MCP server directory

> For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs; this page is available as Markdown. Proxyman MCP (Model Context Protocol) is a feature that enables AI assistants (Claude, Cursor, and other MCP-compatible tools) to directly interact with the Proxyman macOS app. It allows AI to inspect HTTP traffic, create debugging rules, and control Proxyman - all through natural language conversations. The architecture consists of two components:

6 tools · create_breakpoint, enable_ssl_proxying

> Build AI agents that interact with your data securely. Connect databases, create governed views, and deploy MCP tools to any agent builder. Pylar is a secure data access layer for AI agents that enables interaction with structured data sources without requiring direct database access or complex API integrations. 1. Data Sources connect to Pylar (Snowflake, BigQuery, PostgreSQL, HubSpot, Salesforce, and more) 2. SQL View is created to govern exactly what data agents can access 3. MCP Tools are built on the view—multiple tools for different use cases 4. Tools publish to Agent Builders (Claude Desktop, Cursor, LangGraph, Zapier, Make, n8n, and more) 5. Evals monitors all tool interactions for observability and optimization

5 tools · Create governed SQL views, Generate MCP tools from natural language

Official Next.js MCP server for coding agents. Provides runtime diagnostics, route inspection, dev server logs, docs search, and upgrade guides. Requires Next.js 16+ dev server for full runtime features.

4 tools · browser_eval, nextjs_call

Reports what your test suite is structurally unable to see and proves each gap with a real failing test, across six languages.

Returns recent posts from LinkedIn profiles and company pages with real engagement counts, plus the commenters LinkedIn shows publicly. No cookies and no account.

How to Install the Query Streams Agent on Windows How to Install the Query Streams Agent on Linux How to Install the Query Streams Agent on macOS Query Streams Access Level Permissions: Complete User Role Management Guide How to Install the Query Streams Google Sheets Addon Nova Concierge Mode: A Personal Data Analyst for Every User Nova Taught Knowledge: How Verified Learning Works How Nova AI Learns Your Database Schema Automatically AI Data Analytics: Query Any Database Without a BI Tool BI and Data Analytics Without Tableau or Power BI Text to SQL: How Nova AI Turns Questions Into Database Queries AI Powered Analytics: Ask Questions, Get SQL + Charts Natural Language to SQL: How Nova AI Turns Questions Into Database Queries

5 tools · Automate data syncs, Connect SaaS APIs to spreadsheets

Turns a web page into decision-ready state for agents: dates as ISO fields, numbers with units as facts, token-budgeted chunks with anchors back to the page, and the token bill (median 53,718 → 1,106). Deterministic, no model or API key; pairs with decision models such as Jev. `npx -y codearia-sieve`.

The Railway MCP Server implements the <a href="https://modelcontextprotocol.org" target="_blank">Model Context Protocol (MCP)</a>. It lets AI assistants create projects, deploy templates, manage environments, pull variables, and redeploy services. The server runs at mcp.railway.com. Connect to it in one of two ways: Through the CLI (default). The railway mcp command connects your editor to mcp.railway.com through the Railway CLI, reusing your railway login credentials so no second authentication is required. With OAuth. Editors that support OAuth connect directly to https://mcp.railway.com without the CLI.

6 tools · Control feature flags, deploy_template

Ethically sourced residential IPs that help you bypass CAPTCHAs, avoid IP blocks, and reduce operational costs. - 90M+ premium IPs - 99.9% Uptime - < 0.58s Response - 200 countries - 24/7 support Chosen by industry leaders around the world Rapidproxy provides stable, high-quality rotating and static residential proxies. With 90M+ real-user IPs in 200+ regions, we enable secure, fast, and geo-targeted access for data collection, automation, and global web operations. - 90M+ Residential IPs - Free Proxy Trials - 200+ Global Locations - Never-Expiring traffic - City-Level Geo-Targeting - Unlimited concurrent sessions - HTTP(S) & SOCKS5 Support - 99.9% success rate Start Now

5 tools · Multi-language code samples, Proxy authentication setup

Revise has a built-in AI Agent, but it also exposes an MCP server for external agents. This means any agent with MCP support can use Revise to write, edit, read, and share documents - collaboratively in our web-based editor or just by itself. All documents in Revise are DOCX-compatible, and sync in real-time with tracked changes. Revise MCP is free with no subscription tiers or per-tier caps - just generous rate limits. Create a free account and bring your own inference. Claude Desktop interacting with a Revise document

6 tools · create_document, edit_document

Bike, e-bike, kick scooter, motorcycle, wheelchair and walking routes across Europe from the On va où ? Routing API: up to three variants (safe, balanced, fast) with cycle lane, unpaved and main road shares, climb and turn-by-turn steps. Free API key. Install: `npx -y onvaou-itineraires-mcp`.

