Search

AI Agent 集中式凭证管理与授权代理 CLI 工具

MCP server for Box admin-log analytics — external-sharing visibility, read-only

MCP server for Worthless split-key API proxy — wraps `uvx worthless mcp`

MCP server that verifies an npm package name is real before a coding agent installs it — catching hallucinated ('slopsquat') package names and typosquats of popular packages, with age/downloads trust signals.

@ai-sdk/anthropic with all dependencies updated to latest

Patched Bash and Zsh binaries for Codex shell execution.

SSH & Kubernetes access broker for AI agents; the model never touches a credential.

MCP proxy that wraps any MCP tool with AgentMesh trust verification

Mantivor — runtime monitoring collector for MCP servers

Pre-flight MCP tool-contract drift interceptor — one-line wrap() over an MCP client session that HOLDs a tool call before your agent runs it when the contract drifted from your pin. No credential handling.

AgentValet MCP server — lets AI agents call approved platforms via the AgentValet proxy

MCP server for the HackerOne Hacker API (Hackers section only). Built from https://api.hackerone.com/hacker-resources/

Installed software, vulnerabilities and end-of-life components across your servers, apps and repos

The best way to build MCP servers in Python. Turn any function into an AI-callable tool.

A provenance control plane for tool-using agents — contain the blast radius of a prompt injection at the MCP layer.

CSOAI DEFONEOS ISR (Intelligence, Surveillance, Reconnaissance) — sovereign UK defence ISR pipeline: object detection + geolocation + BFT-signed ISR + Cesium GeoJSON feed

SEO audit of any URL: meta tags, headings, links, images, schema, score 0-100. x402 payments.

Audits any live MCP server URL or GitHub repo on Glama's 6-dimension TDQS rubric and compiles dro.

Model Context Protocol implementation for TypeScript

Open-source, self-hosted Zero Trust policy enforcement layer for MCP servers.