All MCP Servers — Page 172

An MCP server that lets AI clients discover and query the OmniStream marketplace, browse APIs, and inspect available operations through a structured tool interface.

Live status, incidents, and uptime history for 172 cloud and SaaS vendors via a keyless hosted MCP server.

Agent-first private page hosting: your AI publishes real HTML pages to your own address, and checkboxes and inputs keep their state across devices and conversations.

Calculate historical crypto investment returns via MCP. Automatically handles $0.02 USDC payment per query on Base mainnet using x402.

Public EPK property listings and multilingual real-estate guides for AI agents.

Search 18,800+ verified restaurants and bars across 20 cities, each with a 0-100 Quality Score.

VaultMCP is an encrypted secret vault and MCP gateway. You store provider credentials once. Your AI IDE connects to one endpoint. VaultMCP decrypts secrets only when calling upstream MCP servers — your agents and config files never see the raw keys.

Generate 3D models and images from a text prompt or reference images, then remesh, retexture, auto-rig, animate, and export GLB/FBX/OBJ.

Structured rows from public sources: SEC filings, clinical trials, papers, npm packages, job listings.

Inspect, validate and preview VRM / VRMA avatar and animation files locally. 5 tools, stdio, no network access at runtime.

Draft, schedule and publish social posts to 8 platforms from any AI agent. Official APIs only, no scraping.

An MCP server providing science-based psychometric tools and sexual well-being assessments for AI agents.

Shared drive for your agents and teammates.

SEO autopilot: analyze any domain for winnable queries, 45+ free SEO tools, generate & publish SEO articles. Hosted MCP at https://www.tryspook.com/api/mcp

Agent-native global eSIM over MCP: an agent buys and manages one eSIM for 193 countries anonymously, billed per megabyte in USDT/USDC — and earns 20% referral on every payment it refers, forever.

A comprehensive Model Context Protocol (MCP) server implementation for the ESP32 CYD (Cheap Yellow Display) board. This project provides extensive remote control capabilities for the ESP32-2432S028R board through a WebSocket-based MCP interface.

Control Unity Editor from MCP clients or from chat inside Unity — 70+ tools for scenes, GameObjects, components, assets, Shader Graph, PlayTest DSL, screenshots with visual diff, batch operations, and token-efficient protocol. 11,700+ tests, cross-platform CI, Setup Wizard for 10 clients.

Technical SEO audits in Claude: Search Console history, a first-party crawl and DataForSEO merged into one prioritised audit with paste-ready fixes.

Delegate bounded work from Claude to any OpenAI-compatible LLM endpoint (LM Studio, Ollama, OpenRouter), preserving your Claude context and quota.

Generate configurable Gridfinity baseplates from natural-language instructions and receive a ready-to-open 3D model link.

Local-first, zero-knowledge semantic memory for AI agents with on-device vector search (LanceDB + ONNX) and client-side AES-256-GCM encrypted sync.

Academic conference and journal data: CFP submission deadlines, CCF/CORE/QUALIS rankings, acceptance-rate history and journal impact factors — remote server, nothing to install, no credentials needed for search.

Local-first AI memory engine for coding agents with Ebbinghaus decay, bi-temporal facts, and hybrid retrieval.

Production-ready Model Context Protocol server for ServiceNow platform integration - ITOM, ITSM, CMDB with OAuth, natural language queries, and enterprise security controls

Run edge-AI regression gates on real Snapdragon and Jetson hardware, with signed evidence for CI.

AI-agent-native Kanban board. Claude Code, Cursor, and any MCP client manage tasks as native tools — with human review gates and real-time updates.

Official Azure DevOps MCP Server. Read and manage work items, repositories, pull requests, wiki, builds, releases, and project resources.

Build prospecting lists from buying signals, enrich them, and run LinkedIn outreach.

Generating content is the easy part. Publishing to your socials is the manual part. Now there is an MCP which acts as the publishing layer directly to socials. No more manual exporting of files. No more pain.

Knowledge your AI agent can actually afford to read. Every time your agent looks something up, it pays for about 15,000 tokens of markup to recover roughly 500 tokens of fact. You are billed for all of it — the navigation, the citation scaffolding, the edit links — and then your model throws it away. Wikexa did that reading already. You get the facts.