Code

Four-tool MCP adapter for Urdira.

Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots

Mandu MCP Server - Agent-native interface for Mandu framework operations

o2n（Obsidian→Notion移行ツール）のローカルMCPサーバー

One system around coding agents to run, verify, recover, and hand off software work.

Angi MCP server for Claude — developed and maintained by AI (Claude Code)

Local-first context engine for AI coding agents. Pre-indexes your codebase into a dependency graph and feeds any MCP agent only the code that matters — 87% fewer tokens per call. New in 2.5: mechanical work verification and a PII/secret scanner. Works wit

Attach agent-oriented documentation to any class, object, or function

Model Context Protocol server for Testomatio API

Standalone MCP server for SmarTTest that forwards tool calls to the SmarTTest backend.

Persistent memory for agents. Corrections stick, context compounds, every session starts smarter.

CRAP metric CLI for TypeScript: combines cyclomatic complexity and test coverage to find risky code, with a bundled cross-agent AI skill.

Search and audit CVEs by keyword, severity, CWE, CISA KEV status, and CPE via the NIST National Vulnerability Database. STDIO or Streamable HTTP.

Evidence-backed codebase memory for MCP-capable coding agents. Ships a portable workflow skill, an MCP server, client adapters, and a diff-aware materializer.

Bst-Table MCP server — gives AI coding agents accurate, version-pinned knowledge of @bloomskill/table-* : docs search, the feature-toggle registry, cell types, config validation and grid scaffolding.

Lightweight pure-CLI client for Model Context Protocol (MCP) servers: interactive REPL shell, tool discovery & invocation, connection profiles.

An MCP server fronting `opencode serve`, letting Claude Code collaborate with other LLMs (consult, panel, research, review, delegate). Ships slash commands + hardened opencode agents; `npx modelguild init` wires it into a project. The bash layer in modelg

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

TestingBot's official MCP Server for AI-powered testing automation

MCP server for SandboxAPIs — read-only, API-compatible replicas of GitHub, GitLab, Bitbucket, Azure DevOps, Jira, Linear, Slack, Microsoft Teams, Sentry, PagerDuty, CircleCI, Buildkite, Zendesk, Salesforce, HubSpot, Anthropic, OpenAI, ChatGPT, Cursor and