Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Onça Setorial
MCP serversBrazilian regulator data: CVM filings, dam safety, airline punctuality, rules, enforcement
-
Complitas
MCP serversFor Complitas customers: use your Complitas building safety compliance account (account required)
-
ProofPass
MCP serversCurrent safety data sheets and product documents from manufacturers; EU deadlines and duties.
-
oasis
SkillsThe open-source coding agent for any model: terminal and self-hosted web app, Claude Code plugins, subagents, and work that is actually verified.
git clone https://github.com/FAHTHIZ/oasis.git -
tailscale-superpowers
SkillsPro Tailscale workflows for every device you own, run by your AI agent with a safety tier on every command. Community skill, not affiliated with Tailscale.
git clone https://github.com/cathrynlavery/tailscale-superpowers.git -
futureagievals-mcp
MCP serversA paid remote MCP for AI SDK eval dashboard, built to return verdicts, receipts, usage logs, and aud
-
Vellarin Hub
MCP serversApps with human approval, shared memory, a run log and evals for your agent. One URL, one key.
-
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
boundaryai
MCP serversDeterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
-
Enoki
MCP serversTest your AI agents for security and safety weaknesses, and re-verify the fixes.
-
GuildControl MCP
MCP serversSafety-first MCP server for Discord with privacy-safe reads, audits, and reviewed administration
guildctl@2.3.9 -
NodeRooms Discovery
MCP serversRead-only NodeRooms Agent discovery, safety policy, public indexes, and arrival contract.
-
agentiam-mcp
MCP serversStdio MCP wrapper for AgentIAM's 18 x402 endpoints — agent safety + intelligence on Base.
-
EP AgentIAM
MCP serversAI agent execution safety via x402 micropayments: risk scoring, integrity, memory checks
-
lu
MCP serverslu.ma events MCP server with draft+confirm safety, audit logging, and prompt-injection scrubbing.…
https://github.com/adelaidasofia/luma-mcp/releases/download/v0.1.0/luma-mcp.mcpb@0.1.0 -
queryshield
MCP serversSecure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.
queryshield-mcp@1.0.1 -
mongo-scout-mcp
MCP serversScout your MongoDB databases with AI - safety features, live monitoring, and data quality
mongo-scout-mcp@1.0.3 -
calllint
MCP serversStatic preflight safety gate for MCP servers — scan configs before you run them. Never executes.
calllint-mcp@0.2.1 -
outreach-deliverability-mcp
MCP serversChannel-safety for cold outreach: volume limits, SPF/DKIM/DMARC, spam-trigger auditing.
outreach-deliverability-mcp@1.0.2 -
K-Work Trust
MCP serversKorean business record validation and workflow safety gates for AI agents.
-
agent-guard
MCP serversSafety checks an agent runs before it acts: package malware, destructive command, secret leak.
agent-tripwire@0.2.1 -
sw-postgres-mcp
MCP serversSafe-write Postgres MCP server with preview-before-execute writes and rollback safety.
sw-postgres-mcp@0.3.1 -
agent-guard-mcp
MCP serversVerify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
@liminallablibs/agent-guard-mcp@0.2.1 -
open-compute (computer-use)
MCP serversModel-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting.
open-compute-mcp@0.1.0-alpha.6
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.