Add Assay to Agent Firewalls & Gateways#56
Open
Rul1an wants to merge 1 commit into
Open
Conversation
Policy-as-code gate for MCP: a fail-closed proxy that denies risky tool calls before they run, emits offline-verifiable evidence bundles, and enforces IPv4/TCP egress in-kernel via eBPF/LSM and Landlock on Linux.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds Assay to Agent Firewalls & Gateways (Runtime Protection), alphabetically after AgentGateway. It sits between the agent and the world exactly as the section describes.
Assay is policy-as-code for MCP: a fail-closed proxy that denies risky tool calls before they run, produces offline-verifiable evidence bundles of what actually executed, and enforces IPv4/TCP egress in-kernel via eBPF/LSM and Landlock on Linux. Rust, MIT, offline-first.
Entry kept to one line in the section format. It's deliberately bounded: a gate and an evidence layer, not a prompt-injection or tool-poisoning scanner and not a trust score. Thanks for curating this!