MCP server directory

ContextStream MCPThe production connection for your assistantPlatformCode, memory, media, and project operations ContextCode BetaOptional terminal coding agent in beta Connect your assistant Manual setup Custom MCP Connector Hosted or local Instruction files Keeping it current Troubleshooting Command reference ContextStream's production product is the MCP connection used from the assistant you already have. It is implemented by the Rust MCP server and connects Claude Code, Cursor, Codex, VS Code, and other supported clients to ContextStream's search, memory, and durable project context.

6 tools · Generate operational runbooks, Hand off work to another agent

`@deliveriq/mcp` — email-deliverability tools for AI agents. 12 tools: single + batch verification, email finder, DNSBL across 50 zones, SPF/DKIM/DMARC/MTA-STS/BIMI infrastructure analysis, spam-trap scoring on 13 weighted signals, composite domain trust report, account credits. 5-stage / 21-check pipeline under the hood. Free tier, no card. Install: `npx -y @deliveriq/mcp`.

AllRatesToday currency exchange rates: real-time mid-market rates for 160+ currencies (Reuters/Refinitiv), historical data (1d/7d/30d/1y), currency list, and multi-target lookups. Free tier, no key needed for the simple-rate endpoint. Install: `npx @allratestoday/mcp-server`.

An MCP Selenium Server for controlling browsers using natural language in Cursor IDE. Perfect for testing, automation, and multi-user scenarios.

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

Yandex Merchants (Яндекс Товары) API — product feeds, offer prices, discounts, and hiding/unhiding offers in Yandex Search.

The Elementary MCP Server allows you to connect your Elementary environment to any client that supports MCP (Model Context Protocol). This lets AI agents, copilots, or natural language interfaces query and act on your data stack using live context. MCP (Model Context Protocol) is an open protocol introduced by Anthropic. It defines a way for AI systems to retrieve context and trigger actions from external tools in a structured way. The Elementary MCP Server exposes an interface to query key parts of your data environment — including:

6 tools · get_execution_history, get_incidents

A sub-harness (both an MCP server and an MCP client). Delegates documentation and source code analysis, as well as interactions with related context-providing MCP servers, to a local or inexpensive OpenAI-compatible LLM. Drastically reduces token usage and context size for coding agents on the top-tier LLM. `uvx codebase-agent-mcp`

17 MCP tools for the food industry. Describe food in plain English and get structured, content-addressed data blocks back. Covers actors, places, ingredients, products, transforms, transfers, and observations. Works standalone with zero config via `npx foodblock-mcp`.

🎖️ 📇 ☁️ 🏠 – Web scraping for AI agents: one auto tool walks a cost-aware ladder (direct → rotating proxy → full browser), solving anti-bot challenges and reporting which rung delivered and what it cost. Pay-per-success, EU-hosted, free tier.

Chinese metaphysics (bazi 八字, qimen 奇門, 5-element, daily 干支) as decision-support tools. Ask "when should I do X" and get specific time windows instead of vague advice. 5 tools: daily reading, compat, best-time-for-action, today's energy, name analysis. `npm install -g @asktian/mcp-server`

🏎️ 🏠 – A high-performance multi-database MCP server built with Golang, supporting MySQL & PostgreSQL (NoSQL coming soon). Includes built-in tools for query execution, transaction management, schema exploration, query building, and performance analysis, with seamless Cursor integration for enhanced database workflows.

Unified agent work logging and observability across ChatGPT, Claude, Cursor, Codex, and OpenClaw with config-first schemas and pluggable sinks.

AI-powered task management system for AI-driven development. Features PRD parsing, task expansion, multi-provider support (Claude, OpenAI, Gemini, Perplexity, xAI), and selective tool loading for optimized context usage.

MCP server for Kubernetes cluster operations — inspect pods, deployments, services, and logs via AI agents.

Adversarial test generation for AI coding sessions. Detects language and framework; writes tests; runs them; classifies failures via R12 (real_bug / environment / test_bug). Ships 8 adversarial scenario categories. Works in Cline directly and in 8+ editors via Cline host coverage. 162 plugin tests. MIT.

Model Context Protocol Server for looking up company ethics information. Learn about the ethical and unethical actions of major companies.

Local-first meeting pipeline: Whisper transcription + Ollama-powered summaries, action items, and decisions — no cloud. Reference implementation of the [memnex](https://github.com/UladzKha/memnex) spec (portable meeting-output format with provenance chain). MCP server exposes `process_recording`, `transcribe_audio`, `summarize_transcript`, `extract_action_items`, `extract_decisions`. Install: `npm i -g @samuraizer/mcp-server`.

MCP server and plugin that lets AI agents (Claude Code, Cursor, Codex, Gemini) directly control a live Roblox Studio session — create scripts, instances, terrain, lighting, and assets via natural language. 21 tools, 140+ actions, bidirectional sync, and automated playtest.

