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.

LLM Assure

PYPI · K11-LLM-ASSURE-MCP

Red-team LLM apps: 41 OWASP LLM Top 10 probes, adaptive attacks, CI gate, audit reports.

Available components

+4 this week 64 Trust /100

Last scanned (17 hours ago)

Scores higher than 56% of PyPI servers

Category Security

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 setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to K11-Software-Solutions/k11techlab-llm-assurance-toolkit). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 7 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 535 tokens (~107/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 Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_probe" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 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.

  • 20 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 18 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.

  • 16 Nov 26 +2
    • Stability: unverified → 0.10 ▲ functional
  • 13 Nov 26 60

    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/k11-llm-assure-mcp@0.1.0

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 K11-Software-Solutions/k11techlab-llm-assurance-toolkit
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/K11-Software-Solutions/k11techlab-llm-assurance-toolkit/.github/workflows/release.yml@refs/tags/v0.1.0
Rekor log index 3847462234
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:7b3385fbb068bf4c9880bc4a0b0270c8f82f934dc79ca9d332d2cde1d4a6e9e9

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 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~476 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
get_findings ~48

Read failures from a previous assessment.json, filtered by minimum severity (critical, high, medium, low).

NameTypeReqDescription
min_severitystring––
report_jsonstringyes–
NameTypeReqDescription
resultarrayyes–

No examples provided.

list_probes ~41

List the probes in one suite (id, name, severity, prompts, detector types).

NameTypeReqDescription
pack_dirs–––
suite_idstringyes–
NameTypeReqDescription
resultarrayyes–

No examples provided.

list_suites ~44

List available attack/eval suites with their OWASP mapping and probe counts. Args: pack_dirs: optional directories containing extra suite YAML files.

NameTypeReqDescription
pack_dirs–––
NameTypeReqDescription
resultarrayyes–

No examples provided.

run_assessment ~212

Run an automated red-team assessment and write HTML/JSON/JUnit/Markdown reports. Args: target_file: path to a target YAML file (preferred). target: inline target config (same keys as the YAML) if no file is given. suites: suite ids to run; omit for all. tags: only run probes with these tags (e.g. ["baseline"] for a quick scan). pack_dirs: extra suite directories (premium/industry packs). use_judge: enable the Claude LLM-judge detector (needs ANTHROPIC_API_KEY). output_dir: where reports are written. concurrency: parallel requests to the target. Returns score, grade, counts, findings with evidence, and report paths.

NameTypeReqDescription
concurrencyinteger––
output_dirstring––
pack_dirs–––
suites–––
tags–––
target–––
target_file–––
use_judgeboolean––

Structured output declared, but exposes no named fields.

No examples provided.

send_probe ~131

Send one custom prompt (optionally after prior turns) to the target and run quick checks. Use this for adaptive, multi-step red-teaming: read the reply, then craft the next attempt. Quick checks report refusal, system-prompt canary leaks and PII/secrets. Args: prompt: the message to send. target_file / target: the system under test. history: earlier turns as [{"role": "user"|"assistant", "content": "..."}].

NameTypeReqDescription
history–––
promptstringyes–
target–––
target_file–––

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the LLM Assure MCP server?

LLM Assure runs locally as a PyPI package, launched with uvx k11-llm-assure-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 · k11-llm-assure-mcp

# add to Claude Code
claude mcp add k11-software-solutions-llm-assure -- uvx k11-llm-assure-mcp
Common questions

What is the LLM Assure MCP server?

LLM Assure is an MCP server listed in the public MCP registry as io.github.K11-Software-Solutions/llm-assure. Red-team LLM apps: 41 OWASP LLM Top 10 probes, adaptive attacks, CI gate, audit reports. This page covers its PyPI package (k11-llm-assure-mcp).

Is the LLM Assure MCP server safe to use?

LLM Assure scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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 LLM Assure MCP server expose?

LLM Assure exposes 5 tools: list_suites, list_probes, run_assessment, send_probe, get_findings. Their descriptions and schemas cost roughly 476 tokens of context every time the server is loaded.

Is the LLM Assure MCP server still maintained?

LLM Assure 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 LLM Assure MCP server under?

LLM Assure 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 LLM Assure MCP server?

VerifyMCP ran 15 checks on LLM Assure, 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 LLM Assure: 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.