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.
-
anti-hallucination-mcpgithub.com/akunimal/anti-hallucination-mcpupdated this year
Minimalist MCP server + hooks for anti-hallucination in AI coding assistants. Detects hallucinated symbols, typos in imports, and invalid API routes via AST-based fuzzy matching.
npm MIT -
eruka-mcpgithub.com/dirmacs/eruka-mcpupdated this year
MCP server for Eruka — anti-hallucination context memory for AI agents
cargo MIT ★ 3 -
Python SDK for Komplex AI — a hallucination detector for LLM output. Score any response for hallucination risk in one call. Includes an MCP server.
NOASSERTION -
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 -
FactAnchor-MCPgithub.com/Tausifonly001/FactAnchor-MCPupdated this year
Reduce AI hallucinations by 80% with zero-cost, local context anchoring (MCP server).
MIT ★ 1 -
@vibecheckai/mcp-servergithub.com/vibecheckai/vibecheckupdated this year
VibeCheck — AI Code Firewall | MCP Server for hallucination prevention in AI-assisted development
npm MIT -
A judge for code written by AI: plain Python, rules against hallucinations.
pypi 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 -
kaelis-memorygithub.com/kaelis/kaelisupdated this year
Kaelis AI Native Memory System — Four-layer memory, MCP server, and multi-agent hallucination guard
pypi MIT -
The AI Integrity Sentinel: Open-source MCP server & CLI preventing AI dependency hallucinations, code degradation (AI slop), and cognitive scope drift
NOASSERTION -
autoai-agentwatchgithub.com/autoailabadmin/agentwatchupdated this year
AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior
npm Apache-2.0 -
wisdom-storegithub.com/InfiniQuest-App/wisdom-storeupdated this year
MCP server that gives AI coding assistants persistent memory, context control, and anti-hallucination tools
MIT ★ 1 -
verifiable-memory-mcpupdated this year
Verifiable memory for AI agents — 0% hallucination, cited, provably forgettable, deterministic. MCP server. CPU-only, no GPU, zero dependencies.
pypi MIT License -
agentoolboxgithub.com/solhammer/agentoolboxupdated this year
The quality layer for AI agents — hallucination firewall, import validator, context distiller. Pay per call in SOL.
npm MIT -
vetpkgactive
Catch hallucinated and squatted packages before an AI agent installs them. MCP server + CLI, zero dependencies.
npm MIT -
guardrail-ai-mcpgithub.com/saifsysim/guardrail-mvpupdated this year
Guardrail AI — MCP server for Claude Desktop. Score AI responses for hallucinations, safety, and confidence. Zero setup.
npm MIT -
verifiable-memorygithub.com/Mars-proj/verifiable-memoryupdated this year
Verifiable memory for AI agents — 0% hallucination, cited answers or honest abstention, provable forgetting, deterministic. MCP server. CPU-only, no GPU.
MIT ★ 1 -
SourceTrace: AI compliance provenance API. Traces regulations and standards to primary sources. Auditable JSON—no hallucinations. For AI agents and compliance teams.
MIT -
RAG-assistantgithub.com/MedBenDakkoum/RAG-assistantupdated this year
AI-powered knowledge assistant for SMEs, built with Spring Boot & Angular, combining RAG and MCP to deliver accurate, hallucination-free answers from company documents.
-
vaporcheckgithub.com/cdmx-in/vaporcheckupdated this year
Stops AI coding assistants from using packages, files, and functions that don't exist. A safety net against hallucinated and slop-squatted names.
Apache-2.0 -
couchloop-eq-mcpgithub.com/wisenbergg/couchloop-mcpupdated this year
Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions
npm MIT -
The anti-hallucination gate for AI coding agents: 9 MCP tools (undefined-symbol verification in 17 languages with real toolchain adapters, hallucination-word scan, sandboxed run, evidence receipts), a cross-client hook and a CI gate — so 'done' means obse
npm PolyForm-Noncommercial-1.0.0 -
sovereign-braingithub.com/sophiacave/sovereign-brainupdated this year
Local-first persistent memory for AI agents. SQLite + sqlite-vec. Semantic search, graph relationships, anti-hallucination. Zero cloud dependency.
pypi MIT -
Stop AI coding agents installing packages that do not exist. MCP server + CLI for detecting hallucinated and slopsquatted npm packages. Zero dependencies.
