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.

ModelLens

PYPI · MODELLENS-MCP

See which models actually work: probe, rank and recommend across OpenAI-compatible gateways.

Available components

+3 this week 75 Trust /100

Last scanned (18 hours ago)

Scores higher than 68% of PyPI servers

Category AI and Machine Learning

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability76
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 510 tokens (~102/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
  • Stability observed for 16 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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (16)

  • Malware scan
  • 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

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 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

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

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 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.

  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

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/modellens-mcp@0.1.3

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 setuptools.build_meta

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

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~490 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
list_models ~98

List the models each configured endpoint advertises (GET {base_url}/models). Read-only network call to your own configured endpoints — no inference, no token cost. Use this FIRST, before probe/ranking, to see what is available. Returns model ids grouped by endpoint name; empty list if an endpoint is unreachable.

NameTypeReqDescription
containsstring–optional substring filter (matches model id)
limitstring–optional max models per endpoint

No output schema declared.

No examples provided.

probe ~153

Probe models by sending REAL chat-completion requests; measures latency, success rate, streaming and tool calling. Side effects: consumes upstream tokens/quota and hits the network (open-world) — every probe is a real, billed completion. Use to measure what works RIGHT NOW, then call ranking. Returns per-model probe rows (ok, latency_ms, status, stream_ok, tools_ok).

NameTypeReqDescription
check_toolsstring–also test function calling (slower)
containsstring–substring filter on model id
endpointstring–optional endpoint name to restrict probing to
limitstring–max models to probe (default 20)
modelstring–probe exactly this model id

No output schema declared.

No examples provided.

ranking ~96

Return the quality ranking computed from RECORDED probe history (read-only: no network, no new probes). Ordered best-first by score = success 50% + median latency 30% + cancellation 20%. Use after probe to see the ranked table; use recommend for a single best pick. Rows include model, score, success%, cancel%, median latency, verdict.

NameTypeReqDescription
limitstring–rows to show (default 30)

No output schema declared.

No examples provided.

recommend ~82

Return the single best model for a task profile: 'fast' (lowest latency), 'cheap', or 'capable' (highest quality). Read-only, computed from recorded probe history; omit profile to use the default. Use when you need ONE model to route to right now.

NameTypeReqDescription
profilestring–fast | cheap | capable (optional, default = capable)

No output schema declared.

No examples provided.

report ~61

Return the whole picture as a markdown report: endpoints, verdict counts, top models by score, and the full per-model table. Read-only, from recorded history (no network). Use to inspect or share overall gateway health (e.g. paste into a STATUS.md).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the ModelLens MCP server?

ModelLens runs locally as a PyPI package, launched with uvx modellens-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 · modellens-mcp

# add to Claude Code
claude mcp add greatbeing-modellens -- uvx modellens-mcp
Common questions

What is the ModelLens MCP server?

ModelLens is an MCP server listed in the public MCP registry as io.github.Greatbeing/modellens. See which models actually work: probe, rank and recommend across OpenAI-compatible gateways. This page covers its PyPI package (modellens-mcp).

Is the ModelLens MCP server safe to use?

ModelLens scores 75 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 ModelLens MCP server expose?

ModelLens exposes 5 tools: list_models, probe, ranking, recommend, report. Their descriptions and schemas cost roughly 490 tokens of context every time the server is loaded.

Is the ModelLens MCP server still maintained?

ModelLens 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 ModelLens MCP server under?

ModelLens 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 ModelLens MCP server?

VerifyMCP ran 16 checks on ModelLens, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.