Search
mrfentmen
Hash and HMAC text locally with MD5, SHA-1, SHA-256, SHA-384 and SHA-512, in hex and base64 - no network.
Mustapha Hamdi
Intent control plane for LLM agents: the agent proposes, a deterministic gateway resolves every critical argument against trusted sources and decides (Cedar). Includes an MCP proxy.
...morehoneylabshq
https://github.com/honeylabshq/honeylabs-mcp
AlanNiew <[email protected]>
变更驱动的代码审查证据引擎:MCP 服务器 + 审查协议 Skill,为 AI 编码助手提供高信号的变更审查能力
beeswaxpat
MCP server for ChronoVerify: verify a photo's capture time and provenance from any MCP-compatible AI agent.
krishhgg
Your AI agent needs your API keys. It doesn't need to see them. tokenstash writes keys straight into .env.local for Claude Code, Codex, Cursor and Gemini CLI. Paste each key once, in your browser, never in the chat.
...morejdugueto
IP allowlist guard for MCP servers. Ships with OpenAI/ChatGPT egress IP ranges and supports custom CIDR ranges. Zero dependencies.
...moreMatt Wagstaff
MCP server for Australian PII detection and sanitisation — TFN, Medicare, ABN, ACN, BSB, bank account, drivers licence, passport, Centrelink CRN, and address recognisers with checksum validation, compliance audit logging, built on Presidio
...moremayhemx87
Static scanner for malicious MCP config files in AI-integrated editor repos
Tarek Mohamed <[email protected]>
A Lightweight Defense Architecture Against Indirect Prompt Injection in Tool-Calling AI Agents and MCP Workflows
mrfentmen
Bitwarden public API: organization members, collections, groups, event logs. Needs API key.
wallettriage-mcp
WalletTriage MCP server — real-time wallet risk check for AI agents, paid per query via x402 (USDC on Base).
https://github.com/jstibal/openterms-mcp
Custodian Guard for OpenAI Codex — typed action risk classification, fail-closed enforcement, and hash-chained receipts for Codex tool calls.
...moreAgentTrust Contributors <[email protected]>
Hardware-attested MCP runtime — TEE-enforced policy and TRACE Claim generation
tinemaher
MCP proxy router that intercepts downstream tool calls, runs Blekline enforcement (mask/block), then forwards approved calls to a downstream MCP server (Daytona, Modal, E2B, Cloudflare, Vercel Sandbox, or mock).
...moreUday Rathore
Static claim-versus-capability analysis for Python MCP servers
satsvloex
Vloex MCP Gateway — stdio proxy for MCP tool call governance
rookbot-io
A firewall for AI agents — intercept, inspect, and control MCP tool calls