MIT -
halugardgithub.com/ppp727276/halugardupdated this year
Anti-hallucination MCP server for AI agents. 4-gate dual-stage pipeline. Go binary. Blocks fabricated claims, identity drift, credential leaks, dangerous commands.
MIT -
@altirs/mcp-serveractive
MCP server for Altirs — AI guardrails (content safety, PII, prompt injection, hallucination) as tools for Claude Code, Claude Desktop, Cursor, and any MCP client
npm MIT -
owl-memory-mcpgithub.com/gauravv-g/owl-memory-mcpupdated this year
Memory that thinks. Local AI memory with hallucination firewall, 95% token savings, Cloudflare bypass, and P2P LAN bug sharing. 55+ tools. Zero cloud.
★ 3 -
open-code-reviewgithub.com/raye-deng/open-code-reviewupdated this year
🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more. MCP Server + CLI + CI/CD Action.
npm NOASSERTION ★ 41 -
typed-recallgithub.com/yash194/recallupdated this year
Memory layer for AI agents — typed-edge graph, bounded hallucination, audit-grade, surgically forgettable. Local SQLite + MCP server. Full install includes BGE neural embedder and OpenAI client out of the box.
pypi Apache-2.0 -
MCP server for validating legal citations against CourtListener's 9M+ opinion database — detects AI-hallucinated citations, name mismatches, and ambiguous reporters with an interactive citation panel.
MIT ★ 5 -
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
go MIT ★ 123 -
> **Model Context Protocol (MCP) Server for ColabAI** > Direct academic citation verification, anti-hallucination paper validation, and multi-source academic search for AI agents and LLM tools (Cursor, Claude Desktop, Windsurf, LangChain, OMP).
npm MIT -
pkgguardgithub.com/Highcrypto7/pkgguardupdated this year
Vet the packages & repos your AI assistant recommended — before you install. Catches hallucinated/slopsquatted names, CVEs, malware, fake stars, and license traps in 25 languages. MCP server so the assistant checks itself. No API key.
MIT -
Cross-vendor multi-model review committee that gates AI/agent-generated content before it ships — consensus-based hallucination defense. Zero dependencies, local-first CLI, MCP server, CI gate exit codes.
GPL-3.0 ★ 1 -
trustoraclegithub.com/ToolOracle/trustoracleupdated this year
FeedOracle Trust Layer — Verifiable evidence & verification MCP server for AI agents. 10 tools: claim verification, ES256K-signed facts, provenance tracing, freshness guard, hallucination detection, confidence gates, on-chain evidence anchoring. Standardized verdict schema with proceed/caution/abstain/escalate actions.
NOASSERTION -
A zero-cost FastMCP research server for AI agents featuring Dual-Pillar defense: 4-pass anti-poisoning / prompt-injection sanitization & anti-hallucination context budgeting over arXiv, GitHub, Semantic Scholar, and Wikipedia.
GPL-3.0 -
arthur-mcpgithub.com/zachdelong/arthurupdated this year
Ground truth verification for AI-generated code plans. Catches hallucinated file paths, schema references, imports, env vars, types, API routes, Express/Fastify routes, and Supabase schema — deterministically, zero cost, no API key.
npm MIT -
lingjing-classroom-mcpactive
LingJing Classroom — a deterministic (no-LLM) knowledge & blindspot MCP for AI agents: a teaching loop that returns 7-dimension blindspots and a summary. An independent gap-check layer, never hallucinates, never grades.
npm UNLICENSED -
Cubicle: anti-hallucination trading for AI agents. Reverse-engineer a strategy or a TradingView Pine script, compile it, backtest it on recorded bars of NQ, ES, YM, BTC, ETH, SOL. MCP server + zero-dependency SDK (npm, Python).
