MCP Tools | Model Context Protocol Server Directory

The mcp-walmart-marketplace server connects your development environment directly to Walmart's Marketplace APIs, letting you query product catalogs, pricing, inventory, and order data programmatically through the standardized MCP protocol. It's aimed at developers building tools, dashboards, or automation pipelines for US-based third-party sellers on Walmart.com. Instead of manually integrating each Walmart endpoint, you get a single MCP-compatible interface that handles authentication, request formatting, and response parsing. This makes it easy to plug Walmart data into IDEs, agent workflows, or custom applications that already support MCP. Compared to scraping or raw API wrappers, it offers a cleaner, more maintainable integration path, though it's limited to the US marketplace and requires valid seller credentials. If you're already using MCP-based tooling, adding Walmart data becomes a matter of enabling the server rather than writing boilerplate HTTP clients. The project is community-maintained and hosted on GitHub, making it a practical starting point for seller-side analytics or backend sync utilities.

The Ozon MCP Server connects your development environment directly to Ozon's Seller and Performance APIs through 151 purpose-built tools. It's designed for developers managing multiple Ozon seller accounts programmatically, offering streamlined access to pricing, promotions, advertising, orders, returns, finance, and analytics data without wrestling with API authentication and pagination. Instead of building custom integrations for each endpoint, you can query or update information using natural language prompts within your existing MCP-compatible client. This is particularly useful for automating repricing strategies, syncing inventory across accounts, pulling performance reports, or building dashboards that aggregate data from multiple Ozon entities. Compared to direct API integration, it reduces boilerplate code and handles request throttling automatically. The server acts as a middleware layer, so you get consistent JSON responses and can chain operations easily. Since it's community-maintained, it evolves with Ozon's API changes, and being open-source means you can inspect or extend the toolset as needed. It's not a replacement for the official API but a practical abstraction for developers who want results over setup.

As LLM-integrated applications move from prototype to production, the attack surface for prompt injections and data poisoning has expanded significantly. Universal Poison Armor is an open-source MCP security layer designed to sit between your data sources and your model. Unlike traditional perimeter security, this tool functions as a specialized firewall within the Model Context Protocol framework, intercepting adversarial inputs—such as sybil attacks and poisoned RAG retrieval chunks—before they hit your context window. For developers, this means you can leverage external tools and dynamic data fetching without manually sanitizing every incoming retrieval. It integrates directly into your existing MCP ecosystem, providing a programmable defense layer that mitigates the risk of indirect prompt injection. Instead of building custom regex filters for every new integration, you can deploy this as a standardized middleware to harden your agentic workflows against evolving adversarial patterns.

Jueban is a specialized MCP toolset designed to bridge the gap between LLMs and authentic Buddhist scholarship. Unlike generic religious queries that often suffer from hallucination, this implementation provides read-only, source-backed access to canonical scriptures. For developers building contemplative or educational AI agents, Jueban offers four distinct production-ready tools that enable precise scripture searching, contextual passage guidance, and deep doctrinal explanations. The protocol allows your model to verify interpretations against actual texts rather than relying on internal training weights, making it ideal for high-fidelity research tools or guided practice applications. It integrates seamlessly into existing MCP-compliant environments, providing a structured way to inject verified religious context into a conversation without compromising the model's core logic or safety parameters.

For developers building local-first AI workflows, your-mail-mcp provides a secure, read-only bridge between LLMs and your personal email archives. Unlike cloud-based integrations that require granting third-party access to your entire mailbox, this tool operates via a self-hosted architecture. It functions by mirroring your IMAP data to a local maildir and leveraging the notmuch indexing engine, allowing your AI agent to perform high-speed, semantic searches across years of correspondence without taxing your mail server. This setup is ideal for creating personalized RAG (Retrieval-Augmented Generation) pipelines where the model needs context from past threads to draft replies or summarize long-running discussions. Because it relies on local indexing, the latency is significantly lower than traditional API polling, making it a robust choice for developers who prioritize data sovereignty and high-performance local tool use.

Octura Solutions Site Tools is a specialized MCP server designed to bridge the gap between LLMs and deterministic financial logic. While general-purpose models often struggle with precise arithmetic and complex regulatory compliance, this tool provides a suite of 24 hardened calculators that ensure mathematical accuracy for critical business operations. It covers a specific range of high-value use cases, including Odoo ERP cost modeling, multi-jurisdictional sales tax calculations (US, Canada, EU), Canadian payroll deductions, and inventory planning. For developers building agentic workflows or financial assistants, this server eliminates the 'hallucination risk' inherent in LLM math by offloading calculations to a reliable, hosted environment. Instead of prompting a model to 'estimate' tax, you can integrate this tool to fetch exact, rule-based results via standard MCP protocols, making it an essential component for enterprise-grade ERP and fintech integrations.

Melt is a finance-focused MCP server that analyzes your team's headcount and labor cost data to quantify wasted spend and time across AI coding agents like Claude, Cursor, and others. It doesn't just report activity—it estimates real dollar leakage from idle agents, redundant workflows, and inefficient task allocation. For dev teams already using multiple MCP-compatible agents, Melt connects to your existing cost and usage telemetry to surface actionable inefficiencies, helping you right-size subscriptions, optimize agent routing, and justify budget reallocations. It integrates via standard MCP protocols, so setup is lightweight if you're already in the ecosystem. Unlike generic analytics tools, Melt speaks the language of engineering finance: it translates agent behavior into departmental value loss, making it easier to have concrete conversations about ROI with stakeholders who care about bottom-line impact rather than token counts.

