#provenance

Protect media from AI training, detect AI-generated content, and find stolen work. 27 tools for watermarking, C2PA provenance, similarity search, and licensing.

Memory with integrity for AI coding agents. SAME tracks provenance, flags stale knowledge, and surfaces contradictions; so your AI trusts what's current, not what's outdated. 17 MCP tools: semantic search, cross-vault federation, session handoffs, decision logging, knowledge graph, trust-aware retrieval, consolidation, health analysis. Provenance on every write. Stale notes rank lower automatically. SQLite + vector search. Ollama, OpenAI, LM Studio, or keyword-only. One 12MB Go binary. No cloud, no API keys, no telemetry. Your notes never leave your machine. Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and any MCP client.

Audit-grade memory backbone for agent teams. Bi-temporal facts (event time + transaction time, with recall(as_of=...) replay), 6-step deterministic retrieval (no LLM in the critical path), conversation ingest with speaker-locked dual-pass extraction, per-tenant Postgres row-level security, and Ed25519-signed provenance. Postgres + pgvector + Neo4j defaults; ArangoDB / DynamoDB / Cosmos / AlloyDB also supported. Listed on the official MCP Registry as io.github.bolnet/attestor.

AnchorRegistry is the open provenance layer for the agentic economy. Every digital artifact — code, research, data, models, media, agents, transactions — can be anchored to Base L2 with a permanent, machine-resolvable identifier (an AR-ID). When an AI assistant encounters an SPDX-Anchor or DAPX-Anchor tag in a README, paper, model card, or website, this MCP server lets it resolve the artifact's full provenance record in one call: who anchored it, when, what type it is, manifest hash, and whether the tree has been sealed, retracted, voided, or affirmed. This is the verify-only edition (v0.1). Three read-only, authless tools wrap the public AnchorRegistry verify endpoints. Free, no API key, no account, no rate limit beyond defaults. Future versions will add registration, balance, and seal tools once the MCP credential pattern stabilizes.

AI agents make decisions you can't audit. Lemma fixes that with zero-knowledge proofs over confidential documents — selective disclosure, on-chain provenance, no plaintext exposure. Query cryptographically verified attributes from agents in production. Built for regulated industries and x402/MCP-native developers. Models change. Proofs remain.

mcp-kinetic-gain is a single stdio MCP server that exposes all eleven Kinetic Gain Protocol Suite specs to any MCP-compatible client (Claude Desktop, Cline, Cursor, etc.) — 71 tools across AEO Protocol, Prompt Provenance, Agent Cards, AI Evidence Format, MCP Tool Cards, AI Tutor Cards, Student AI Disclosure, Classroom AI AUP, Clinical AI Disclosure, AI Incident Card, AI Procurement Decision Card, plus the DefenseTech 6-pack tooling shipped in v0.8.0. Includes ed25519 attestation verification, hash-chained audit-stream event composition and chain verification (offline AND live against a running audit-stream-py via the optional AUDIT_STREAM_URL env var), cross-spec drift detection, and a Decision Intelligence preview that generates a PolicyBundle from a Decision Card, infers rubric status, and plans incident remediation. Also doubles as a CLI: `npx mcp-kinetic-gain validate path/to/doc.json` auto-detects which Suite spec a JSON file belongs to and validates it against the same zod schemas the MCP tools use. No API key. No build step. Headline tools: aup_check_compliance, decision_card_validate, decision_card_to_policy_bundle, attestation_verify, suite_doc_drift, audit_chain_verify, audit_event_emit, audit_events_query, audit_chain_verify_live. Repo: https://github.com/mizcausevic-dev/mcp-kinetic-gain Suite: https://suite.kineticgain.com License: Apache-2.0