- Conduid
- Marketplace
- #provenance
MCP servers tagged provenance
260 live MCP servers tagged "provenance", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with provenance.
Bruriah
An MCP server that lets an agent consult your knowledge without letting your knowledge instruct the agent. Evidence with provenance, never instructions.
Flowproof MCP
Run reproducible bioinformatics pipelines from an AI assistant over MCP, with verifiable provenance
Norms MCP Engine
Fail-closed evidentiary eligibility engine for AI-agent norms, with a self-linting claim map.
Litmuz Agent
Claim-level verification for life-sciences research agents: honest, auditable, per-claim traffic-light verdicts against the primary literature and genomic reference data. MCP-nati…
Prioritize4me
A local-first personal AI OS: a provenance-checked memory and a commitment cockpit, with a trust boundary that keeps your private data off the network.
Osiris
The persistent memory and coordination graph for AI agents (MCP, DeepSeek Harness, Claude Code, Cursor)
Heydey
Local-first AI OS that proves every answer: per-sentence receipts, a fail-closed check by a different model family, cite-or-silent refusals. Interactive knowledge graph, artifact…
Proofspec
Claims are cheap. Proofspec makes them executable — evidence contracts, claim graphs, hash-chained receipts, CI gates, reports, and MCP for public software claims.
Loomdb
An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a p…
Altretta Skill
Give your AI a second brain. Altretta connects your local, encrypted knowledge vault to 70+ AI agents with query-first, cited retrieval and signed provenance.
Sssnack Plugin
Agent-native MCP, CLI, and skill for discovering and publishing visual work on SSSNACK.
Lex Provenance MCP
Verifiable, provenance-first legal corpora for AI systems - a read-only MCP connector (search, fetch, and hash-verifiable citations).
Provenanceguard
Source-aware factuality verification for MCP-based LLM agents — paper artifact
LongTable
Research control plane for AI-assisted scholarship: durable human checkpoints, lawful evidence provenance, and verifiable research packages.
Epistemedia
Knowledge that can show its work: an open, federated knowledge system for humans and agents.
ATF AI
Infrastructure-agnostic trust and governance protocol for autonomous agents, RWA privileged actions, verifiable provenance and compliant digital-asset workflows.
UST Protocol
RSS for state. Open portable evidence layer for machine state - preserving what an agent or system saw, produced, derived and learned, so another party or future agent can verify…
Maqam
Give AI agents hands without handing them the keys: exact one-use approvals and verifiable receipts for registered actions.
Machine Meaning Layer
Open protocol proposal for AI-readable, claim-level, verifiable web content using JSON-LD, provenance, signatures, embeddings and trust signals.
Haypile Lite
A local-first asset haypile for agent workflows: drop files, register bundles, hand them off through HTTP/MCP.
Data Science Agent
Verifiable AI data scientist for CSVs and databases — SQL, statistics, ML, and visualization with claim-level evidence and reproducible artifacts.
Dreamnet
Open contracts for persistent AI agents: assignments, Capsules, DreamLoops, claims, receipts, and deterministic validation.
Suede SDK Python
Python SDK for the Suede Labs AI x402 surface — pay-per-call music, stem, MIDI, mastering, and IP endpoints, settled in USDC on Base. By Jason Colapietro.
Delegated Fidelity
The handshake for agents acting on the open internet. Six layers say the authorization is legal; the seventh asks the only question that matters once it is — is the agent still yo…
Command Scope Contract
Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.
Decision Trace Reconstructor
Post-hoc trace reconstruction for AI agents: turns raw runtime traces into per-property reconstructability reports naming evidenced, missing, and opaque decision facts.
Attestload
attestload
Scavenge
Deterministic web-evidence engine: trace one field across raw HTML, structured data, embedded state, rendered DOM and network JSON, with exact provenance. CLI and MCP. No LLM.
Retconary
Local memory firewall that stops AI agents from acting on stale decisions.
Codedistill
CodeDistill Community Edition — open-core (AGPL-3.0). The full scratchpad→classify→verify→provenance loop; commercial editions add MCP write tools, code anchors, and more.
Proto Agent Workbench
Local AI workbench for auditable DNA design, real protein structures and governed biological materials. Python CLI, MCP and Windows desktop.
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。
PROOFCHAIN
Cryptographic provenance for AI agents on the live web. Ed25519-signed, hash-chained evidence for every Bright Data fetch. EU AI Act Article 12 compliant. MIT.
Syncropel
An open coordination protocol for human + AI teams: immutable records, evidence-based trust, and workflows that learn and replay.
Agentroots
Evidence-governed continuity for AI agents. Different agents. Same roots.
Attestroot
Local-first, tamper-evident audit and evidence layer for AI agent activity. Hash-chained capture, RFC 6962 Merkle sealing, offline-verifiable bundles.
Dgb Attest MCP
On-chain attestation for the AI era: hash content onto DigiByte for permanent, timestamped, tamper-evident proof of existence. Verify anytime.
Oscillink Agent
Governed project memory for coding agents—corrected, cited continuity across compaction and restarts.
Plr MCP
Auditable MCP tools for PyLabRobot: run and sample context, typed provenance, simulation by default, and explicit hardware permission.
Atrib
Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.
Lexius
AI regulatory compliance tool with provenance-tracked verbatim law. 20 regulations, 2 jurisdictions (EU + Cayman Islands CIMA). 1,456 articles, 8,123 deterministic extracts. No ha…
Magus Mcpsentinel
Deterministic, non-executing evidence and change monitoring for public npm MCP servers. Reports what changed since the version you approved. It never claims a package is safe.
Agentlock
An MCP server wrapper that gates tool calls on where a value came from, not what it says. Catches cross-hop prompt-injection laundering.
Apohara Sealchain
Tamper-evident, independently-verifiable receipts for AI artifacts — a single Rust binary (CLI + MCP server) with five real cryptographic layers and always-offline verify.
Slsa Supply Chain MCP
🔌 Exposes SLSA v1.0 supply chain levels + provenance attestation.
Mint Attest
mint-attest — Python SDK for universal work attestation. Register, attest, verify, rate, recommend, and discover agents on the MINT Protocol. @attest decorator + LangChain/CrewAI/…
Rutter
A record of what your AI sessions decided — and the receipts behind it. An MCP memory-of-use server over markdown notes: append-only, content-hashed, no model inside.
Evidence Lane Plugin
Evidence Lane v4 is in active development. Public source is available; install only from a verified v4 release tag after release qualification.
Aibom
Generate an AI bill of materials for models, MCP servers, tools, datasets, vector stores, and external APIs.
Northstar Workload Optimizer
Governed expense-operations platform with deterministic policy execution, durable workflows, provenance, evaluations, observability, and MCP interfaces.