MIT ★ 1 -
Hallucination guardrail for AI output about indexed documents. POST a claim, get PASS or FAIL with the exact source passage, checked by a Researcher + Critic LangGraph pipeline (LangChain, Pinecone, GPT-4o). FastAPI service on Render, plus an MCP server, Streamlit UI and eval harness.
MIT -
open-mind-mcp-servergithub.com/HelloThisWorld/open-mind-mcp-serverupdated this year
MCP server that exposes Open Mind's verification-first codebase context to AI agents — glossary, architecture, flows, and claim validation, with file:line evidence for every answer and honest refusals instead of hallucinations.
MIT ★ 1 -
MCP-scopusgithub.com/andri-setiawan/MCP-scopusupdated this year
MCP server for searching Scopus academic papers - Helps AI write accurate academic content without hallucinating citations
MIT ★ 3 -
perf-mcpgithub.com/Perf-Technology/perf-mcpupdated this year
Fact-check and fix AI outputs. MCP server for hallucination detection, schema validation, and output correction.
npm MIT -
indiestackgithub.com/Pattyboi101/indiestackupdated this year
Dependency guardrail for AI coding agents — validates packages, catches hallucinations, 6,500+ developer tools. MCP server + CLI + web.
pypi MIT ★ 3 -
Eliminate AI hallucinations. Zero config. Works instantly with Cline, RooCode, KiloCode, and more.
npm MIT ★ 33 -
import-guardiangithub.com/Baneado98/import-guardianupdated this year
Catch AI-hallucinated (slopsquatted) npm imports in generated code before npm install. MCP server + x402 pay-per-call API.
npm MIT -
lmcp-demogithub.com/suryapa1/lmcp-demoupdated this year
MCP (Model Context Protocol) server: tool integration, context management & hallucination-safe AI agent pipelines
-
audigeo-mcpupdated this year
AudiGEO MCP server — exposes AudiGEO.ai capabilities (audits, monitoring, hallucinations, content) to MCP-compatible agents.
pypi SPONGE THEORY PROPRIETARY LICENSE -
MCP-coding-assistantgithub.com/AviOfLagos/MCP-coding-assistantupdated this year
Detect hallucinations, repetitive bug fix (AKA. bottomless pit) and help AI coder's with access to documentations and suggest fixes.
MIT ★ 14 -
hadith-mcpgithub.com/chenten16/hadith-mcpupdated this year
MCP server providing verified access to the six canonical hadith collections, no AI hallucination
-
depshield-mcpgithub.com/devanshkaria88/depshield-mcpupdated this year
MCP server that checks dependencies against CVE databases before your AI coding agent installs them. Blocks vulnerable and hallucinated packages in real time.
npm MIT ★ 5 -
agentcitegithub.com/Kevinx702/agentciteupdated this year
Fabrication-free, DOI-backed citations API + MCP server for AI agents. Real openAlex sources, never hallucinated.
npm -
Local-first MCP project brain for AI coding: SSOT, roadmap, anti-hallucination audits, semantic governance, and verifiable acceptance.
npm MIT ★ 4 -
qc-validator-mcpgithub.com/mdfifty50-boop/qc-validator-mcpupdated this year
MCP server for AI agent output quality — hallucination detection, scope compliance, quality scoring
npm -
Read-only local security gate & scanner for AI coding workflows, MCP, and package hallucination risks.
MIT -
AndroJack: AI that actually knows Android. Real-time dependency tracking, modern architectures, and zero hallucinations.
npm NOASSERTION ★ 21 -
MCP server serving real GitHub trending data to AI agents (Claude, Cursor) — no hallucinations.
MIT -
Script workflow management via MCP. Converts AI workflows to persistent scripts, reducing tokens & delays while minimizing hallucination risks.
MIT ★ 8 -
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