Keyword: firewall
- pando-aiReleased3d agoVersion0.9.8
AI coding firewall for Codex and Claude Code
- @fidacy/mcpReleased23h agoVersion0.1.5
Fidacy action firewall for AI agents. Mandate-gated payment authorization as an MCP server.
- @solongate/proxyReleased22h agoVersion0.49.0
AI tool security proxy — protect any AI tool server with customizable policies, path/command constraints, rate limiting, and audit logging. Zero code changes required.
- @kehto/firewallReleased6d agoVersion0.3.2
Pure, WASM-ready behavioral firewall engine for the napplet protocol — zero dependencies, zero side effects
- @noirtrack/sdkReleased1 week agoVersion0.2.0
NoirTrack server SDK. Block bots and bad traffic before your app renders, and record goals, revenue, and identify from your backend with one secret key. Framework-agnostic core plus Next.js, Express, and fetch/edge adapters.
- @emilia-protocol/gateReleased4h agoVersion0.7.0
EMILIA Gate — the Trusted Action Firewall. Deny-by-default enforcement for consequential machine actions: an action runs only with a valid, in-scope, sufficiently-assured, non-replayed EMILIA authorization receipt (proof a named human authorized this exac
- @arcane-spark/ubel-nodeReleasedyesterdayVersion0.6.0
Supply-chain security firewall for Node.js — resolves dependencies, scans via OSV.dev and NVD, and enforces configurable vulnerability policies before anything reaches node_modules.
- lurien-matrixReleased3h agoVersion1.0.1
Production-grade firewall proxy client for LLM APIs. Intercepts and blocks prompt injections.
- @emilia-protocol/fire-drillReleased3h agoVersion0.3.1
The Agent Action Firewall Test. Scan any MCP server manifest, OpenAPI spec, or tool list for dangerous actions an AI agent can take without an accountable human receipt — money movement, data destruction, production deploy, permission change, bulk export,
- voidhack-agent-firewallReleased17h agoVersion1.0.0
Drop-in security guardrails for AI agents. Blocks unauthorized tool calls, exfiltration, prompt injection, and secret leaks — in-process, sub-millisecond, zero network.
- @stbr/safe-ai-skillReleased2d agoVersion1.0.0
Security firewall + supply-chain verifier for Solana AI dev — gates transactions, deploys, and secrets; verifies skills and MCPs.
- safe-ai-skillReleased2d agoVersion1.0.0
Security firewall + supply-chain verifier for Solana AI dev — gates transactions, deploys, and secrets; verifies skills and MCPs.
- @consensus-tools/wrapperReleased2d agoVersion0.11.0
Runtime decision firewall — wraps any function with consensus gates
- llm-firewall-jsReleased2d agoVersion0.1.0
A lightweight, framework-agnostic JavaScript firewall for protecting LLM API routes from prompt attacks, secret leakage, spam abuse, and runaway usage costs.
- @wasmagent/mcp-firewallReleased2d agoVersion1.3.4
Runtime firewall for MCP and tool-augmented agents — descriptor integrity, static vetting, per-call policy, taint tracking, consent ledger
- @khushwant.r/promptguardReleased5d agoVersion0.1.1
Secret firewall for AI prompts. Scans prompts for API keys and secrets and blocks them before they're sent to Cursor or Claude Code, via a local prompt hook.
- eicar-testReleased6d agoVersion0.0.1
EICAR-style firewall/scan test package (SAFE, non-malicious). For validating Sonatype IQ/Firewall publish+scan workflow in a private repo.
- eicar-fw-testReleased6d agoVersion0.0.2
EICAR-style firewall/scan test package (SAFE, non-malicious). For validating Sonatype IQ/Firewall publish+scan workflow in a private repo.
- airlock-cliReleased6d agoVersion0.1.0
A firewall between AI coding agents and dangerous actions. Blocks hallucinated packages, leaked secrets, destructive commands, and test-subversion.