Home › Search: safety

Search: safety

Search MCP servers and agent skills by name, description, category or topic — 70 results.

MCP Server Maintained

CKBrennan/overtone-news-mcp

Real-time news with tone analysis, brand safety, and narrative shift signals for AI agents.

1 Python Updated 2mo ago Score 46
MCP Server Maintained

wei9072/aegis

AI-agent admission-control MCP server: validates file edits against Ring 0 syntax + Ring 0.5 structural-cost regression + workspace boundary (path / glob / shell-redirect / symlink). Negative-space framing — emits BLOCK / WARN / PASS verdicts, never coaches the agent.

1 Python Updated 2mo ago Score 46
MCP Server Maintained

cuttalo/depscope

Package Intelligence for AI agents. 22 tools across 17 ecosystems (npm/pypi/cargo/go/maven/nuget/rubygems/composer/pub/hex/swift/cocoapods/cpan/hackage/cran/conda/homebrew) — check health, vulnerabilities (OSV + CISA KEV + EPSS), typosquats, malicious flags, alternatives, known bugs, breaking changes, stack compatibility and error-to-fix. 31k+ packages, 2.2k+ CVEs enriched. Zero auth, MIT. Remote

1 TypeScript Updated 2mo ago Score 46
MCP Server Maintained

BeBraveBeKind/mcpskills-server

Pre-install trust layer for MCP servers, AI skills, and npm packages. Scores any repo or package across 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence) with safety scanning for prompt injection, credential theft, and supply-chain risk; the `auto_gate` tool returns a go/no-go install decision. Listed in the official MCP Registry as `io.mcpskills/server`. npm: `@mcpskillsio/server`. https

1 JavaScript Updated 1mo ago Score 46
MCP Server Maintained

helbertparanhos/postforme-mcp-pro

Post for Me MCP server with 27 typed tools to publish, schedule, edit, delete and analyze social posts across 9 platforms (Instagram, Facebook, TikTok, YouTube, X, LinkedIn, Pinterest, Bluesky, Threads), plus a postforme_raw escape hatch and a readonly safety mode.

1 TypeScript Updated 1mo ago Score 46
MCP Server Active

sukrutkrdg/x402-bazaar-mcp

The Base token-safety toolkit for agents: the only B20 (Base-native token) freeze/seize/rug suite, plus pre-trade GO/HOLD/STOP gates, honeypot/sellability, wallet + approval audits, sign-guard, prices and Claude-written AI reports. 90+ pay-per-call tools over x402 (USDC on Base), free tier, no API keys. `npx x402-bazaar-mcp`

0 JavaScript Updated 2d ago Score 45
MCP Server Active

mcpindex-ai/mcp-server-mcpindex

Find MCP servers by natural-language task and get advisory trust screens (check_tool_trust, assess_server) before you connect. The directory client for mcpindex.ai; advisory, not a safety verdict.

0 JavaScript Updated 3d ago Score 45
MCP Server Stale

sim-xia/blind-auditor

A zero-cost MCP server that forces AI to self-correct generation messages using prompt injection, independent self-audition and context isolation.

11 Python Updated 7mo ago Score 44
MCP Server Maintained

openpulsechain/mcp-server

PulseChain on-chain analytics: token safety scores (0-100), honeypot detection, whale tracking, smart money feed, scam alerts, DEX volume, bridge stats, holder leagues. 11 free + 9 pro tools. `npx @openpulsechain/mcp-server`

2 TypeScript Updated 2mo ago Score 43
MCP Server Maintained

0xDegenMo/lighter-mcp

MCP server for [Lighter](https://lighter.xyz) — a zero-fee zk-rollup perpetual DEX. Trade ~190 perpetuals (crypto + RWA: PAXG/XAU gold, XAG silver, WTI oil, equity tickers like TSLA/AMZN/ASML) from Claude Desktop, Cursor, Hermes, or any MCP client. Three credential tiers (PUBLIC market data → READ account → TRADE signing), native on-chain stop-loss / take-profit, server-side safety caps (max-quote

2 Python Updated 2mo ago Score 43
MCP Server Stale

AIM-Intelligence/AIM-Guard-MCP

Security-focused MCP server that provides safety guidelines and content analysis for AI agents.