TiDB database integration with schema inspection and query capabilities

Connect your AI tools to Streamient with the Model Context Protocol (MCP) — an open standard that lets AI assistants work directly with your notes, memories, saved URLs, emails, projects, and knowledge graph. Instead of copying context between tools, your assistant reads and writes the same shared memory layer your team already trusts — across sessions, projects, and clients. MCP is an open standard, developed by Anthropic, that creates a universal bridge between AI assistants and external tools. With the Streamient MCP server, your assistant can search and update your knowledge base directly — securely, and with your permission — without you leaving the chat.

6 tools · Bookmark and read URLs, Create and update notes

AI virtual staging for real estate. Stage empty rooms, beautify floor plans into 3D renders, classify room images, generate property descriptions, and get style recommendations.

MCP (Model Context Protocol) is an open standard that lets AI assistants discover and use external tools. The TemplateFox MCP server gives your AI assistant 8 tools to generate PDFs, manage templates, and check credits — all from natural language. 1. Node.js 18+ installed on your machine (for npx) 2. A TemplateFox API key — get one from your Dashboard (starts with sk_) Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

5 tools · generate_pdf, generate_pdf_async

Native stdio bridge for the hosted Delx Protocol MCP endpoint, with one-command client install, doctor checks and live tool discovery.

Solana token safety oracle for AI agents and trading bots. Byte-level SPL mint analysis, honeypot detection, freeze/mint authority checks, Birdeye market enrichment, and composite risk scoring. Deployed on Google Cloud Run.

An MCP server running inside a trusted execution environment (TEE) via Gramine, showcasing remote attestation using [RA-TLS](https://gramine.readthedocs.io/en/stable/attestation.html). This allows an MCP client to verify the server before conencting.

Helping Your AI Agent Identify Hotspots for Refactoring; Help AI Understand How to 'Make Code Better'

Record development decisions as structured JSON, embed as vectors via Gemini, and search semantically over MCP. Shared store across Claude Code, Cursor, Windsurf, and any MCP client. CLI + MCP server, local-only, free Gemini embedding tier.

Condition-aware ingredient, product & supplement safety for agents, with provenance on every answer — a verdict, an evidence tier (Gold/Silver/Bronze), and a verifiable citation — across breastfeeding, pregnancy, histamine/MCAS, rosacea, HS, allergy and fertility lenses. 9 tools incl. validate_claim (fact-check a claim against curated cited sources) and check_recall (FDA/consumer recall lookup by brand with Class I flagging and source URLs). Hosted at mcp.healthai.com.

Coherence guard for shared files: when two agents write the same file, the stale writer is denied instead of silently overwriting, then reacquires and retries. Single-host, TLA+-verified. Install: `uvx --from "agent-coherence[mcp]" stale-write-guard-fs`.

iOS leak hunting and performance investigation. Reads `.memgraph` (`leaks(1)`) and `.trace` (`xctrace`) files, classifies retain cycles against a 34-pattern catalog (SwiftUI, Combine, Swift Concurrency, UIKit, Core Animation, Core Data, SwiftData, RxSwift, Realm), surfaces a Swift `fixTemplate` snippet for each match, and bridges to source via SourceKit-LSP. Single-call build+boot+launch fixes the macOS 26.x `leaks --outputGraph` regression; `replayScenario` + `captureScenarioState` close the verify-fix loop. 31 MCP tools, 34 catalog resources, 5 investigation prompts. CI-gateable via `verifyFix` and `compareTracesByPattern`. Apache 2.0.

The Compeller MCP endpoint implements the Model Context Protocol as a thin JSON-RPC 2.0 wrapper over the existing v1 REST API. It is intended for agent integrators (Claude Desktop, Cursor, custom MCP clients, DigiRAMP) that speak MCP natively rather than raw HTTP. - Transport: Streamable HTTP (single JSON-RPC message per HTTP POST). - URL: POST https://compeller.ai/api/mcp - Protocol version: 2024-11-05 - Server name / version: compeller-mcp / see initialize result. - Tool contract: The tool list below is the public integration contract. Use tools/list for the runtime-advertised set on the deployed server. - Directory listings: Official MCP Registry · Smithery · Glama

6 tools · get_account_credits, get_compel

MCP server for DigiSign.cz digital signature API — create, send, and manage digital signature envelopes.

Deep research MCP server for OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.

A MCP server for MobSF which can be used for static and dynamic analysis of Android and iOS application.

Real Amazon (US, UK, DE, CA, AU) and Walmart shopping data for AI assistants — ranked product shortlists, current prices, live stock, real ratings, and 30-day price/BSR history from a 17M+ product warehouse. Free hosted endpoint, no signup (30 queries/day). Remote streamable-http at api.logimu.com/mcp.