Keystash
MCP servermacOS Keychain secret broker where an agent can use your API keys but never read them
Runs locally- 6 tools
- Open source
- Security
macOS Keychain secret broker where an agent can use your API keys but never read them
Runs locallySearch Microtoll Engine docs and scaffold an end-to-end-encrypted notes app locally
Runs locallyRead-only WordPress plugin audits: vulnerabilities, leftovers, autoload weight and cron
Not checked yetExact-action approval and signed receipts for consequential AI agent actions
Runs locallyTrade Compliance MCP — the two questions an importer asks that the tariff schedule alone…
Not checked yetArticle-level answers on China's AI filing, labelling and algorithm rules, in Chinese
Not checked yetNetwork scanner for AI agents: host discovery, port scans, DNS, ARP and mDNS lookups
Runs locallyHosted MCP checks that npm and PyPI packages, versions and functions actually exist
Not checked yetGo daemon giving AI agents scoped Linux host tools over MCP instead of an SSH shell
Not checked yetFind vendor trust centers, analyze SOC 2 reports and request access from an AI client
Not checked yetLet an agent clear node_modules and other junk folders, only inside roots you allow
Runs locallyRead-only Postgres access for agents that parses SQL and refuses write-capable roles
Runs locallyOn-premises document retrieval for agents, with folder-level access rules checked first
Runs locallyRead-only npm preflight: reviews what install scripts do before packages run
Runs locallyOWASP API Top 10 tests from your OpenAPI spec, plus scanner SARIF judged for release.
Runs locallyMCP server that checks if a video is AI-generated, scoring picture and sound separately
Not checked yetTamper-evident local record of what your AI agent did, plus verifiable markdown memory
Runs locallyGuard agents' PostgreSQL and MySQL access with SQL audit, masking and write approval
Not checked yetRole-aware onboarding answers about a codebase, filtered to what the caller may see
Not checked yetFind and strip zero-width, bidi and tag characters hidden in text, offline
Runs locallyCheck an agent work row, post one and preflight a no-spend cap before spending
Runs locallyAccess control for AI agents: allow, hold for approval or block each tool call
Runs locallyCNCF release intelligence: typed changes from release notes and local stack checks
Runs locallyMCP server and open protocol for signed messages between agents with human-gated approvals
Runs locallySigned, hash-chained receipts of agent tool-call decisions, verifiable offline
Runs locally
Vulnerability management across all ConnectSecure clients: exposure ranking, CVE impact…
Runs locally
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
Runs locally
Hook Security phishing and training data for MSPs: click rates, overdue training, QBR…
Runs locally
Read-only Keeper MSP posture across every client, with history, a change feed and no…
Runs locallyFraud and abuse investigation, escalation triage and rule tuning inside Dregs
Not checked yet