Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
sevDesk
MCP serversSafety-first MCP server for sevDesk accounting: invoices, receipts, banking, reports. Unofficial.
mcp-server-sevdesk@1.6.0 -
willdeep-cli
Agents & frameworks自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
git clone https://github.com/niuwoai/willdeep-cli.git -
flagrm
SkillsRemove feature flags with your AI coding agent, safely. Skills and guardrails for Claude Code, Copilot and Codex.
git clone https://github.com/dino-cosic/flagrm.git -
spring-ai-playground
AI repositoriesSafe local execution layer for AI agent tools. Build and test-run MCP tools (no pass, no run), serve them from a built-in MCP server, and use them in Agentic Chat with RAG, human-in-the-loop approval, and built-in observability. Cross-platform desktop app powered by Spring AI.
git clone https://github.com/spring-ai-community/spring-ai-playground.git -
Text Tools
MCP serversExact character/word counting, reversal, palindrome checks, indexing, sorting; Unicode-safe.
-
Block Lottos
MCP serversSafe Block Lottos MCP for Base tickets and Base or Polygon jackpot reads.
blocklottos-mcp@1.0.2 -
oracle
MCP serversMCP tools: collectible price-fairness, recall safety, drop tracking, card grading, settlements.
-
mcp
MCP serversEconomic-safety tools for trading agents: executable quote + rug/honeypot pretrade check via x402.
@getplexa/mcp@0.2.0 -
VibeRevert
MCP serversLocal MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
viberevert@0.7.1-beta.4 -
HumanMirror One
MCP serversAgent routing, safety preflight, execution receipts, best execution and verified outcomes.
-
model-scanner
MCP serversScans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
@guardbee/mcp-model-scanner@0.1.2 -
HTTP
MCP serversHTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting.
@abhishekmcp/http@0.1.0 -
ossfind
MCP serversSafety-ranked open-source component discovery for agents across six package ecosystems.
ossfind@0.1.12 -
ghost-publisher
MCP serversLocal-first MCP server for safe Ghost authoring, diagnostics, scheduling, and publishing.
ghost-publisher-mcp@0.10.1 -
ghost-publisher
MCP serversLocal-first MCP server for safe Ghost authoring, diagnostics, scheduling, and publishing.
ghost-publisher-mcp@0.10.0 -
mssql
MCP serversMCP server for Microsoft SQL Server — schema discovery, profiling, safe writes, and DDL
@connorbritain/mssql-mcp-server@0.4.5 -
creedspace-mcp-server
MCP serversConstitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
@creedspace/mcp-server@1.1.4 -
ohm-mcp
MCP serversAST-based Python refactoring MCP server with safe automated refactorings and rollback
ohm-mcp@1.0.1 -
oriel
MCP serversSafety-gated AI control of Docker and Colima: containers, images, volumes, networks, Compose.
ghcr.io/paradoxinfinite/oriel:0.7.0 -
humane-proxy
MCP serversAI safety middleware — detects self-harm and criminal intent in LLM prompts.
humane-proxy@0.6.0 -
quarry
MCP serversSafety-railed database access for agents: Postgres, MySQL, Redis. Read-only by default.
quarry-db@0.2.2 -
Agentic Mermaid
MCP serversRender, verify, describe, and safely edit Mermaid diagrams through MCP.
agentic-mermaid@0.5.6 -
Facebook Publisher
MCP serversSafe Facebook Pages publishing with brand-voice, image-required & anti-duplication checks.
mcp-fb-publisher@0.1.1 -
NSFW Image Detector
MCP serversNSFWJS-based image safety detector (GIF/APNG/WebP/JPEG/PNG).
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.