The SAP ABAP MCP server connects external tools to ABAP development environments through SAP's ABAP Development Tools (ADT) and JSON RPC protocols. It enables developers to query repositories, inspect code objects, run programs, and gather system metadata without leaving their preferred editor or automation pipeline. By exposing MCP-compliant endpoints, it bridges modern LLM-powered tooling with legacy SAP systems, letting you build custom assistants for code review, refactoring, or documentation generation. Integration requires an SAP system with ADT enabled and basic auth credentials, then register the server in your MCP client configuration. Unlike generic HTTP wrappers, this server understands ABAP-specific structures like function modules, classes, tables, and DDIC objects, so responses are structured for downstream tool consumption rather than raw dumps. It's aimed at teams maintaining SAP codebases who want to automate repetitive tasks or embed AI assistance directly into ABAP workflows.

Gives an AI agent a disposable email and a real UK phone number to test signup/verification flows end to end

apillow-mcp bridges the gap between LLM reasoning and real-world real estate intelligence by exposing granular Zillow datasets through the Model Context Protocol. Instead of relying on outdated training data or brittle web scraping scripts, developers can integrate this tool to give AI agents direct access to live property metrics. It supports high-fidelity queries, including ZIP-based searches, specific address lookups, and deep dives into historical pricing and Zestimates. For developers building autonomous real estate agents, investment analysis tools, or localized market bots, this provides a structured way to ingest over 50 distinct data fields per listing. Unlike general search tools that return messy HTML, apillow-mcp delivers clean, schema-ready property data, making it significantly easier to build reliable workflows for mortgage calculations, market trend analysis, or property management automation.

tube-bridge is a self-hosted MCP server that lets you treat YouTube as a research data source rather than just a video platform. It exposes 17 tools covering search, transcripts, timestamped video frames, comments, and a local semantic corpus you can query privately. The server runs locally, so your queries and any cached content stay on your machine, which matters for both privacy and avoiding rate limits. Integration follows the standard MCP protocol, so any MCP-capable client (Claude Desktop, custom agents, editors with MCP support) can discover and call its tools without extra glue code. Compared to ad-hoc scraping, tube-bridge normalizes transcript and comment data into structured outputs, supports timestamped frame extraction for visual evidence, and adds a local vector store so you can build private, semantic search over collected content. It's aimed at researchers, analysts, and developers who need repeatable, scriptable access to YouTube data without depending on external APIs or sending queries to third-party services. Setup is via the GitHub repo, and you'll need a local environment that can run the server and store the corpus.

Leadgen MCP provides programmatic access to Romanian business registry data from ONRC, the country's official registry. Developers can look up company details, search for directors by name or ID, extract website contact information, and perform domain audits including WHOIS, DNS, SPF, and DMARC records. It's designed for integration with AI agents and automation workflows that need reliable, structured business data from Romania. The tool acts as a bridge between raw registry data and practical applications, returning clean JSON responses. For comparison, it's more focused than general web scraping tools since it targets official sources directly, though it's geographically limited to Romanian entities. Use cases include sales prospecting, compliance verification, fraud detection, and building business intelligence dashboards. Integration follows standard MCP protocols, making it compatible with existing agent frameworks. You'll need the MCP client set up and can find implementation details on the GitHub repository linked in the metadata.

Choosing the right hosting infrastructure often involves navigating a fragmented landscape of provider specs, regional latency, and pricing tiers. The vps-choose-mcp tool solves this by integrating real-time cloud service selection directly into your LLM workflow. Instead of manually cross-referencing vendor documentation, you can use this MCP server to query managed VPS and cloud host options tailored to specific deployment scenarios—whether you need low-latency edge computing, high-memory instances for databases, or budget-friendly nodes for testing. For developers, this means your AI assistant can act as a specialized DevOps consultant, capable of recommending optimal infrastructure based on your project's technical requirements and geographic constraints. It bridges the gap between high-level architectural planning and the granular reality of cloud provisioning, making it a practical utility for rapid prototyping and infrastructure-as-code preparation.

Obsify is a local, privacy-preserving PII detection and redaction tool built on MCP, designed for developers who need to handle sensitive data without exposing it to external services. Unlike cloud-based solutions, Obsify runs entirely on your machine, using Presidio and checksum-based validation to identify PII such as Australian identifiers (ABN, ACN, TFN) with deterministic accuracy and no reliance on LLMs or network calls. It operates on data shape rather than raw values, meaning your local code handles real data and returns only masked, aggregated results. This makes it ideal for compliance workflows, data anonymization pipelines, and secure testing environments where privacy is critical. Since it's MCP-compliant, Obsify integrates smoothly into existing development tools and agent ecosystems. It’s particularly useful for teams working with regulated data in finance, healthcare, or government sectors who want to avoid vendor lock-in and ensure auditability without sacrificing developer flexibility.

Auditra exposes a focused MCP interface for auditing WordPress plugins directly from your IDE or AI assistant. Instead of manually scanning codebases or running disparate CLI tools, you get a standardized `audit_plugin` method that accepts a plugin slug or local path and returns structured findings: outdated dependencies, known CVEs, coding-standard violations, deprecated API usage, and permission overreach. The server wraps WP-CLI, PHP_CodeSniffer (WordPress ruleset), Composer audit, and a curated vulnerability database, so results are consistent and actionable. Typical workflows include pre-merge checks in CI, quick vetting of third-party plugins before installation, and automated reporting for client site maintenance. Integration is zero-config for most stacks — add the server to your MCP client (Cursor, Claude Desktop, Continue, etc.) and call the tool like any other function. Compared to standalone SAST scanners, Auditra is WordPress-aware: it understands plugin architecture, hook semantics, and the WP.org update cycle, reducing false positives. It doesn't replace deep static analysis but excels at the 80% of issues that are WP-specific and immediately remediable. Open-source (MIT), community-maintained, and extensible via custom rule packs.