LLM Assure
Red-team LLM apps: 41 OWASP LLM Top 10 probes, adaptive attacks, CI gate, audit reports.
- tools
- 5
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Nov 13, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
list_suitesBrowse attack categories and probes.
Browse attack categories and probes.
No parameter schema in public metadata yet.
list_probesBrowse attack categories and probes.
Browse attack categories and probes.
No parameter schema in public metadata yet.
run_assessmentRun a full audit and write all reports.
Run a full audit and write all reports.
No parameter schema in public metadata yet.
send_probeSend a custom prompt (with history) and get leak/PII/refusal checks, for adaptive multi-turn attacks.
Send a custom prompt (with history) and get leak/PII/refusal checks, for adaptive multi-turn attacks.
No parameter schema in public metadata yet.
get_findingsRead findings from an earlier assessment.json.
Read findings from an earlier assessment.json.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
ANTHROPIC_API_KEYsecretOptional: enables the Claude LLM judge and adaptive red-teaming
Readme
K11 LLM Assurance Toolkit
Red-team your LLM application before your users do.
llm-assure runs automated attack and evaluation suites against any chatbot, RAG
app or AI agent. It fails your CI build on serious findings and produces an
audit-ready HTML report. It also includes an MCP server, so Claude (or any MCP
client) can run assessments and adaptive red-team sessions for you.
- 41 probes in 8 suites, mapped to the OWASP Top 10 for LLM Applications (2025)
- Any target: your HTTP API, OpenAI-compatible endpoints, Claude, or a Python function
- Deterministic first: canary-leak, PII/secret, refusal and pattern detectors are free and reproducible. An optional Claude LLM-judge handles the nuanced cases.
- CI-native: JUnit XML, a
--fail-onseverity gate, and a GitHub step summary - Client-ready: a self-contained HTML report with a score, findings, evidence and remediation
- Extensible: add industry packs with
--pack DIR
Details
- Repository
- github.com/k11-software-solutions/k11techlab-llm-assurance-toolkit
- Website
- github.com/K11-Software-Solutions/k11techlab-llm-assurance-toolkit
- Categories
- AI & LLM Tools, Security & Pentesting
- Package
k11-llm-assure-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
More from k11-software-solutions
Related AI & LLM Tools MCP servers
View all
Memory Mcp Litethuupx/memory-mcp-liteA lightweight, structured, token-efficient local-first MCP memory server2stars
Agent Mosaic Skillable-rip/agent-mosaic-skillConvert photos to LEGO-style brick mosaic previews with AI-powered color quantization.1stars
Impact Previewagent-polis/impact-previewImpact preview for AI agents - see what changes before any action executes.1stars
Agent Moduleagentmodule/mcpDeterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.0stars
AgentScrapehshintelligence/agent-scrapePay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.1stars
Dingdawg Data Agentdingdawg/dingdawg-agent-1AI data agent — schema analysis, query optimization, PII detection, pipelines.0stars