MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP-based API Management System to prevent Claude Code hallucinations
npm MIT -
codeguardian-mcpgithub.com/codegoddy/codeguardian_mcpupdated this year
CodeGuardian MCP - Automated Quality Assurance for Vibe Coding with AI Hallucination Prevention
npm MIT -
@tac0de/epistemic-check-mcpgithub.com/tac0de/epistemic-check-mcpupdated this year
An MCP server that prevents AI coding agent hallucinations through comprehensive validation
npm MIT -
The AI Integrity Sentinel: Open-source MCP server & CLI preventing AI dependency hallucinations, code degradation (AI slop), and cognitive scope drift
NOASSERTION -
mcp-hallucination-suitegithub.com/steveswain14/mcp-hallucination-suiteupdated this year
A unified suite of MCP suppressors that prevent hallucinations, enforce grounding, and stabilise agent behaviour.
NOASSERTION -
mcp-prompt-suppressorgithub.com/steveswain14/mcp-prompt-suppressorupdated this year
A standalone MCP suppressor that filters, sanitises, and stabilises user prompts to prevent hallucinations and enforce grounding.
NOASSERTION -
@vibecheckai/mcp-servergithub.com/vibecheckai/vibecheckupdated this year
VibeCheck — AI Code Firewall | MCP Server for hallucination prevention in AI-assisted development
npm MIT -
@iflow-mcp/tfscharff-doi-mcpupdated this year
MCP server that prevents citation hallucination by verifying academic citations against CrossRef database
npm MIT -
MCP server that prevents hallucinated numbers over ERP/finance data. Every figure links to its source rows, with a hash-chained audit log.
npm MIT -
secure-mcp-auditorgithub.com/dhzkh68cgj-cmyk/secure-mcp-auditorupdated this year
A verifiable audit layer for LLM tool-calling using Model Context Protocol (MCP) to detect hallucinations and prevent logic sabotage.
-
MCP server for Japanese real estate brokerage law — fetches law text from e-Gov API v2 to prevent AI hallucination in property transaction reviews
npm MIT -
CodeShield-MCPgithub.com/Thejosem4/CodeShield-MCPupdated this year
MCP server and CLI that prevents LLM hallucinations by verifying code against known libraries and frameworks
npm MIT -
MCP server for Japanese building regulations — fetches law text from e-Gov API v2 to prevent AI hallucination in building permit reviews
npm MIT -
A Model Context Protocol (MCP) server that prevents citation hallucination by verifying academic citations against 9 authoritative databases. This server enables AI assistants to verify every citation against real publications before citing them.
MIT ★ 18 -
mcp-json-suppressorgithub.com/steveswain14/mcp-json-suppressorupdated this year
A standalone MCP suppressor that sanitises, validates, and stabilises JSON outputs to prevent malformed or hallucinated structures.
NOASSERTION -
ragalgo-mcp-serverupdated this year
Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).
npm MIT -
A standalone MCP suppressor that filters, stabilises, and sanitises tool responses to prevent hallucinated or unsafe output.
NOASSERTION -
@iflow-mcp/kokogo100-ragalgo-mcp-serverupdated this year
Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).
npm MIT -
dotnetaimcpservergithub.com/arbelh/dotnet-ai-mcp-serverupdated this year
MCP Server for .NET AI development - provides real code samples from Semantic Kernel, OpenAI .NET, MCP C# SDK, and more. Prevents LLM hallucinations by fetching live code from GitHub repositories.
nuget MIT -
design-system-mcpstale
A focused Model Context Protocol server that prevents AI coding assistants from hallucinating design tokens by providing direct access to W3C Design Token JSON files.
npm MIT -
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
npm NOASSERTION ★ 41 -
Magneto is a non-LLM adversarial citation gate whose job is to prevent hallucinations by fact-checking an agent in real-time. Currently for Kiro. EXPERIMENTAL.
go NOASSERTION -
MCP server for AI agents to lookup function signatures from any API. Uses SQLite and universal ctags to index source files across multiple languages (Python, C, Go, C++, JS, Rust, Java, etc.). Prevents hallucination on unknown or recently updated source files by providing accurate function signatures
★ 4 -
quriogithub.com/irahardianto/qurioupdated this year
Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.
MIT ★ 17 -
nexus-mcp-extensiongithub.com/tanaikech/nexus-mcp-extensionupdated this year
Nexus-MCP solves Tool Space Interference in LLMs. It uses a single gateway to aggregate multiple MCP servers and employs a deterministic 4-phase workflow (Discovery, Mapping, Schema Verification, Bridged Execution) to prevent context saturation and tool hallucinations, maintaining reasoning accuracy with massive tool ecosystems.
MIT ★ 4 -
PR-SENTINELgithub.com/Kapish7717/PR-SENTINELupdated this year
An autonomous GitHub App review agent built with LangGraph, FastMCP, and Groq (LLaMA 3.3). Combines deterministic static analysis (Ruff) with advanced LLM reasoning to catch bugs, styling nits, and security risks—validated with evidence-checking to prevent hallucinations. Runs asynchronously via webhook integration.
-
ingest-apigithub.com/Perry-Multi-LLM/ingest-apiupdated this year
FastAPI-based multi-agent orchestrator for Odoo. Uses a Semantic Router to dispatch intents to specialized agents via Model Context Protocol (MCP/FastMCP). Features Guardrails AI for hallucination prevention, Human-in-the-Loop validation, Logfire observability and support for Groq, Ollama and vLLM.
★ 1 -
figma-edit-mcpno update data
Connect AI assistants to Figma via Model Context Protocol to read designs, create and modify elements, and manage design systems programmatically. This plugin empowers your AI assistant to become an active design co-pilot, executing updates and modifications Safer, Cleaner, and Faster than manual entry. By offloading repetitive, error-prone manual operations to automated systems, designers are freed to focus entirely on creative decision-making and product strategy. ### Core Principles * **🛡️ Safer**: The server enforces robust programmatic checks and validations that exceed the Figma Desktop app's default protections. For instance, it prevents deleting variables currently in use to avoid dangling references. By validating all writes against a locked editable scope and strict name checks before execution, it protects files from human error and AI hallucinations. * **✨ Cleaner**: System-driven, programmatic operations guarantee that no layers, text nodes, or components are skipped or forgotten during complex updates. Every design file stays consistent and conforms exactly to your design system. * **⚡ Faster**: Bulk edits like propagating instance overrides, batch-updating copy, or restructuring auto-layout frames are handled via high-performance APIs. Hours of tedious, click-heavy manual work are completed in seconds. ### How it Works (Prerequisites) This server runs locally on your machine. To operate, it requires: 1. The Figma Desktop App to be open. 2. The `Figma Edit` plugin to be active on the file you want to modify (listening on local port `3845`).
smithery -
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
npm Apache-2.0 ★ 20 -
Self-corrective Agentic RAG with LangGraph - eliminates hallucinations through intelligent relevance grading before answering. Features Streamlit UI, MCP server integration & multi-turn memory.
MIT -
Provenance-aware memory format for AI agents: every claim carries its source, age and boundary. A VERAX Teknoloji project (verax-ai.com).
npm Apache-2.0 -
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
pypi MIT ★ 660 -
lucross-sensory-grounding-mcpgithub.com/luclinocruz/lucross-sensory-grounding-mcpupdated this year
Give Claude Code / Codex / any MCP agent real eyes and ears — closed-loop visual/audio/video verification with mandatory enforcement hooks, so agents stop reporting 'done' when it isn't.
Apache-2.0