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.
-
MCP server for DRC (Deterministic Replay Compute) — trace, analyze, search, diff, bisect, replay, and verify captured executions
npm MIT -
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.
go Apache-2.0 ★ 2 -
agent-replay-mcpgithub.com/mdfifty50-boop/agent-replay-mcpupdated this year
MCP server for agent session recording and replay — debug non-deterministic agent behavior with session comparison and divergence detection
npm -
🔌 Exposes Agent Replay Debugger over MCP — step-debug + deterministic replay + signed audit evidence. MIT. By MEOK AI Labs.
pypi NOASSERTION -
@anyforgex/recordforgeactive
Record browser workflows over CDP and replay them deterministically. An MCP server + CLI that gives any agent-driven browser automation a capture-and-replay capability.
npm MIT -
Deterministic record/replay & time-travel debugging for AI agents. Local-first, MCP-native.
MIT ★ 1 -
Record browser workflows over CDP and replay them deterministically — an MCP server + CLI for agent-driven browser automation.
AGPL-3.0 ★ 1 -
Schema-aware synthetic test data with deterministic replay, relational integrity, business rules, and MCP tools.
MIT -
coach-kernelgithub.com/LeesungDang/coach-kernelupdated this year
Deterministic safety kernel for AI-agent training plans, with MCP data boundaries, Claude Agent SDK integration, replay evals, and fuzzing.
MIT -
Deterministic, non-destructive, replayable memory substrate for AI agents: an append-only claim ledger with supersession, provenance, deterministic replay, and semantic recall over MCP.
-
Agent-native game engine in Rust, inspired by HPL3 (SOMA, Amnesia): deterministic fixed-tick ECS core, input replay, built-in MCP server, headless screenshots.
★ 3 -
browser-memorygithub.com/frisbee-one/browser-memoryupdated this year
Local MCP server that gives an agent a reusable memory of web actions (learn once, replay deterministically).
npm MIT -
Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
npm MIT ★ 3 -
@neurcode-ai/mcp-servergithub.com/sujit-jaunjal/neurcodeupdated this year
Model Context Protocol server for the Neurcode deterministic governance runtime. Local-first. Zero-install via npx. Replay-stable. Source-free lifecycle ingress for governed AI coding sessions.
npm MIT -
Deterministic Webhook & Event Replay Engine with Cryptographic Signatures and Race Injection
npm MIT -
Self-hosted broadcast studio for AI matches. One append-only event stream drives live view, replay, directing, audited recaps and highlights. 12 deterministic game types, bilingual UI, CLI + portable exe, MCP/A2A/webhooks.
MIT ★ 3 -
Self-hosted broadcast studio for AI matches. One append-only event stream drives live view, replay, directing, audited recaps and highlights. 12 deterministic game types, bilingual UI, CLI + portable exe, MCP/A2A/webhooks.
MIT -
Self-hosted broadcast studio for AI matches. One append-only event stream drives live view, replay, directing, audited recaps and highlights. 12 deterministic game types, bilingual UI, CLI + portable exe, MCP/A2A/webhooks.
MIT -
Explain changing SEO findings with versioned evidence, deterministic replay, transparent evaluation, and local MCP tools.
MIT -
Mint any website task into a tested, deterministic MCP tool with Claude Code, then replay it with no model — Playwright browser tools plus page tools that run in your own Chrome tab.
npm MIT -
A shared physics world where each AI agent drives one simulated robot through MCP. Deterministic replay and offline rendering. MIT.
MIT -
Open-source sandbox to test AI agents on hotel booking over MCP: injected supplier faults, deterministic grading, replay-verified leaderboard.
MIT ★ 1 -
A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed semantic plans, evidence-backed effects, deterministic replay.
go MIT ★ 27 -
terxgithub.com/ixchio/terxactive
Browser-agent memory that turns repeated workflows into deterministic replays.
pypi MIT -
Agent-first browser automation runtime — deterministic Chromium sessions with replay-equal hash chains, MCP-native tools, and a content-addressed action store.
Apache-2.0 ★ 1 -
Replay-verified minimal JSON reproductions and deterministic TypeScript/OpenAPI drift checks. Local-first CLI and MCP server.
npm MPL-2.0 ★ 1 -
Reusable web-scraping toolkit — Pattern A/B/C/D ladder, TLS-impersonation fallback chain, deterministic fixture-replay testing, and an optional MCP server for LLM agents.
pypi MIT -
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 -
Record once, replay with zero LLM tokens: a Chromium/CDP browser-control MCP server and CLI with deterministic skills, human login handoff, privacy de-identification and a hash-chained audit log.
Apache-2.0 -
forgedgithub.com/sam-siavoshian/forgedupdated this year
Browser automation that learns. An MCP server that makes AI agents faster at repeated browser tasks by recording what works and replaying deterministic steps via Playwright.
