Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
mcp-android
MCP serversControl Android devices over ADB from AI agents — safe-by-default, read-only by default, audited.
@dockndevai/mcp-android@0.1.0 -
mcp-cdp
MCP serversSafe-by-default MCP that drives an Electron/Chrome app over CDP: DOM, console, network, input.
@dockndevai/mcp-cdp@0.2.3 -
mcp-ios
MCP serversDrive iPhone/iPad via Appium/WebDriverAgent from AI agents — safe-by-default, read-only by default.
@dockndevai/mcp-ios@0.1.0 -
mcp-laya
MCP serversSafe-by-default MCP for Laya: fast, local, typed decisions (classify/score/yes-no), 100+ langs.
mcp-laya@0.1.1 -
bies-guardian
MCP serversDeterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian).
-
fluxgit-mcp-server
MCP serversSafety-first Git MCP server: rich read tools plus human-approved FluxGit operation proposals.
fluxgit-mcp-sidecar@0.2.1 -
eds-mcp-server
MCP servers41 tools for Adobe Edge Delivery Services: read, audit, track, monitor, fix, publish, undo — safely.
@focusgts/eds-mcp-server@0.15.0 -
Gizmos Audacity
MCP serversSafe local audio editing, analysis and production in Audacity 3.7 through mod-script-pipe.
@gizmos-quest/audacity-mcp@0.1.0 -
arbiter
MCP serversIs this transaction safe to sign? Decodes what it really does and answers allow, warn or block.
@arbiterlabs/mcp@0.1.1 -
MoySklad MCP (RU)
MCP serversMoySklad JSON API 1.2 in your AI assistant — schema-driven, safety-gated document writes.
moysklad-mcp-ru@0.2.0 -
Evercraft Web
MCP serversRead public web content with Evercraft; search and browser automation stay behind safety gates.
-
shopify-operations-mcp
MCP serversSafe-write Shopify operations: plan-before-execute writes with out-of-band approval and audit.
shopify-operations-mcp@0.1.2 -
nextjs-cache-handler-mcp
MCP serversInspect and operate Next.js Redis caches: health, tag state, SWR simulation, safe invalidation.
@leejpsd/nextjs-cache-handler-mcp@0.1.2 -
nervous-system
MCP serversGovernance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.
mcp-nervous-system@1.12.1 -
agent-firewall-mcp
MCP serversInput/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
agent-firewall-mcp@1.3.0 -
email-guard-mcp
MCP serversEmail safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
email-guard-mcp@1.3.0 -
HubSpot
MCP serversHubSpot API: 1,000+ endpoints as safety-categorized, hub- and plan-aware MCP tools, stdio or HTTP.
ghcr.io/ohneben/hubspot-mcp:2.0.1 -
Open Agreements
MCP serversFill standard legal agreement templates (NDAs, SAFEs, NVCA docs, employment) as DOCX files.
@open-agreements/contract-templates-mcp@0.10.2 -
Patchloom
MCP serversAgent-safe structured edits: JSON/YAML/TOML/md/AST, dry-run, batch/tx. Not a filesystem MCP.
patchloom@0.37.7 -
QueryBear
MCP serversSafe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
-
Apache Pinot MCP Server
MCP serversQuery and manage Apache Pinot through MCP with typed tools and preview-first safety.
mcp-pinot-server@5.0.0 -
SMB Sandbox
MCP serversMock small-business CRM, inbox, calendar, invoicing and phone tools for testing AI agents safely.
@teamshift/sandbox-mcp@0.1.0 -
mcp-for-ynab
MCP serversYNAB budget access for AI assistants: safe gated writes, month-close sessions, float attribution.
@walensis/mcp-for-ynab@0.2.0 -
Respira WordPress MCP
MCP serversAI-native WordPress editing across 19 page builders. 283 tools, 387 with WooCommerce. Safe writes.
@respira/wordpress-mcp-server@8.7.7
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.