Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
easyserp
MCP serversSearch Google and Bing through MCP with source-domain filters and safe request recovery.
https://github.com/aiispower/easyserp/releases/download/v1.0.0/easyserp-1.0.0.mcpb -
tz-mcp
MCP serversTimezone toolkit: convert and compare instants across IANA zones with DST-safe arithmetic
@nopilot/tz-mcp@1.0.1 -
browser-verified-skill
SkillsBrowser automation with evidence. An Agent Skill that lets an AI agent drive a real browser while every action passes a policy gate, every run leaves an auditable artifact, and the run compiles into a plain Playwright script that replays for free.
git clone https://github.com/OMD-123/browser-verified-skill.git -
construction-agent-skills
Skills28 installable agent skills for construction: estimating, architecture, rendering, engineering, scheduling, site, safety, commercial and BD. Claude Code plugin, plain SKILL.md, CC BY 4.0.
git clone https://github.com/constructelligence-lab/construction-agent-skills.git -
nestjs-skills
SkillsSeven Agent Skills for NestJS implementation, architecture, OOP, code and feature audits, runtime performance, and safe Git publication.
git clone https://github.com/amirtaherkhani/nestjs-skills.git -
devops-ai-kit
SkillsRules, skills, subagents and guardrails that make Claude Code safer for DevOps and cloud infrastructure work (Kubernetes, Terraform, Ansible, Helm, Argo CD, Azure/AWS/GCP).
git clone https://github.com/hoangminhung/devops-ai-kit.git -
Arclan MCP Registry
MCP serversMCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.
-
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.
-
PoliteReach
MCP serversLinkedIn outreach from Claude: invites under safe caps, follow-ups, replies and inbox triage.
-
SkanQRCode
MCP serversCheck whether a URL or IP is safe before an AI agent fetches or opens it.
@skanqrcode/mcp-server@1.0.0 -
Tudetic Product Search
MCP serversRead-only Tudetic product search and vehicle compatibility with safe public pricing.
-
emailmd
MCP serversRender markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
emailmd@0.13.3 -
Trust Live
MCP serversEvidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.
-
LTD MCP
MCP serversProject management MCP for AI agents with safe task reads and writes.
-
Bollard MCP
MCP serversAn AI-powered, safe database access gateway built on the Model Context Protocol (MCP).
bollard-mcp@0.1.4 -
maias
MCP serversValidate, query, safely edit, and wireframe MAIAS app-IA documents: cascading renames, atomic edits.
@maias/mcp@0.5.1 -
NodeRooms Discovery
MCP serversRead-only NodeRooms Agent discovery, safety policy, public indexes, and arrival contract.
-
elementor-mcp-agent
MCP serversAgency-grade MCP for WordPress Elementor — multi-site, safe edits, templates, versions.
elementor-mcp-agent@1.3.0 -
regex-test-mcp
MCP serversTrustworthy JS regex testing. Real offsets, named groups, safe against zero-width loops.
@mukundakatta/regex-test-mcp@0.1.0 -
thrd
MCP serversThrd MCP: agent email tools for events/threads, safe send/reply, usage, trust and security.
thrd-mcp@0.1.5 -
nr-mcp
MCP serversMCP server for Node-RED — safe deploy, optimistic locking, smart search, 13 tools
nr-mcp@1.2.2 -
TrustFetch
MCP serversPrompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
-
agentiam-mcp
MCP serversStdio MCP wrapper for AgentIAM's 18 x402 endpoints — agent safety + intelligence on Base.
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.