you asked, and nothing you have already been shown. Use it with the handle from a `run` call made with `background`. The lines keep the numbers they have in the whole run, so `peek` on any of them returns that same line; a stretch that was only progress comes back as a gap saying how many lines it stands for, and a quiet minute comes back as nothing at all rather than as filler. Set `stop` when you are done with the command: it ends it, and everything it started, and returns the last of the output. Always stop a command you are finished with -- a background command left alone keeps running.
With `everything` it answers about every run still going in one call, which is what to use when you started three things and want to know where they are. With `wait` it holds until something is actually said rather than coming back empty: an empty answer is a tool result that stays in the conversation for the rest of it, so waiting once costs less than asking five times.

Input parameters:

- `everything` (boolean)
- `handle`
- `stop` (boolean)
- `wait` (number)

Output parameters:

- `result` (string)

### `outline` (~140 tokens)

Outline a file

Return what a file declares -- its types, functions, exports, targets and settings -- without their bodies, so that reading a 2,000-line source file costs a page. This is the machine behind `run` asked a different question: it holds no table of languages and never reads the suffix, so it answers about Rust, Haskell, a Makefile, a config file with no extension, or a language that did not exist last year. Lines come from the file byte for byte, and `peek` on the same path returns any range of it in full.

Input parameters:

- `budget`
- `keep`
- `path` (string, required)

Output parameters:

- `result` (string)

### `digest` (~154 tokens)

Digest a file

Read a file and return a distilled view of what is in it instead of its text. This is for anything already written down that would flood the conversation if opened whole: a log, a saved build or CI transcript, a test report, a crash dump, a long JSON export. The server opens the file, so its contents never enter the conversation -- a 40,000-line log costs a screenful -- and every line shown is the file's own, byte for byte, with `peek` on the same path returning any range in full. Use `outline` instead when the file is source code and the question is what it declares.

Input parameters:

- `budget`
- `keep`
- `path` (string, required)

Output parameters:

- `result` (string)

### `tool` (~181 tokens)

Run a dense tool

Run one of three dense tools and return a distilled view of what it printed: `sg` (ast-grep) for structural search, `diff` (difftastic) for a diff that can tell a reindent from a change, `loc` (scc) for the size of a tree. Each of them answers a question *without opening the file* -- reach for `sg` instead of reading candidates to find where a shape occurs, and `loc` instead of listing a directory to size it. Their output is large by nature and is distilled like anything else, so a 4,000-line structural search costs a screenful with every byte still reachable through `peek`. A tool this machine does not have says so and says what it is called; nothing is installed for you.

Input parameters:

- `args`
- `name` (string, required)

Output parameters:

- `result` (string)

### `digest_many` (~110 tokens)

Digest several files

Digest several files in one call, asked at the same time. Use it whenever there is more than one file to read: four logs cost four waits asked one by one and roughly one wait asked together, and come back as one tool result instead of four. Each file keeps its own last line saying which it is, and a file that cannot be read says so in its place rather than taking the others down with it.

Input parameters:

- `budget`
- `keep`
- `paths` (array, required)

Output parameters:

- `result` (string)

### `peek` (~167 tokens)

Peek at a capture

Return the exact original lines of a capture or a file, byte for byte, with the line numbers they had there. Use it with the handle at the end of a `run` result, or with any path, to open up a gap that a view left behind. A range reaching past the end is clamped rather than refused, and with no range at all it returns the whole thing. With `grep` it searches instead: every line matching your pattern comes back with a few lines of context around it, which is the way into a gap when you know the word you want but not the line number.

Input parameters:

- `around` (integer)
- `cap` (integer)
- `first`
- `grep`
- `handle` (string, required)
- `last`

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/slymnysr-sift/sift-cli#diagnostics

## Score history

- 2026-10-23: 89
- 2026-10-22: 88
- 2026-10-21: 88
- 2026-10-20: 87
- 2026-10-19: 87
- 2026-10-18: 86
- 2026-10-17: 86
- 2026-10-16: 86
- 2026-10-15: 85
- 2026-10-14: 85
- 2026-10-13: 84
- 2026-10-12: 69
- 2026-10-07: 81
- 2026-10-04: 80
- 2026-10-03: 76
- 2026-10-02: 76
- 2026-10-01: 76
- 2026-09-30: 76
- 2026-09-29: 61
- 2026-09-28: 66
- 2026-09-27: 51
- 2026-09-26: 51
- 2026-09-25: 25
- 2026-09-24: 22
- 2026-09-23: 22
- 2026-09-22: 22
- 2026-09-21: 22
- 2026-09-20: 22
- 2026-09-19: 22
- 2026-09-18: 22

## Common questions

### What is the sift MCP server?

sift is an MCP server listed in the public MCP registry as io.github.slymnysr/sift. Runs a command, keeps every byte on disk, returns only the lines that matter. This page covers its PyPI package (sift-cli).

### Is the sift MCP server safe to use?

sift scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. 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 sift MCP server expose?

sift exposes 7 tools: run, follow, outline, digest, tool, and 2 more. Their descriptions and schemas cost roughly 1,211 tokens of context every time the server is loaded.

### Is the sift MCP server still maintained?

sift is still listed as active in the MCP registry. We last reached this channel on 23 October 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 sift MCP server under?

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

## Links

- PyPI project: https://pypi.org/project/sift-cli/
- Socket report: https://socket.dev/pypi/package/sift-cli
- Repository: https://github.com/slymnysr/sift
- Changelog RSS feed: https://verifymcp.io/servers/slymnysr-sift/sift-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/slymnysr-sift/sift-cli.json
- HTML version of this page: https://verifymcp.io/servers/slymnysr-sift/sift-cli