BountyVerdict Agent Decision Tools
Six read-only decision tools for coding agents to assess GitHub bounties, audit agent instructions, diagnose GitHub Actions failures and flakes, and detect MCP…
Directory
Six read-only decision tools for coding agents to assess GitHub bounties, audit agent instructions, diagnose GitHub Actions failures and flakes, and detect MCP…
Turn your favourite AI tool into a feature management assistant. DevCycle's MCP works with your favourite coding assistant so you can create and monitor…
Seamlessly integrate AI assistants with GitLab using the glab CLI tool.
A universal control plane for managing MCP servers and providing intelligent tool discovery for AI agents.
CLI + 46-tool MCP server for the Orion declarative services runtime — build and operate REST/Kafka services, manage workflows, channels, connectors, traces…
MCP security scanner — finds tool poisoning, credential leaks, and insecure transports in AI agent configurations.
Score and optimize MCP tool definitions for AI agent discovery. Analyzes Findability, Clarity, Precision, and Efficiency.
CLI tool that generates MCP servers from OpenAPI/Postman specs — pip install mcpgen-cli
Security, control & observability layer for AI agents: pre-tool policy enforcement (allow/block/require_human_approval) + append-only JSONL audit logs. Wraps…
Add translation keys to Lokalise projects. Requires a Lokalise API key.
Security scanner for MCP servers — detects tool poisoning, prompt injection, and 90+ vulnerability patterns
MCP tool that audits a code diff against the originating prompt and flags out-of-scope changes an AI agent made.
A minimal file bundling and tagging tool for AI development, featuring a web interface and MCP server mode for AI integration.
An MCP server (and command-line tool) to provide a dynamic map of chat-related files from the repository with their function prototypes and related files in…
Check any MCP server's identity, risk grade and tool classifications before installing it.
A TypeScript framework that turns a single class into an MCP server, CLI tool, and web dashboard with a marketplace of 35 ready-made photons.
Cryptographic action receipts for AI agents. Signs every MCP tool call with Ed25519, hash-chained audit log. 3 lines of code to integrate.
Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.
The firewall for MCP tool calls. Block unsafe calls, audit every decision, replay anything. Deterministic policy enforcement with replayable evidence bundles.
A deploy tool for Claude Code, Cursor, and any MCP client: say 'deploy this' and your code comes back as a private URL, open only to the people you invite.
Billing and metering infrastructure for MCP tool servers. 10% platform fee, MIT-licensed billing spec, signed receipts and SLA tracking.
Governed MCP gateway: approval gates, signed audit receipts, and cost control for agent tool calls.
Since AI can write code, it can also maintain structured architecture diagrams for your team. DiagramGuru is the MCP tool that lets AI agents create, update…