Update: In Safari 27 beta and Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging workflow faster and more powerful. We know agents are increasingly integral to the coding process and the Safari MCP server gives your agent the ability to know how your code actually renders in the browser by connecting it to a Safari browser window. Any MCP-compatible client can connect to the Safari MCP server. By connecting your agent to a Safari browser window, your agent can emulate what your users experience, giving it the information it needs to debug more autonomously, like access to the DOM, network requests, screenshots, and console output.

6 tools · browser_console_messages, create_tab

Screenies has a remote MCP server. Connect it to Claude Code, Claude.ai, Cursor, or any agent that speaks MCP, and the whole workflow runs from a prompt: upload your app screenshots, generate a polished set, localize it, and download files sized for App Store Connect. Create an account → Included with every account. Generation uses your normal credits. Then run /mcp in a session, pick screenies, and sign in. In Claude.ai, Cursor, and other MCP clients, add this URL as a remote MCP server (claude.ai: Settings, then Connectors, then Add custom connector):

6 tools · create_app, generate_screenshot_set

The Model Context Protocol (MCP) is an open standard that allows AI models to interact with external tools and data sources. The Scrapfly MCP Server transforms your AI from being limited by training data to having real-time access to any website-giving your AI the power to scrape live web data on demand. Instead of your AI answering "I don't have current information," it can now: Pull current prices, listings, news, or any webpage content in real-time Automatically handle CAPTCHAs, proxies, JavaScript rendering, and rate limits

5 tools · Bypass anti-bot protections, Capture page screenshots

Try Scite MCP for free. Create an account to get started. After starting the app, ChatGPT will prompt you to sign in with your Scite account. To use Scite in your prompts, type @Scite to activate the connector. For best performance, refresh or reconnect the Scite connector before each session by clicking the ··· menu next to Scite and selecting "Reconnect". For example: "@Scite find papers on CRISPR gene editing". If Scite is not responding, try reconnecting the connector. ChatGPT may silently disconnect tools between sessions. Click the ··· menu next to Scite in your conversation and select "Reconnect" to restore the connection.

4 tools · Activate via connector, Reconnect the connector

SigParser now connects directly to AI tools like Microsoft Copilot, Claude, ChatGPT, Harvey AI, Athena, and other MCP-compatible assistants through a Model Context Protocol (MCP) server. This means you can access your contact database, company records, and relationship intelligence without ever leaving your AI workspace. This feature requires an active SigParser subscription. Model Context Protocol (MCP) is an open standard that allows AI assistants to securely connect to external data sources and tools. By connecting SigParser’s MCP server to a compatible AI tool, your assistant can access and query your SigParser data —contacts, companies, relationships, and more—in real time, as part of a natural conversation.

6 tools · Contact and company lookups, Data enrichment

Trusted across education, enterprise, and government Right now, your employees are using AI tools on personal accounts. They're uploading sensitive documents to ChatGPT, Claude, Gemini — whatever's newest, whatever's best. You can't blame them. They want to work faster. They want the best tools available. But you have no visibility. No governance. No control. The answer isn't to lock AI down. It's to give them a better place to use it. You tried to get ahead of this. You ran a pilot. It didn't stick. You're not alone — most enterprise AI pilots fail to scale. Here's what went wrong:

5 tools · Connect enterprise data sources, Delegate multi-step tasks

The Scrptly MCP (Model Connector Protocol) Server allows you to connect Scrptly with your preferred Large Language Model (LLM) via the MCP interface. This enables you to leverage custom LLMs for generating professional videos through Scrptly's AI Agent. You can connect Scrptly's MCP Server to your LLM of choice through this configuration: - Endpoint URL: https://mcp.scrptly.com/ - Authentication: Use your Scrptly API key for authentication. The authentication method used is Bearer Token in the Authorization header.

3 tools · Check task status, Generate AI video

Connect MCP-compatible AI clients to SikkerKey through a dedicated, scoped, audited, and plaintext-blind AI-agent identity. The SikkerKey MCP server connects MCP-compatible AI clients to the SikkerKey management plane. It lets an AI assistant help administer projects, secret metadata, policies, machines, alerts, audit activity, and other vault operations through a dedicated AI-agent identity. The MCP server is read-blind for stored secret values. It can create or replace values that you deliberately provide, but no tool can retrieve the plaintext of an existing stored secret.