MIT ★ 5 -
Browser automation MCP built for small local models (1B-8B): compact e1-style snapshots, loop guard, CDP attach, deterministic replay. Selenium-based, 23 tools.
npm MIT -
⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails & deterministic action replay over MCP.
npm MIT ★ 8 -
bleagithub.com/Nitmi/bleaactive
Universal Agent Plugin for safe BLE diagnostics and automation, with Agent Plugins 1.0.0 metadata, a portable Skill, deterministic CLI, local MCP, and evidence capture/diff/replay.
pypi MIT ★ 13 -
Language-agnostic Spec-to-Contract AI Testing Harness & 500 Crash Preventer. Fuzzes OpenAPI/JSON Schema endpoints with boundary & adversarial vectors, provides zero-token deterministic replays, and integrates seamlessly via MCP for AI Agent ecosystems.
Apache-2.0 -
Scrapogithub.com/vikast908/Scrapoupdated this year
AI-native, agent-first web scraping for Python. Cost-aware tiered fetching (HTTP, browser, stealth, agent), model-agnostic LLM extraction with self-healing selector caches, API-first resolution, deterministic replay and field-level diff, and an MCP server.
pypi MIT ★ 4 -
Vellis — open-source context graph engine for AI agents: typed, local-first memory with explicit schema, validated change, deterministic query, migration, snapshots, replay, and audit. MCP-native. Apache-2.0.
Apache-2.0 ★ 9 -
Compile one recorded browser-agent run into a deterministic BrowserOps procedure that replays with zero LLM tokens, plus a registry where procedures earn trust from verified runs, get demoted on site drift, and heal from the live page.
-
maponcegithub.com/shivampatel0714/maponceupdated this year
AI authors browser automations once (record or map); deterministic Playwright replays them at zero token cost - self-healing when the UI drifts, with business rules, credential housing, and an MCP server. LLMs at build time, auditable code at runtime.
MIT -
neruva-mcpupdated this year
Neruva MCP -- proprietary memory + grounding substrate for AI assistants (Claude Desktop / Claude Code / any MCP client). Typed Records store, document knowledge graph with exact multi-hop traversal (ownership/relationship tracing), semantic + structural recall, deterministic corrections, provenance/citations, GDPR/Law-25 atomic forget, snapshot/replay audit. Thin client: all algorithms run server-side. For Neruva integration clients only -- NOT open source. Bring your own LLM.
pypi Proprietary -- (c) Clouthier Simulation Labs. For Neruva integration clients onl -
Bernsteinno update data
Deterministic, verifiable orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, Aider, Cursor and 40+ more), exposed over MCP. Bernstein runs orchestration tasks in isolated git worktrees, records a lineage and replay journal for every run, and can anchor task claims, progress updates and posted artifacts in an opt-in HMAC-chained audit log. Tools: 14 are advertised at the default `standard` tool tier. Set BERNSTEIN_MCP_TOOL_TIER to change the tier: `core` advertises 5, `standard` advertises 14 (default), `all` advertises 18. Transports: stdio (default), Server-Sent Events, and streamable HTTP. Install and run: uvx --from bernstein bernstein mcp or pip install bernstein && bernstein mcp HTTP transport: bernstein mcp --transport http Authentication: the stdio transport needs none. The HTTP transport accepts a static bearer token via BERNSTEIN_MCP_TOKEN or BERNSTEIN_AUTH_TOKEN, and binds to loopback only when neither is set. Documentation: https://bernstein.readthedocs.io Requires Python 3.12 or newer. Package `bernstein` on PyPI, version 3.9.0.
smithery -
Reproduce and record a browser bug once, verify the fix in seconds. A deterministic eye for coding agents — one MCP call instead of a model round trip per click.
MIT -
NovaFlagship 创新旗舰 AI —— 零运行时依赖的智能体引擎:OpenAI 兼容网关、MCP 工具协议、三段式记忆、BM25⊕稠密⊕RRF 混合检索、确定性回放验证。作者:晨星
MIT -
Cross-agent handoff attestor: signed, verifiable delegation with scope narrowing, constraint compatibility, replay protection and chain continuity. Reference implementation of the public SHPBL behaviour specification.
MIT -
maestrogithub.com/rexchengm/maestroupdated this year
Stronger hands for your AI — the RPA it can actually drive. Record a task once; AI optimizes, combines, and composes it into deterministic automations that control your real apps & browser. Pure-vision, local, MCP-native. The smarter the AI, the stronger it gets.
Apache-2.0 ★ 3 -
prworldsupdated this year
PR Worlds — the CLI and MCP server that gives your repo coherent, reproducible worlds your agent can open, replay, and inhabit. v0.2 ships the coherence resolver: agents see the plan's confidence, evidence, and explicit unknowns before the world is materi
npm MIT