- Conduid
- Marketplace
- #reproducibility
MCP servers tagged reproducibility
56 live MCP servers tagged "reproducibility", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with reproducibility.
Scitex Python
Umbrella package for SciTeX — reproducible science from raw data to manuscript
Paperdelta
Trace changed experiment results to the numbers, claims and figures in your LaTeX paper. Offline bilingual review, safe numeric patches and read-only MCP tools.
TRACE
TRACE protocol for auditing decision-provenance in AI-assisted scientific workflows
Avo
Open reproduction of NVIDIA's AVO paper (arXiv:2603.24517): evolutionary search where an autonomous coding agent IS the variation operator — Vary(P)=Agent(P,K,f). Runs on the Clau…
Red Team Blue Team Agent Fabric
AI agent security harness, adversarial testing: 611 executable tests in the v4.20.0 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loo…
AegisTrace
AegisTrace - verifiable execution for durable AI agents. Compile policy-bound workflows, record every effect, replay without the network, and prove individual events.
Sharpebench
MCP server exposing SharpeBench's luck-robust quantitative evaluation tools for trading agents, including deflated Sharpe, pass^k, process discipline, and risk analysis.
Woma
Conda for AI coding agents: give your Claude Code and Codex named, isolated sets of Skills, plugins and MCP servers, and recreate the whole harness from one file.
MCP Server Attestation
Auditable research provenance as local-first MCP tools. The claim checker, paper feed, knowledge graph and symbolic math assume nothing about your field — any results JSON or CSV…
CSCCD MetagenomeFlow
Gut-metagenome multi-kingdom analysis platform: 183-script + Snakemake pipeline, agent-driven mining loop, MCP visualization — VibeCoding-ready
Agent Emulator
Emulation & experimentation platform for trustworthy AI agent infrastructure —trace-driven replay of agent behavior on a sharded blockchain. Built on BlockEmulator-X by HuangLab @…
Agent Engineering Toolkit
Proof-carrying workflows for coding agents: bind tests to exact code, detect stale evidence, review scope, and hand proof across agents.
Hermes Rubric
Evidence-first LLM-as-judge scoring for AI artifacts — papers, PRs, prompts, cold emails: synthesizes a rubric, collects quoted-evidence citations, scores only against that eviden…
Gnosislab
A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.
Clew
Lineage-based impact analysis and remediation for workflow runs. What a bad input or an incident report reached, what to re-run, delete or disclose, sealed as evidence an auditor…
Gnosislab Vm
Virtualized GnosisLab research environment with KVM isolation, protected scientific services, and sandboxed experiment execution.
Agora
A live research world where autonomous AI agents challenge, reproduce and audit each other's work. Agents run on their owners' machines; keys never leave. Open protocol, auditable…
Litmus
An AI reproducibility auditor that predicts whether a scientific paper's claims will replicate. Deterministic forensic checks, multi-source retrieval, calibrated verdicts, and an…
Comsol Research Workflow
中文自然语言驱动 COMSOL：Java 官方进度窗口 / MCP 原生 GUI，交付完整可视 MPH
Deterministic Agent Gatekeeper
Determinism you can prove for AI agent tool calls: a pure decision core whose every verdict re-derives hash-exact from its record.
Repro Gate
Action-bound authorization and verifiable evidence contracts for MCP tool execution
Webaudit
Evidence-first browser automation for AI agents and operators, with recovery and MCP.
Attestation
Auditable research provenance as local-first MCP tools. The claim checker, paper feed, knowledge graph and symbolic math assume nothing about your field — any results JSON or CSV…
Dsh Research Check
Deliverable evidence-chain & conformance checks for DSH — turn requirements into an executable spec, trace every number to a provenance ledger, audit PDF/OOXML metadata and archiv…
Workagent
Others ship conversations, we ship reproducible conclusions. A zero-dependency agent delivery-package format and toolchain: 12 verifiable scenarios organised by delivery form, 22…
Web Agent Comparison
Reproducible 8-dimension benchmark of 7 browser-automation MCP servers (Playwright, Lightpanda, browser-use, Chrome DevTools, Firecrawl, Cloakbrowser, Obscura) against frozen loop…
Readproof
Readproof — the lockfile and replay primitive for what AI agents read: stable identity, freshness policy, content-addressed snapshots, per-run manifests, diff, byte-exact replay,…
AI Assisted Insights Agent
MCP agent translating natural language questions into explainable, reproducible data insights with built-in quality checks and semantic layer integration.
Oncora
Oncora — A Reproducible, Uncertainty-Aware Agentic Reasoning Platform for Oncology Drug Discovery (Rust-native, on-prem, MCP)
Flowproof MCP
Run reproducible bioinformatics pipelines from an AI assistant over MCP, with verifiable provenance
Lca Copilot Open Demo
Open evidence demo for SDAI LCA Copilot: Brightway reference LCIA, provenance, uncertainty, and reproducibility bundles.
ASAREE
A visual analytics platform for engineering, executing, and evaluating reproducible agentic AI teams using experimental design methods.
Claude Snaps
Session-event-driven snapshot lineage for your Claude Code agent's .harness/ composition. Time-travel, diff, reproduce.
Data Science Agent
Verifiable AI data scientist for CSVs and databases — SQL, statistics, ML, and visualization with claim-level evidence and reproducible artifacts.
Shadow Threads
Deterministic workflow state and execution replay for AI systems
Agenticstash
Deterministic record and replay for agent runs. A zero-runtime-dependency TypeScript library and CLI that captures every source of non-determinism an agent touches (model output,…
Urusilla
Open AI-agent interoperability research. Bring your own agent, complete verified public work, and earn contribution credit; if URSL launches, 1 credit = 1 URSL.
Prfrail
Provable rails for unattended AI engineering — every code change, gate, evidence and rollback is auditable. / ProofRail 为 AI 无人值守编程铺设可证明的轨道——代码变更、门禁、证据、回滚，全程可审计。
PermitWeave
Local-first, explainable runtime policy gateway for AI tool calls
Aobench
Role-aware, permission-enforced benchmark for LLM agents that operate HPC systems — SLURM, telemetry, RBAC, docs, facility. A policy violation hard-fails the task. 88 tasks (10 ca…
Elbi
Write a Python function. Elbi serves it to AI agents over the Model Context Protocol as a versioned, cached, verified tool.
Coordination Noise Floor Protocol
Code, data & paper: How Much Coordination Gain Is Real? A Paired Noise-Floor Protocol for Multi-Agent LLM Benchmarks (KDD 2026 Workshop)
Moemodels
Open tooling and verifiable evidence for planning, measuring, and reviewing mixture-of-experts deployments.
Agentic Base
Run provenance, comparison validity, and the shared primitives for agentic work on research infrastructure. A base layer, not an agent framework.
Evidence First Agents
Deterministic readiness and boundary checks for AI-agent projects across skills, MCP, tools, approvals, and handoffs.
Figops
FigOps: reproducible research figure pipelines and MCP tooling
Reprogate
GitHub Action and CLI that checks issues/PRs for reproduction steps, environment details, and logs
Launchcheck
Safe, local-first preflight diagnostics and reproducible failure bundles for MCP servers.
Cct
Reproduction harness, released run (n=144, qwen3:32b), and transcripts for the CCT inference-time probe — curated δ_IT method context vs δ_ref answer-keys — from 'Curated Context,…
Papercheck
A reproducible audit harness for mathematical LaTeX papers: deterministic scanner, schema-validated issue ledgers with mechanical quote verification, and a stage-gated final gate…