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.
-
An LLM eval harness graded by computed ground truth, not an LLM judge. Worked example: poker, served to models as MCP tools — gpt-4o-mini goes from 26/75 to 75/75 with them.
MIT ★ 1 -
GROUNDTRUTH is a narrative sci-fi puzzle game. Play Demi, the sole survivor aboard the crippled research vessel Sanctuary, while an AI agent plays as KORE through WebMCP. Restore power, protect the last living specimen, and complete the mission before auxiliary power runs out.
GPL-3.0 ★ 1 -
@sdkrun/platform-oracleupdated this year
The Platform API Oracle - MCP server serving ground-truth native SDK knowledge from NativeScript metadata
npm Apache-2.0 -
Persistent ground truth for Claude Code. Stop AI agents from drifting on your codebase.
npm MIT ★ 6 -
penquifygithub.com/MAXMARDONES/penquifyupdated this year
OCR in reverse. Make your documents worse. Python toolkit for synthetic logistics document & photo datasets with verified ground truth.
pypi MIT ★ 7 -
deepmap-earth-grounding-mcpactive
MCP server for verifiable physical-world ground truth (water, hazard, ground stability, resource, space weather) from DeepMap AI, with Bitcoin-anchored provenance.
pypi Proprietary -
groundtruth-mcpgithub.com/grmkris/ethglobal-cannes-2026-groundtruthupdated this year
MCP server for Ground Truth — verified intelligence map
npm MIT -
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
MIT ★ 1,343 -
D&D 5e SRD MCP server — monster search, spell lookup, encounter building, and character tools powered by ground-truth SRD data
npm MIT ★ 8 -
MCP server for job search: many sources, resume-grounded scoring, truthful document tailoring, application tracking
pypi MIT -
lsbiblegithub.com/kdcokenny/lsbibleupdated this year
Bible SDK and MCP server – give Claude, Cursor, and AI apps ground-truth Scripture context
pypi MIT ★ 9 -
sift-aegisgithub.com/ssurekumar01111-hue/sift-aegisupdated this year
Autonomous DFIR investigation agent for the Find Evil! hackathon. Custom MCP server wrapping Volatility3 + self-correcting orchestrator + ground-truth benchmark.
Apache-2.0 -
Hard ground truth for CSS — the browser's rendered layout as deterministic, diffable text for coding agents. MCP server + CLI.
npm MIT ★ 2 -
Zero-Hallucination Chord Progression Search Engine & Music Theory Analyzer (Hooktheory 75k+ & Mandopop Ground Truth)
NOASSERTION ★ 1 -
MCP server for debugging PX4 SITL flights from ULog logs with Claude: failsafes, EKF vs ground truth, offboard velocity lag.
MIT -
MCP server exposing live machine ground-truth (processes, listening ports, daemons, load) to agent fleets — stop guessing what's actually running.
npm MIT ★ 1 -
Ground truth about npm packages for AI coding agents. Catches hallucinated and slopsquatted dependencies before they reach your lockfile.
npm MIT ★ 4 -
leonardgithub.com/jasondillingham/leonardupdated this year
Local-first ground-truth toolkit for Claude Code: symbol index + decision log + claim ledger over MCP and hooks.
go Apache-2.0 ★ 1 -
groundtruth-mcpgithub.com/ZhenGtai123/groundtruth-mcpupdated this year
Give coding agents your project's own ground truth: semantic lint, deterministic replay, seeded simulation with threshold gating, and guarded read-only queries, as MCP tools.
MIT ★ 1 -
Local-first research environment: one SQLite ground truth driven by your AI via MCP, with span-anchored verified citations, experiment DAGs, and enforced provenance
MIT -
Local vs. cloud LLMs triaging real Splunk alerts through the Splunk MCP Server, evaluated against manual ground truth, with a least-privilege AI identity.
-
Token-saving browser automation MCP server: cached actions, then a local LLM, then Claude. Ground-truth benchmark included; 0 Claude tokens across 20 real runs.
