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. 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.
-
@jhlee0409/elenchus-mcpgithub.com/jhlee0409/elenchus-mcpupdated this year
MCP server for Elenchus adversarial verification system - state management, context sharing, and orchestration for code verification loops
npm MIT -
Deterministic verification gateway for MCP — risk-gated Python execution in a restricted environment, math/logic/code/SQL verification engines, and skill supply-chain provenance guard
pypi Apache-2.0 -
elenchus-mcpgithub.com/jhlee0409/elenchus-mcpupdated this year
Elenchus MCP Server - Adversarial verification system for code review
MIT ★ 5 -
codeloopgithub.com/orienjoji/codeloop-internalupdated this year
CLI tool for CodeLoop — automated verification for AI coding agents
npm MIT -
Verify AI-generated code with execution evidence — deterministic, local-first verification for coding-agent changes via a macOS app, CLI, and MCP server.
MIT ★ 1 -
Stale-proof repo memory for coding agents: citations + JIT verification + TTL (MCP).
MIT ★ 1 -
codeloop-mcp-servergithub.com/orienjoji/codeloop-internalupdated this year
CodeLoop MCP server - verification, self-repair, and recommendation layer for AI coding agents
npm MIT -
Code intelligence and deterministic verification for AI coding agents: symbol-level code graph, blast radius, dead-code analysis, and MCP servers for Claude Code, Cursor, and Codex
npm Apache-2.0 -
MCP servers and hooks that add deterministic verification, code intelligence, supply-chain checks and cross-project memory to Claude Code, without replacing its native loop.
-
Local MCP server that reads verification codes from your own Cleat US mobile line.
npm MIT -
Local change evidence, impact review, and verification receipts for developers, CI, and coding agents.
npm MIT -
FerryCat: Contract-driven cross-host AI agent handoff, code review & verification harness over MCP and SQLite WAL
npm MIT -
sms-florin-mcpgithub.com/flovoice53-tech/sms-florin-mcpupdated this year
MCP server for sms-florin — lets AI coding agents (Claude, Cursor, Codex, Windsurf...) rent a real UK phone number and receive SMS/OTP verification codes during automated testing.
npm MIT -
cortexgithub.com/supernavyl/cortexupdated this year
Rust pre-apply verification gate for AI coding agents — sandbox-checks edits before they touch disk. MCP server + daemon + CLI.
MIT -
The deterministic trust layer for autonomous AI coding agents. Compiler-grounded verification of what an agent actually did vs. what it claimed, blast radius mapping, and persistent contract memory.
npm MIT -
MCP servers that add verification, code intelligence, context packing, memory, sub-task offload, supply-chain checks and deep research to the OpenAI Codex CLI on any model backend.
-
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 -
Official Model Context Protocol (MCP) server for AliasMail (https://aliasmail.space) — Zero-log disposable temporary inboxes, autonomous OTP & verification code extraction, and email security tools for AI agents.
MIT ★ 1 -
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 -
MCP security server for AI agents — runtime verification and receipt verification for Claude Code, Cursor, Cline and Windsurf. 7-dimension CCS checks, Ed25519 tamper-evident receipts, offline verification, zero runtime dependencies.
npm Elastic-2.0 -
Open-source, no-code ecommerce launcher and developer kernel for proof-native artifacts. Clone, configure, and launch your own storefront powered by the Receiz SDK, MCP server, offline verification, ownership receipts, and programmable commerce objects.
MIT ★ 1 -
Independent verification for AI coding agents. Real commands. Human-owned acceptance. Hash-manifested evidence.
NOASSERTION -
MCP server for AI agents that need a phone number: order a private number in 200+ countries, read the SMS verification code, hand it back. The widest country coverage in the category, and you can check it with one API call.
npm MIT ★ 522 -
Open-source literature verification for Claude Code and Codex, with traceable source passages.
Apache-2.0 -
Disposable email (temp mail) CLI + MCP server for AI agents. Spawn a throwaway inbox, wait for the OTP verification code, toss it. --json on every command, exit codes 0-4, no sign-up, no API keys. Node 18+, Homebrew, npm, npx, GitHub Action.
MIT ★ 1 -
Official OrigoID MCP server — CURP, INE, RFC/SAT, IMSS, OFAC/PEPs checks as tools for Claude Code and any MCP-compatible client. Identity verification for Mexico.
-
@texau/mcp-serverupdated this year
MCP server for TexAu Enterprise API — LinkedIn enrichment, people search, post search, email finding & verification, sync waterfall enrichment (email/phone/person/company) for AI agents, Claude, Cursor, Windsurf, VS Code Copilot, and more.
npm MIT -
High-performance WebAssembly theorem prover with dependent types, hash-consing (150x faster), Ed25519 proof signatures, MCP support for Claude Code, AgentDB vector search, episodic memory, and ReasoningBank learning. Formal verification with cryptographic
npm Apache-2.0 -
Rust planning and verification harness for AI coding agents: dependency-aware decomposition, beam strategies, incremental verification and recipe memory. MCP server included. Zero dependencies.
MIT ★ 1 -
A local-first project spine for coding agents: shared context, durable tasks, verification evidence, and seamless handoffs.
MIT -
Your agent says it's done. Elliot checks. Independent verification for code written by AI agents.
