# Siftdog (pypi · siftdog)

Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- pypi · `siftdog`: 65/100 (this document), [markdown](https://verifymcp.io/servers/khsarvar-siftdog/siftdog.md), [page](https://verifymcp.io/servers/khsarvar-siftdog/siftdog)

## Channel facts

- Registry: `pypi`
- Package: `siftdog`
- Version: `0.3.0`
- 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 2026-09-28.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - 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.
  - 4 of 56 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to khsarvar/siftdog).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 637 tokens (~159/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

Siftdog runs locally as a PyPI package, launched with uvx siftdog. 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 khsarvar-siftdog -- uvx siftdog
```

### Cursor

```json
{
  "mcpServers": {
    "khsarvar-siftdog": {
      "command": "uvx",
      "args": [
        "siftdog"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "khsarvar-siftdog": {
      "command": "uvx",
      "args": [
        "siftdog"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add khsarvar-siftdog -- uvx siftdog
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add khsarvar-siftdog --command uvx --arg siftdog
```

### Hermes

```yaml
mcp_servers:
  khsarvar-siftdog:
    command: "uvx"
    args: ["siftdog"]
```

### Netclaw

```json
{
  "McpServers": {
    "khsarvar-siftdog": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "siftdog"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add khsarvar-siftdog -t stdio -c uvx -a siftdog
```

### Other

```json
{
  "mcpServers": {
    "khsarvar-siftdog": {
      "command": "uvx",
      "args": [
        "siftdog"
      ]
    }
  }
}
```

## 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.

### 2026-09-28 (score 65)

First indexed and scored.

## MCP tools (4)

### `siftdog_search` (~177 tokens)

Search the web and return ranked results with titles, URLs and relevant content.

Use this to find sources for a question or to discover pages about a topic. If you
already know the URLs, use siftdog_extract instead.

Input parameters:

- `exclude_domains`: Never return results from these domains.
- `include_domains`: Only return results from these domains.
- `max_chars` (integer): Maximum characters of content to return per page.
- `max_results` (integer): Number of results.
- `query` (string, required): The search query.
- `search_depth` (string): 'basic' returns search snippets; 'advanced' reads each page and returns its most relevant passages (slower, better content).
- `time_range`: Only return results from this recent period.
- `topic` (string): Use 'news' for current events.

Output parameters:

- `result` (string)

### `siftdog_extract` (~84 tokens)

Fetch web pages and return their main content as clean markdown or text.

Use this when you already have the URLs, for example from siftdog_search results.

Input parameters:

- `format` (string): Output format of page content.
- `max_chars` (integer): Maximum characters of content to return per page.
- `urls` (array, required): 1 to 20 page URLs.

Output parameters:

- `result` (string)

### `siftdog_crawl` (~169 tokens)

Crawl a website from a starting URL and return the content of the pages found.

Use this to read many pages of one site. For large sites, call siftdog_map first and
narrow the crawl with select_paths.

Input parameters:

- `allow_external` (boolean): Follow links to other domains.
- `exclude_paths`: Regexes matched against URL paths, e.g. ['/docs/.*'].
- `limit` (integer): Maximum pages to return.
- `max_chars` (integer): Maximum characters of content to return per page.
- `max_depth` (integer): How many links deep to follow from the start.
- `select_paths`: Regexes matched against URL paths, e.g. ['/docs/.*'].
- `url` (string, required): The page to start crawling from.

Output parameters:

- `result` (string)

### `siftdog_map` (~121 tokens)

List the URLs of a website without fetching their content.

Use this to see how a site is organised before extracting or crawling specific pages.

Input parameters:

- `exclude_paths`: Regexes matched against URL paths, e.g. ['/docs/.*'].
- `limit` (integer): Maximum URLs to return.
- `max_depth` (integer): How many links deep to follow from the start.
- `select_paths`: Regexes matched against URL paths, e.g. ['/docs/.*'].
- `url` (string, required): The site or page to map from.

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-09-28: 65

## Common questions

### What is the Siftdog MCP server?

Siftdog is an MCP server listed in the public MCP registry as io.github.khsarvar/siftdog. Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents. This page covers its PyPI package (siftdog).

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

Siftdog scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 28 September 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 Siftdog MCP server expose?

Siftdog exposes 4 tools: siftdog_search, siftdog_extract, siftdog_crawl, siftdog_map. Their descriptions and schemas cost roughly 551 tokens of context every time the server is loaded.

### Is the Siftdog MCP server still maintained?

Siftdog is still listed as active in the MCP registry. We last reached this channel on 28 September 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 Siftdog MCP server under?

Siftdog 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/siftdog/
- Socket report: https://socket.dev/pypi/package/siftdog
- Repository: https://github.com/khsarvar/siftdog
- Website: https://siftdog.com/
- Changelog RSS feed: https://verifymcp.io/servers/khsarvar-siftdog/siftdog.xml
- Changelog JSON feed: https://verifymcp.io/servers/khsarvar-siftdog/siftdog.json
- HTML version of this page: https://verifymcp.io/servers/khsarvar-siftdog/siftdog