21 TypeScript Updated 9mo ago Score 41
MCP Server Maintained

astafford8488/agentaegis-mcp

Security & trust layer for AI agents. Scan an MCP server or skill *before* you install it (`scan_mcp_plugin`, `scan_skill`) — flags exfiltration, prompt-injection sinks, dangerous capabilities, install hooks and obfuscation → PROCEED/CAUTION/BLOCK. Plus `vet_endpoint` (endpoint safety verdict before an agent calls or pays it) and 25 more tools: vuln scans, threat intel, compliance (SOC 2/ISO 27001

1 TypeScript Updated 1mo ago Score 41
MCP Server Maintained

rev2ret/SecureAudit-MCP

Model Context Protocol (MCP) server for static C/C++ memory-safety scanning and compiled PE/ELF binary protections auditing (ASLR, DEP/NX, SafeSEH, PIE) with secure templates remediation.

1 JavaScript Updated 2mo ago Score 41
MCP Server Maintained

uchit/mcp-regulated-ai-compliance

Regulated-industry AI compliance knowledge as MCP. 6 tools (lookup_control · classify_use_case · crosswalk · walk_playbook · get_anti_pattern · list_regulations), 53 resources, 5 prompts. Covers EU AI Act, APRA CPS 230/234, NIST AI RMF, ISO 42001, AU AI Safety Standard (DISR Aug 2024), OWASP LLM Top 10, SLSA, SSDF, OAIC APPs, GDPR, DORA + 17 more frameworks. 56 controls × 28 regulations × 261 tool

1 TypeScript Updated 1mo ago Score 41
MCP Server Maintained

vessel-api/vesselapi-mcp

Maritime vessel tracking via VesselAPI. Search vessels, get real-time positions, ETAs, port events, emissions, inspections, and NAVTEX safety messages.

1 TypeScript Updated 2mo ago Score 41
MCP Server Active

bluetieroperations-create/blackwall-mcp

Pre-action risk gate for AI agents. One `forecast` tool the agent calls before any irreversible action (send money, run SQL, delete data); returns a risk score (0–100), reversibility class, named red flags from 28 failure modes, and a gate: proceed / confirm / human-required.

0 JavaScript Updated 19d ago Score 40
MCP Server Archived

imran-siddique/agentos-mcp-server

Agent OS MCP server for AI agent governance with policy enforcement, code safety verification, multi-model hallucination detection, and immutable audit trails.

72 Python Updated 5mo ago Score 39
MCP Server Stale

AiAgentKarl/solana-mcp-server

Solana blockchain data for AI agents — wallet balances, token prices, DeFi yields (Raydium + Orca), and token safety checks (RugCheck scores, holder concentration, insider detection).

1 HTML Updated 4mo ago Score 36
MCP Server Stale

AgentBase1/mcp-server

AgentBase: open registry of agent instruction files for AI agents. Search and retrieve system prompts, skills, workflows, domain packs, and safety filters via MCP tools. 44 files, CC0-licensed, free.

1 JavaScript Updated 4mo ago Score 36
MCP Server Stale

Lukaris/framedeck-mcp

[Framedeck](https://framedeck.app) is a Kanban content production manager for YouTube, Instagram, TikTok and Podcast creators. 32 tools for managing productions, stages, frames (cards), checklists, comments, and labels. Ideas land in an Idea Pool and graduate into full productions with stages (Idea → Scripting → Filming → Editing → Published). All tools ship with MCP safety annotations. `npx frame

1 JavaScript Updated 3mo ago Score 36
MCP Server Inactive

hannesrudolph/sqlite-explorer-fastmcp-mcp-server

An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.

107 Python Updated 1y ago Score 35
MCP Server Stale

gridinsoft/mcp-inspector

MCP server for domain and URL security analysis powered by GridinSoft Inspector, enabling AI agents to verify website and link safety.

1 JavaScript Updated 6mo ago Score 31
‹ Prev12