MIT ★ 1 -
imugi-aigithub.com/m00n7682/imugiupdated this year
Design to Code — AI-powered frontend builder with visual verification
npm MIT -
A Model Context Protocol (MCP) server that provides security scanning capabilities for code snippets, codebases, and verification of code changes
pypi Apache Software License -
verilog-mcp-servergithub.com/kaiwenyu147369/verilog-mcp-serverupdated this year
AI-powered Verilog/SystemVerilog MCP Server for Claude Code: generate testbenches, lint RTL code, and scaffold UVM verification environments
★ 1 -
Your agent says done. Tessera checks. Deterministic blast radius before every edit and verification after it, for any AI coding agent.
npm Apache-2.0 ★ 2 -
Claude Code orchestrates OpenCode worker agents: dynamic model routing, parallel-write safety, independent verification and read-only review.
MIT -
The design layer for agentic AI — design context, interface checks, and verification for coding agents.
npm MIT ★ 51 -
Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.
MIT ★ 2 -
Verification for agent-written code: evidence-backed findings, honest coverage.
npm MIT -
imugigithub.com/M00N7682/imugiupdated this year
Give AI eyes to see your frontend. Design → pixel-perfect code with visual verification. MCP server for Claude Code & Cursor.
MIT ★ 12 -
Deterministic edit safety for AI coding agents: blast radius before an edit, verification after it. Prebuilt tessera binary, no Rust toolchain required.
npm Apache-2.0 -
DVERA connects coding agents to CT for C/C++ unit and integration verification in functional-safety projects through MCP and Skills.
MIT -
Local-first Build Truth & verification layer for AI coding agents. Stops hallucinations, cuts token costs by 90%, and fixes monorepo test failures for Claude, Cursor, Aider, & Copilot.
Apache-2.0 ★ 3 -
QNSQY for Claude Code: post-quantum scanning, encryption and verification tools in a strict mode that never takes passwords or keys
NOASSERTION -
@stranzwersweb2/skillsync-mcpgithub.com/adityasugandhi/skillsync-mcpupdated this year
SkillSync MCP server — search, scan, install & manage Claude Code skills with built-in security scanning and startup verification
npm MIT -
Precise verification for coding agents on Android: compact screens, impact analysis, verdicts with evidence, UI, performance and compatibility checks. CLI and MCP server.
Apache-2.0 ★ 3 -
Headless verification browser for AI coding agents: 35 ms one-call checks, pixel diffs, live human hand-off
MIT ★ 118 -
The full-state-verification layer for AI coding agents: one native MCP server (Rust host, C engine) that turns a repository into measured, grounded, guarded, predictive, self-improving intelligence with provenance for every claim.
NOASSERTION ★ 5 -
Verification layer for AI-assisted development. Agents don't get to self-certify — settle gates re-check declared acceptance criteria and refuse until the evidence holds. CLI · Claude Code · Codex · MCP.
MIT ★ 2 -
Replay the crash. Prove the fix. 81ns in-process flight recorder, 61µs deterministic replay, and 5.9ms variant fix verification for journal-driven services and AI coding agents.
Apache-2.0 ★ 2 -
Postgres MCP server with OAuth 2.1 authentication, Keycloak/Authentik JWT verification, AST SQL guardrails, and role/RLS data isolation for Claude Code & Cursor.
MIT -
weftgithub.com/spranab/weftupdated this year
Weft — the execution ledger for autonomous coding agents. Verification, not human review, is the merge gate. Paper: doi.org/10.5281/zenodo.21882499
MIT ★ 2 -
Fable 5.1 Multi-Agent Architect & Invariant Verification Gate for Claude Code, Cursor & Web. Decouples task contracts from worker subagents with adversarial failure injection testing. BYOK (Claude 3.7, GPT-4o, DeepSeek, Ollama).
MIT ★ 1 -
sub-atlias: the free sub-harness version of Atlias (not the full Atlias app). Shared project memory, knowledge graphs, host hooks, MCP tools, and verification inside Claude Code, Codex and other hosts.
npm MIT -
Local MCP server for code knowledge, controlled edits and allowlisted verification. TypeScript, Windows and WSL. MIT.
MIT -
Open MCP server suite that gives coding agents, including local and low-cost models, a verification gate, repo map, LSP, code graph, RAG and knowledge graph, research, checkpoints and watchdogs, with a planner/executor model topology.
MIT ★ 1 -
Make AI research agents accountable — give every conclusion a traceable argument graph. MCP server + Claude Code plugin for paper reproduction, hypothesis verification, and auditable scientific reasoning.
MIT ★ 3 -
Verify each git tree once. A stack-agnostic verification queue and cache for parallel coding agents: bounded concurrency, per-tree result cache, request coalescing, CLI for git hooks and an MCP server for agents. Rust.
MIT ★ 2 -
Claude Code plugin: the Opus supervisor plans, specifies and reviews; cheap workers (DeepSeek & co. via 9Router) write the code in isolated git worktrees. Server-side verification, a review gate, and merge-back as one squash commit. Fewer tokens, same quality.
AGPL-3.0 -
Provider-neutral MCP server for software engineering: requirements, goals, milestones, portable implementation plans, verification and durable handover for coding agents, backed by SQLite.
Apache-2.0 ★ 2