In-A-Lign Agent Provenance & Security MCP Server
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"inalign-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<p align="center"> <h1 align="center">InALign</h1> <p align="center"><strong>Tamper-proof audit trails for AI agents</strong></p> <p align="center">Know what your AI agents did. Prove it. Cryptographically.</p> </p> <p align="center"> <a href="https://pypi.org/project/inalign-mcp/"><img src="https://img.shields.io/pypi/v/inalign-mcp?color=blue" alt="PyPI"></a> <a href="https://github.com/Intellirim/inalign/blob/main/LICENSE"><img src="https://img.shields.io/github/license/Intellirim/inalign" alt="License"></a> <a href="https://pypi.org/project/inalign-mcp/"><img src="https://img.shields.io/pypi/pyversions/inalign-mcp" alt="Python"></a> </p> --- ## Zero Trust. Zero Cloud. Zero Telemetry. InALign is **fully decentralized by design**. There is no InALign server. No account. No telemetry. Nothing leaves your machine — ever. | | Other audit tools | InALign | |---|---|---| | **Where data lives** | Their cloud | Your machine only | | **Account required** | Yes | No | | **Telemetry** | "Anonymous" usage data | Zero. Not a single byte. | | **Paid features** | Require their servers | Run 100% locally with your own API key | | **What they see** | Your agent's actions | Nothing. We can't see anything even if we wanted to. | Even Pro features like the AI Security Analyzer use **your own LLM API key** and run entirely on your machine. Your data never touches our infrastructure because **we don't have infrastructure**. ## What's New in v0.9.1 - **PROV-AGENT Ontology** — W3C PROV + PROV-AGENT compliant knowledge graph with 8 node classes, 13 relation types, and LLM reasoning tracked as first-class PROV activities - **AI Security Analysis** — Two modes: Zero-Trust (local Ollama, data never leaves your machine) and Advanced (Claude/OpenAI API with 14 PII patterns masked) - **React SPA Dashboard** — Modern dark-theme dashboard at `localhost:8275` with Overview, Sessions, Security, and AI Analysis pages - **Performance** — Dashboard overview loads in 0.3s, session …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.