6 tools · manage_machines, manage_policies

Connect SiteGuru to your AI assistant with the SiteGuru MCP server. See what it does, what you need, then pick your tool: Claude or ChatGPT. The SiteGuru MCP server connects your SiteGuru data straight to your AI assistant. Instead of opening reports, you can ask "What should I fix first on my site?" and your AI pulls the answer from your live SiteGuru data and explains it in plain English. SiteGuru is an approved connector in Claude and an approved plugin in ChatGPT, so in both you can add it in a few clicks. This page covers what it does and what you need, then points you to the exact setup steps for your tool.

6 tools · Backlink overview, Indexation and sitemap checks

Enable real-time access to CRM, ERP, databases, and more via a secure, no-code MCP Server—designed for AI chatbots and LLMs Skyvia MCP Endpoint is a no-code gateway that makes your business data accessible to AI assistants in real time. Built on the open Model Context Protocol (MCP), it enables tools like Claude to understand and query data from your data source—with no APIs or schemas to manage. No dev work. No setup overhead. Just connect and chat. Skyvia MCP Endpoint connects AI assistants directly to your data—in real time and securely. It helps analyze, summarize, and act on data instantly.

4 tools · Connect live business data, Generate on-demand reports

Slingshot Aerospace · Official Slingshot hosted MCP (Slingshot MCP) Official Slingshot Slingshot Portal MCP server for space, satellite, and space data. Model Context Protocol integration for space domain awareness, satellite tracking, TLE, ephemeris, and anomaly detection via AI agents in Cursor and ChatGPT. Connect with a Portal org API key and active subscription to https://api.portal.slingshot.space/mcp. Illustrative SGSN and Seradata tools and Marketplace and Analytics categories below — full tool inventory: Developer Suite · Help Center.

5 tools · get_latest_tle, get_rocket_body

The Slop or Not MCP server lets Claude, Codex, Hermes Agent, OpenClaw, Cursor, and other agents call a local AI text detector, AI image detector, readability analyzer, and cleanup tool on your Mac. Point your MCP client at the bundled slop mcp command. With Pro, Claude, Codex, Hermes Agent, OpenClaw, Cursor, and other agents can keep running local checks without per-call API metering. Client setup snippets point at the bundled Mac app binary. Your MCP client starts the bundled slop binary and talks to it over stdio.

6 tools · analyze_readability, clean_text

Live USPS, UPS, FedEx and DHL parcel rates from the US (domestic, Canada, UK, Germany, Australia) from a plain-words item description, plus checkout links, checkout status and tracking. No API key.

Structured knowledge of what does NOT work. 2,400+ entries across 54 domains record the dead ends for an error - the fix that looks right and fails, and why - alongside workarounds with success rates and an error transition graph. Covers code errors and country-specific real-world rules (visa, banking, legal, emergency) where generic answers are most often wrong. `pip install deadends-dev`, or hosted at `https://deadends.dev/mcp`

The Stack Overflow Model Context Protocol (MCP) enables AI tools and agents to access trusted developer knowledge from Stack Overflow. It standardizes how knowledge is exposed, discovered, and retrieved for use in agent workflows and developer environments. Access to the Stack Overflow MCP server is limited to 100 calls per day per Stack Exchange user. If you have use cases that exceed this amount, please contact our sales department. To connect to the Stack Overflow MCP Server, you will configure your client to use the remote server. This allows you to continue your tasks across devices with a single login after authentication, without needing to install and run the server locally. Use your preferred MCP client for this procedure.

3 tools · Get contextual coding help, Ground AI responses

Steady’s MCP server lets AI assistants like Claude and ChatGPT interact directly with your Steady data — completing check-ins, pulling team digests, and surfacing insights — without leaving the tool you’re already working in. MCP (Model Context Protocol) is an open standard that connects AI assistants to the tools and data they need. With Steady’s MCP server, your assistant can read and write Steady data alongside every other service you’ve connected. The MCP server covers all the core data and workflows in Steady:

4 tools · absences, Combine with other tools

Stimulsoft Documentation MCP Server connects AI assistants directly to the official Stimulsoft Reports & Dashboards developer documentation. Once configured, AI assistants in Agent mode can search documentation, find code examples, and generate Stimulsoft-specific code using up-to-date information instead of relying on potentially outdated training data. Endpoint: https://devs.stimulsoft.com/mcp-docs Protocol: MCP 2025-03-26, Streamable HTTP Authentication: None required Important Always review AI-generated output: check for architectural problems, security vulnerabilities, and adherence to project standards. AI-generated output can vary greatly based on the prompt, AI model used, and project code clarity.