-
testtracegithub.com/readytorage/testtraceupdated this year
Ground-truth UI element locators for AI coding assistants, plus a Locator Risk Score that flags which locators are likely to break your tests. Local CLI + MCP server, no hosting required.
npm ISC -
locator-registrygithub.com/readytorage/locator-registryupdated this year
Ground-truth UI element locators for AI coding assistants, plus a Locator Risk Score that flags which locators are likely to break your tests. Local CLI + MCP server, no hosting required.
npm ISC -
MCP server and Rails 8 agent skill that give coding agents (Cursor, Claude Code, Codex) ground truth about your Rails app's schema and routes.
rubygems MIT ★ 1 -
chromium-screenshotsgithub.com/samestrin/chromium-screenshotsupdated this year
Vision AI "Cortex" for Agents. A Playwright-based MCP Server & API that captures screenshots with ground-truth DOM extraction and full auth state injection. Containerized.
MIT ★ 2 -
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 -
@vibecheck-ai/mcpgit+https://vibecheckai.devupdated this year
VibeCheck MCP — the code intelligence layer for AI-built software, wired into your agent. Truth-grounded, runtime-aware, multi-agent. 16+ verification engines, runtime probes, and live truthpack context for Cursor, Claude, Windsurf, and any MCP-compatible
npm MIT -
Synapsegithub.com/amitsingh2003/Synapseupdated this year
Give your AI assistant ground-truth knowledge of your entire codebase. Synapse builds a local code graph and serves it over MCP — no file-pasting, no hallucinated symbols, no repeated context.
-
Disciplined Engineering Harness for AI Agents. MCP server + 21 adversarial skill gates. Real-time ground truth for React, Next.js, shadcn/ui, Motion, React Flow, Echo, Go, Rust, and Design Tokens.
★ 1 -
MCP server that gives coding agents ground truth about your React design system: components, props, cva variants, tokens and docs, plus a linter they can run on their own UI.
npm MIT -
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
npm MIT -
scrapeless-browser-instrumentationgithub.com/scrapeless-ai/scrapeless-browser-instrumentationactive
Stealth Chrome DevTools Protocol instrumentation for reverse-engineering hostile client-side JavaScript — anti-bot, captcha, fingerprinting and payment SDKs. Invisible hooks, captured ground truth, and an oracle that verifies your reimplementation. 80 MCP tools for agents.
NOASSERTION -
TrafficSentinel Suite: Ad-Tech IVT Investigator & MCP Platform — An enterprise-grade monorepo combining an interactive clarifying investigator agent, an in-process DuckDB bidstream analytics FastMCP server, and a 50-scenario ground-truth evaluation harness catching prompt regressions in CI/CD.
-
Ground truth for FiveM / GTA V development: a knowledge tree, offline data layers built from your own game, a searchable snippet database and a read-only MCP server — for Claude Code, Codex, Gemini CLI, Cursor, Copilot and ChatGPT.
MIT ★ 16 -
Ground LLM output as provenance-tracked claims, not truths. A maximal super-ontology + native RDF-1.2 logic: reasoning engine — OWL, SHACL, SSSOM, EDOAL are generated lossy projections; a correspondence calculus losslessly subsumes external vocabularies. Rust-first (pip / MCP / GTS).
AGPL-3.0 ★ 13 -
rhizophoragithub.com/punic-pillars/rhizophoraupdated this year
MCP server for React Native spatial integrity and layout audit. Provides Ground Truth for your component tree by detecting margin pollution, token deviations, bridge crossings, and render traps. 15 tools for structural analysis, layout auditing, performan
npm MIT -
Does a computer-use agent do the job every time? Bellwether measures pass^k on legacy enterprise screens: snapshot-forked trials, ground-truth verifiers that must prove they can fail, seeded fault injection, and a compiler that turns solved traces into deterministic MCP tools. Runs offline, no API key.
Apache-2.0 -
Claude agent that finds, fixes and verifies faults in a simulated 100-vehicle fleet through a Go MCP server. Code-enforced write and stale-data checks, a ground-truth eval harness, and a rule-based baseline: Claude 6/6 vs rules 0/6 when the fix is only in the manual.
Apache-2.0 -
Synthetic U.S. medical bills and benefit notices, as PDFs with an answer key, for testing document AI, bill-review tools and agents.
npm Apache-2.0