Development MCP Servers

Open-source Elementor MCP and WordPress MCP server plugin that lets AI agents build, edit, and automate native Elementor websites with permission-aware workflows.

Post and schedule to X from your coding agent — the X token stays in a server-side vault and every post passes a deterministic server-side guardrail, so the agent never holds the credential.

Remote MCP solve engine: breaks a hard request into checkable sub-questions, grounds each to a real tool, and returns a reusable route.

Prompt manager / prompt library. Store versioned prompts locked to a model with API-only settings (reasoning, verbosity, and other per-model dials). Text and image. Tracks successful usage (copy/download) and your edits so you can refine the next version. Hosted MCP at mcp.getpromethic.com/v1.

The OpenRouter for tools. One MCP connection gives any AI agent 250+ hosted tools, pay per call.

Connect your coding agent to Povento to inspect portfolio and project context, discover app capabilities, and prepare scoped setup plans.

Compliance frameworks delivered to AI agents. Nizh gives your agent read access to your organization's compliance program — SOC 2, ISO 27001, CMMC 2.0, NIST, and more — as MCP tools, so it can check posture, read a control's objectives before changing code, and record where evidence lives.

Lets an AI agent search an open-source registry of animated React components, UI blocks and design systems and return their shadcn CLI install commands.

22 composable, auto-triggering skills that turn your coding agent into a principal engineer - from raw idea to production-ready documentation.

Publish a prepared task from your coding agent so a teammate can claim it and run it on their own AI subscription.

Monitor cron jobs and recurring work through a project-scoped Watchgoose connection

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for language tasks.

One key for 63,577 agent tools: scrapers, search, data, AI models. Pay per call, failed runs free. MCP + REST.

A Model Context Protocol server for the EuroDNS User API — domains, DNS zones, contacts, subscriptions, SSL, invoices and orders.

Memwyre is an MCP-native persistent memory layer for AI agents, synchronizing context and project decisions across Claude Code, Cursor, VS Code, and OpenClaw. Key Highlights: - 73% LoCoMo Accuracy: Achieves 73.1% retrieval accuracy on the Long-Context Memory benchmark, outperforming traditional RAG. - Retrieval-Quality Architecture: Employs hybrid vector search, BM25 keyword matching, and cross-encoder reranking to eliminate context bloat. - Persistent Isolated Vaults: Multi-tenant memory storage with strict workspace-level isolation. - Core Tools: Provides search_memwyre, save_memory, and list_memories to save and recall structured facts across any session.

Lets an agent read and re-run its own past sessions. Records a coding-agent run below the harness, then replays it offline or forks it from a checkpoint onto another model.

Turn any task into the right API calls. Describe your task, and Orbit finds public API endpoints that fit, then generates instructions to call them, from auth to gotchas, so agents can discover, evaluate, and integrate public APIs.

Local one-shot YAML/JSON agent workflow CLI with tools, approvals, and resume, plus an optional stdio MCP server. Apache-2.0, BYOK.

Discovers and parses any site's llms.txt (most-specific covering index), returns linked docs as markdown via Accept: text/markdown, .md mirrors or conversion, and searches sections. Remote, keyless: https://llms-txt.dsh.sh/mcp

A Model Context Protocol (MCP) server that provides comprehensive access to SendGrid's API v3 for email marketing, transactional email operations, dynamic template management, and detailed analytics. Features 58 tools covering all aspects of email management and performance analysis.

Signadot's MCP server lets AI agents create and manage lightweight Kubernetes sandboxes, isolated test environments that route traffic to forked or locally running services. Agents can spin up sandboxes, combine them into route groups, and validate microservice changes against real cluster dependencies before merge.

Walks a running web app in a real browser and reports 12 classes of bugs with reproduction steps, a screenshot, and a severity. npm: sniff-qa.

AI-powered dev tool for building web and mobile apps out of micro-apps combining no-code and code interfaces.

Federated registry of 91k+ agent skills and MCP servers with one-command signed installs, plus a fleet control plane that keeps skill bundles identical across Claude Code, Codex, Hermes and OpenCode. 47 MCP tools. MPL-2.0, free tier, self-hostable.

Nine read-only tools over per-function CRAP scores (complexity times uncovered risk), churn-ranked, for Python and JavaScript repos.

Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.

Laravel Telescope-style debugging for Hono apps whose dashboard endpoint is also an MCP server, so an agent can read live requests, exceptions and queries.

Domain Name MCP that allows to search, register, renew, transfer, and manage domains, DNS, VPS, email, and websites

Remote control agents on any one of 10+ agentic platforms.

Lets agents list, search, read and type into the terminals you already have running, on every machine you own.