Open-source MCP gateway that pins tools, holds risky calls and limits egress
Runs locally- Open source
- Security
Open-source MCP gateway that pins tools, holds risky calls and limits egress
Runs locallyOpen-source MCP server scoring pull-request risk from blast radius and git history
Runs locally
Open-source control plane that firewalls MCP tool calls and caps agent model spend
Policy-gated agent spending with signed receipts and audit against the payment rail
Runs locally
MSP-focused MCP server and CLI for WatchGuard Cloud across customers
Runs locally
Read-only payment preflight for AI agents: pay, review or do-not-pay before signing
Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests
Runs locallyCheck an AI agent's action against signed rules before it commits, with auditable proof
Run an 88-test MCP spec compliance suite and get an A-F grade from CLI or agent
Runs locallyLocal input firewall that scans text, files and MCP metadata for prompt injection
Runs locallySealed microVM sandboxes for agents to run untrusted code, locally or in the cloud
Not checked yetLint CLAUDE.md, AGENTS.md and .mcp.json against your actual codebase
Runs locallyElectron IPC scaffolding, security audits, CSP and build-error diagnosis for assistants
Runs locallynpm registry intelligence, security audits and publish-side writes without the 2FA prompt
Runs locallyScreen an x402 payment counterparty with allow, review or block before an agent pays
Runs locally
Offline AI-law rule checks for the EU AI Act, NYC LL 144, GDPR and HIPAA
Runs locally
Checks an x402 payment against your spending policy and returns pay, review or block
Runs locallyFlags fake engagement and prompt injection in AI-agent job board listings
Runs locallyRoute agent LLM calls through spending caps, metering and verifiable receipts
Not checked yetOpen-source scheduler that runs coding agents in parallel under policy-as-code rules
Runs locallyLocal application security scanner with an evidence ledger and honest gap reporting
Runs locallyChecks an agent's PR handback claims against GitHub's own record with no model involved
Runs locallyPre-action firewall that turns thumbs-down feedback into gates for coding agents
Runs locallyLet an AI agent pay USDC on NEAR only within owner-signed mandates, with a signed ledger
Runs locallyLocal permission gate that allows or stops an agent's tool call before it runs
Runs locallyAudit remote MCP servers for OAuth 2.1 gaps, and generate tested connectors
Runs locallyKubernetes MCP server where every change needs a passkey approval from your phone
Runs locally
Hash and sign evidence of what AI agents did, mapped to AI governance frameworks
Runs locallyFree read-only server listing known security incidents and fix procedures for dev software
Not checked yetSee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.