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.

Unfret

PYPI · UNFRET-MCP · 2 COMPONENTS

Checks a store, marketplace seller or listing for scam signals before an agent buys, paid per check

−12 this week 57 Trust /100

Last scanned (16 hours ago)

Scores higher than 53% of PyPI servers

Category E-commerce

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 uv_build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 2 of 33 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability60
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 614 tokens (~204/item across 3 items; 3 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 Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 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
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 18 Nov 26 0
    • Schema quality: 177 → 204 ▼ functional
    • Package version: 0.1.1 → 0.2.0 functional
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
  • 14 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
    • Stability: unverified → 0.07 ▲ functional
    • Package version: 0.1.0 → 0.1.1 functional
  • 12 Nov 26 53

    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 21 Nov 2026 · Analysed pypi/unfret-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool uv_build

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

Dependencies 33 packages
Packages resolved 33
Stale 1
No linked repository 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 3 exposed · ~491 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
check_store ~341

Check a store or product page for scam, dropshipping and dark-pattern risk. Paid per call in USDC or wSOL. Pass page_content (the page's HTML) for marketplaces such as Amazon, which block server-side fetches. :param url: The store or product page URL. :param tier: quick (cheap checks, $0.01) or deep (everything incl. reverse image search, $0.20). :param policy: How cautious the returned action is: strict, balanced or lenient. :param page_content: The page's HTML, if available. :return: ``status`` (ok, not_paid, pending, unknown, unavailable), ``ok``, the ``verdict`` (action, risk_score, confidence, flags, and ``band``: what a shopper is shown, ``reliable`` "Looks fine", ``concerns`` "Worth a look", ``careful`` "Think twice" or ``junk_or_scam`` "Serious concerns") or ``error``, the payment, and ``next_step`` when there's something to do.

NameTypeReqDescription
page_content––The page's HTML, if you have it. Needed for marketplaces such as Amazon, which block fetches.
policystring–How cautious the returned action is; strict warns and blocks soonest.
tierstring–quick: rule checks on the page itself, $0.01. deep: everything, including an LLM reading of the page, reviews, domain age and reverse image search, $0.20.
urlstringyesThe store or product page URL (https).

Structured output declared, but exposes no named fields.

No examples provided.

explain_flag ~62

Explain what a flag in an Unfret verdict means, in one paragraph for the end user. :param flag_type: The flag's ``type``. :return: The explanation.

NameTypeReqDescription
flag_typestringyesA flag's `type` from a verdict.
NameTypeReqDescription
resultstringyes–

No examples provided.

get_pricing ~88

Unfret's current prices (free, no payment): the check tiers in dollars, and the live USDC and SOL amounts. :return: ``status``, ``ok`` and the price list (``x402``: ``quick_usd_micros``, ``deep_usd_micros``; ``usdc``; ``sol``), or ``error``.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Unfret MCP server?

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

pypi · unfret-mcp

# add to Claude Code
claude mcp add net-unfret-mcp -- uvx unfret-mcp
Common questions

What is the Unfret MCP server?

Unfret is an MCP server listed in the public MCP registry as net.unfret/mcp. Checks a store, marketplace seller or listing for scam signals before an agent buys, paid per check. This page covers its PyPI package (unfret-mcp).

Is the Unfret MCP server safe to use?

Unfret scores 57 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 Unfret MCP server expose?

Unfret exposes 3 tools: check_store, get_pricing, explain_flag. Their descriptions and schemas cost roughly 491 tokens of context every time the server is loaded.

Is the Unfret MCP server still maintained?

Unfret is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Unfret MCP server under?

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

What did VerifyMCP test on the Unfret MCP server?

VerifyMCP ran 15 checks on Unfret, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Unfret: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.