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.

Siftdog

PYPI · SIFTDOG · SCANNED SEP 28

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

Available components

65 Trust /100
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 Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 4 of 56 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to khsarvar/siftdog). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • 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. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
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 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

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.

pypi · siftdog

# add to Claude Code
claude mcp add khsarvar-siftdog -- uvx siftdog
// .cursor/mcp.json
{
  "mcpServers": {
    "khsarvar-siftdog": {
      "command": "uvx",
      "args": [
        "siftdog"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "khsarvar-siftdog": {
      "command": "uvx",
      "args": [
        "siftdog"
      ]
    }
  }
}
# add to Codex CLI
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
    }
  }
}
# add to OpenClaw
openclaw mcp add khsarvar-siftdog --command uvx --arg siftdog
# ~/.hermes/config.yaml
mcp_servers:
  khsarvar-siftdog:
    command: "uvx"
    args: ["siftdog"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "khsarvar-siftdog": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "siftdog"
      ]
    }
  }
}
# add to Vellum
assistant mcp add khsarvar-siftdog -t stdio -c uvx -a siftdog
// mcp.json
{
  "mcpServers": {
    "khsarvar-siftdog": {
      "command": "uvx",
      "args": [
        "siftdog"
      ]
    }
  }
}
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.

  • 28 Sept 26 65

    First indexed and scored.

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 28 Sept 2026 · Analysed pypi/siftdog@0.3.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo khsarvar/siftdog
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/khsarvar/siftdog/.github/workflows/release.yml@refs/tags/v0.3.0
Rekor log index 2982850865
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:09638ea8d8bdc9281df9e1c53be0345d8b7ce505d9b644ea0029262954599f1f

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 56 packages
Packages resolved 56
Stale 3
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~551 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
siftdog_crawl ~169

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.

NameTypeReqDescription
allow_externalboolean–Follow links to other domains.
exclude_paths––Regexes matched against URL paths, e.g. ['/docs/.*'].
limitinteger–Maximum pages to return.
max_charsinteger–Maximum characters of content to return per page.
max_depthinteger–How many links deep to follow from the start.
select_paths––Regexes matched against URL paths, e.g. ['/docs/.*'].
urlstringyesThe page to start crawling from.
NameTypeReqDescription
resultstringyes–

No examples provided.

siftdog_extract ~84

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.

NameTypeReqDescription
formatstring–Output format of page content.
max_charsinteger–Maximum characters of content to return per page.
urlsarrayyes1 to 20 page URLs.
NameTypeReqDescription
resultstringyes–

No examples provided.

siftdog_map ~121

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.

NameTypeReqDescription
exclude_paths––Regexes matched against URL paths, e.g. ['/docs/.*'].
limitinteger–Maximum URLs to return.
max_depthinteger–How many links deep to follow from the start.
select_paths––Regexes matched against URL paths, e.g. ['/docs/.*'].
urlstringyesThe site or page to map from.
NameTypeReqDescription
resultstringyes–

No examples provided.

siftdog_search ~177

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.

NameTypeReqDescription
exclude_domains––Never return results from these domains.
include_domains––Only return results from these domains.
max_charsinteger–Maximum characters of content to return per page.
max_resultsinteger–Number of results.
querystringyesThe search query.
search_depthstring–'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.
topicstring–Use 'news' for current events.
NameTypeReqDescription
resultstringyes–

No examples provided.

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.