From a63bb785a379cfca1b3be8f5160bd2ec07610055 Mon Sep 17 00:00:00 2001 From: aurumflux20 <258769813+aurumflux20@users.noreply.github.com> Date: Tue, 1 Sep 2026 12:32:42 -0700 Subject: [PATCH] Add aurumflux20/seal to Security Exactly-once execution for agent money paths (MCP server, stdio, PyPI seal-kernel, in the official MCP Registry). Followed CONTRIBUTING: one server per line, existing format, placed under Security, install command included, links checked. --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 08f1f3ee3..2894b93c5 100644 --- a/README.md +++ b/README.md @@ -3379,6 +3379,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [mastyf-ai/mastyf.ai](https://github.com/mastyf-ai/mastyf.ai) [![mastyf-ai/mastyf.ai MCP server](https://glama.ai/mcp/servers/mastyf-ai/mastyf.ai/badges/score.svg)](https://glama.ai/mcp/servers/mastyf-ai/mastyf.ai) 📇 🏠 🍎 🪟 🐧 - Open-source runtime security proxy for MCP. Transparently intercepts every tools/call through an 18-class attack defense pipeline (prompt injection, SSRF, shell injection, SQL injection, credential exfil, polyglot attacks) with a YAML policy engine and 304-entry adversarial corpus. Trust scoring for npm MCP packages with 0-100 badges. Cloud dashboard, Docker image, Python SDK. MIT. - [timescale/rsigma](https://github.com/timescale/rsigma) [![timescale/rsigma MCP server](https://glama.ai/mcp/servers/timescale/rsigma/badges/score.svg)](https://glama.ai/mcp/servers/timescale/rsigma) 🎖️ 🦀 🏠 🍎 🪟 🐧 - Exposes the RSigma Sigma detection-engineering toolkit to AI agents over stdio or Streamable HTTP with `rsigma mcp serve`. Tools to author, lint, validate, and convert Sigma detection rules, evaluate and explain detections against log events, and inspect correlation state, all backed by a native Rust engine. - [dengyier/OpenWorkProof](https://github.com/dengyier/OpenWorkProof) [![dengyier/OpenWorkProof MCP server](https://glama.ai/mcp/servers/dengyier/OpenWorkProof/badges/score.svg)](https://glama.ai/mcp/servers/dengyier/OpenWorkProof) 🐍 🏠 ☁️ - Verifiable execution protocol for AI agent tool calls. Ed25519-signed PolicyDecisions, causal evidence chains (RFC 8785 JCS), and offline verification from SQLite ledger. 2,281 tests, 2 real-world bugs demonstrated end-to-end. `pip install openworkproof` +- [aurumflux20/seal](https://github.com/aurumflux20/seal) 🐍 🏠 - Exactly-once execution for agents that move money: the same payment can't settle twice across processes or retries. World-confirmation asks the provider ("did this charge actually land?") and returns CONFIRMED_ONE / MULTIPLE / ABSENT / UNKNOWN; out-of-band reconcile catches spend that bypassed the gateway; earned-autonomy licensing (L0–L5) only raises an agent's unattended spend ceiling on proven-clean history. In the official MCP Registry as `io.github.aurumflux20/seal`. `pip install seal-kernel` ### 🌐 Social Media