A
licenseA
qualityC
maintenanceMCP server that provides tools for evaluating LLM agent reliability, including adversarial task generation, automated LLM-as-judge assessment, and confidence statistics.
3
1
MIT
78,672 servers. Updated
Search Relevance ↓
Recent Usage ↓
Date Added ↓
Date Updated ↓
Weekly Downloads ↓
GitHub Stars ↓
Recent GitHub Stars ↓
Matching MCP tools:
Matching MCP Connectors:
com.llm-bus
com.pepevolution
io.github.lazymac2x
com.run402.llm-router
"Connecting external data sources for contextual LLM calls" matching MCP servers:
- AlicenseAqualityCmaintenanceA local MCP server that packages LLM evaluation gates as reusable CI/CD primitives, enabling AI agents to run datasets against models, score responses, and enforce quality thresholds.10MIT
- FlicenseBqualityDmaintenanceProvides a universal bridge to interact with any OpenAI-compatible LLM API (local or cloud), enabling model testing, benchmarking, quality evaluation, and chat operations with performance metrics.8
- AlicenseBqualityBmaintenanceThin HTTP wrapper for the Generate-Data.com API, enabling data generation, schema proposal, and field type listing through MCP tools.8MIT
mock-llm-mcpofficial
AlicenseNot gradedqualityDmaintenanceMCP server to mock OpenAI, Anthropic, and Google Gemini responses for testing AI integrations without real API keys or token spend.MIT- AlicenseNot gradedqualityCmaintenanceEvaluates RAG outputs on faithfulness, answer relevancy, and context precision using an LLM-as-a-Judge backend. Exposes tools for running evaluations, scoring individual samples, and checking thresholds, enabling CI gating and on-demand assessment via MCP.MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to benchmark llm-d from plain English, providing 35 tools and 5 workflow prompts for probing clusters, planning, deploying, running benchmarks, and analyzing results via the Model Context Protocol.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceExposes LLM output validation (schema compliance and prompt-injection detection) as an MCP tool, enabling any MCP-compatible agent to apply real-time guardrails without importing the codebase.MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to generate realistic, synthetic test data on demand, including valid PESELs, NIPs, addresses, and more across 27 EU countries, through two tools: list_generators and generate.258MIT
- AlicenseAqualityCmaintenanceExposes llm-behave's behavioral regression testing as MCP tools, allowing offline semantic similarity checks on LLM outputs without any API calls.3MIT
- FlicenseBqualityDmaintenanceGenerates fixed-length test data records with customizable field types including strings, enums, integers, dates, and fillers. Helps developers create realistic test datasets with specified formats and constraints.11
- AlicenseNot gradedqualityBmaintenanceGenerates importable Optimizely CMS 12 .episerverdata packages from content plans by reading a content-type export and writing the file, without interacting with a CMS instance.MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for comparing JSON, XML, XLSX, CSV, and text data using expected templates, returning pass/fail with difference details.349MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables benchmarking of Large Language Model APIs by measuring performance metrics such as generation throughput, prompt throughput, and Time To First Token (TTFT) with configurable concurrency levels and parameters.1
- FlicenseNot gradedqualityCmaintenanceAn MCP server that mocks payments, third-party API responses, and test data to enable QA flows for donation, checkout, SIP, and subscription pages without depending on a live gateway.
- AlicenseAqualityAmaintenanceZero-sidecar MCP server embedded directly in the Godot 4 editor as a GDScript EditorPlugin — no Node or Python sidecar. Reflection-driven tools over any engine class, validate-before-write GDScript, scene/script/resource authoring, and a runtime play-test loop (play, screenshot, input, assert).545MIT
- AlicenseNot gradedqualityDmaintenanceProvides tools for generating fake data using Faker.js, including person, lorem, internet, and more, with support for multiple locales and customizable options.129MIT
- AlicenseNot gradedqualityCmaintenanceMulti-dimensional data quality validation and statistical anomaly detection for LLM training data, with auto-fix pipeline and MCP tools for AI IDE integration.MIT
Trustabl for Cursorofficial
FlicenseNot gradedqualityBmaintenanceMCP server that brings Trustabl static reliability scanning into Cursor, letting agents inventory agents/tools, flag risky patterns, score production readiness, and write SARIF reports.12- AlicenseNot gradedqualityCmaintenanceMongoDB-integrated MCP server for documenting and analyzing LLM safety challenges in the Grey Swan Arena competitions.247MIT