3 tools · Generate platform-specific code, sti_get_platforms

> These are the tools exposed by the StackQL MCP server. Availability of mutation and lifecycle tools depends on the server mode (read_only, safe, delete_safe, full_access). Providers pulled into the local StackQL cache Resources available under a provider.service

4 tools · describe_method, describe_resource

Connect your Subscribr account to Claude, ChatGPT, OpenClaw, Cursor, VS Code, and other AI assistants using MCP. Access your Projects board, Tasks, notifications, channels, scripts, ideas, templates, Voice Profiles, and Intel research directly from the conversation. Subscribr supports the Model Context Protocol (MCP), which lets AI clients securely connect to external tools and data. - Read data from your Subscribr workspace - Look up YouTube channels and videos from Intel - Open rich MCP Apps for Intel results, script previews, and the interactive Projects board - Create, update, move, promote, comment on, archive, and restore Projects when your role allows it - Manage custom templates and validate a strict Voice Profile before explicitly committing it

5 tools · generate_ideas, list_projects

You can connect your Superlist account directly to AI assistants that support MCP, so they can read and update your lists and tasks for you. This article explains what the Superlist MCP is, what you can do with it, and how to set it up. MCP stands for Model Context Protocol. In plain terms, it's a secure bridge that lets AI assistants talk to other apps. The Superlist MCP is the bridge between your Superlist account and any AI tool that supports MCP. Once it's connected, you can ask the AI to do things in Superlist using everyday language — no copy-pasting, no switching tabs.

5 tools · Add tasks to lists, Create lists with tasks

Compatible with all major IDEs and agents via the open Model Context Protocol (MCP). CursorClaude CodeWindsurfGitHub CopilotDevinAiderClineVS CodeJetBrains AICursorClaude CodeWindsurfGitHub CopilotDevinAiderClineVS CodeJetBrains AI Synapse indexes, chunks, and extracts dependency edges for every mainstream programming language out of the box — no plugins, no configuration, no cloud. Functional Systems / Low-level OO / General-purpose Educational / Scripting / IoT Data / Markup Elixir Erlang Haskell F OCaml Clojure Scala Python JavaScript TypeScript Go Ruby Rust Java C / C++ C Kotlin Swift PHP Dart Perl R Zig Objective-C Groovy Julia SQL HTML CSS JSON Markdown YAML XML TOML HCL Dockerfile Protocol Buffers GraphQL Solidity PowerShell Pascal Lisp VBA Smalltalk Prolog Lua Assembly Shell Tcl Arduino

6 tools · Caller/callee impact mapping, find

Connect Syncro to external tools and services using the Model Context Protocol (MCP), enabling AI-powered workflows across your tech stack. - Connect the Syncro MCP Server - Syncro Claude Plugin - Syncro MCP Tools Reference - Syncro MCP Prompt Library - Troubleshoot MCP Connections - Connect AI to Your Data (MCP 101) 1. Supported Versions 2. Install and Deploy the Syncro RMM Agent 3. Get Started with Syncro 4. Uninstall Syncro Agents 5. Custom Fields for Assets & Tickets 6. Latest Updates 7. Remotely Access a Machine via Splashtop 8. Manage Scripts 9. Ticket Settings Reference

5 tools · Access the prompt library, Browse the tools reference

LLMs can now write, convert, validate, and explain Indie code using the TakeProfit MCP Server. - Ask LLM to write complete indicators from scratch based on your trading ideas - Get explanations of complex algorithm combinations and how they work together - Search the community Marketplace for published indicators by name or description — the LLM can recommend an existing indicator instead of writing one from scratch - Search built-in indicators by name, title, or abbreviation - Ask “how would I implement X indicator?” and get working code examples - Understand the logic behind technical analysis through code explanations - Learn Indie best practices through AI-guided development

5 tools · Explain Indie code and algorithms, Fetch Indie documentation

Set up a WordPress site running the Sweipe or FlatMobile theme: import a demo, plan and build a site from a one-paragraph brief, review it, rewrite page copy, change core settings. Talks to the theme's REST surface with a WordPress Application Password.

This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from your Wiki.JS instance. - Search Wiki.JS Pages: Search for pages using keywords or topics - List Wiki.JS Pages: Get a paginated list of all available pages - Get Specific Page: Retrieve a specific page by its ID - Connection Testing: Test the connection to your Wiki.JS instance - Multiple Transport Modes: Support for both stdio and HTTP stream modes - Docker Support: Ready-to-use Docker image with health checks

4 tools · get_wiki_page, list_wiki_pages