Stop Searching. Start Trusting.

The curated directory of MCP servers, vetted for security, efficiency, and quality.

Browse DirectoryWhy Us?

Tired of the MCP "Marketplace" Chaos?

We built MCPScout.ai to solve the ecosystems biggest pain points.

No Insecure Dumps

We manually analyze every server for basic security flaws.

Easy Setup

Our gotcha notes warn you about complex setups.

Avoid "Token Hogs"

We estimate token costs for cost-effective agents.

Products, Not Demos

We filter out "Hello World" demos.

CATEGORIES:
SORT:

Vetted Servers(9120)

30
1
Medium Cost
u9401066 icon

zotero-keeper

by u9401066

Sec7

AI-powered management and organization of local Zotero bibliographic references, enabling search, import, and basic library analytics through AI agents like VS Code Copilot or Claude Desktop.

Setup Requirements

  • ⚠️Requires Zotero 7.0+ desktop client to be running.
  • ⚠️Zotero's Local API must be manually enabled by running a JavaScript command in the Zotero console once.
  • ⚠️Requires Python 3.12+ (as specified in pyproject.toml).
  • ⚠️Remote Zotero access requires manual `netsh` port proxy and firewall configuration on the Zotero machine (Windows).
  • ⚠️PubMed integration features require the `pubmed-search-mcp` package to be installed separately.
Verified SafeView Analysis
The primary security concern stems from the underlying Zotero Local API (port 23119) which inherently lacks authentication. If the MCP server is exposed on a network, any client can interact with it and, by extension, the local Zotero instance. The server itself does not introduce new code-level vulnerabilities like arbitrary code execution via user input. However, for remote Zotero setups, the user is explicitly responsible for configuring `netsh` port proxies and firewall rules, and for ensuring network security. No hardcoded secrets were identified, and API keys are expected to be provided via environment variables. Input validation is implemented prior to Zotero API calls.
Updated: 2026-01-12GitHub→
30
1
Medium Cost
dalehurley icon

laravel-php-mcp-sdk

by dalehurley

Sec8

A comprehensive Laravel wrapper that enables applications to act as Model Context Protocol (MCP) servers and clients, facilitating AI/LLM integration.

Setup Requirements

  • ⚠️Requires PHP 8.1 or higher and Laravel 10.x, 11.x, or 12.x.
  • ⚠️Relies on 'dalehurley/php-mcp-sdk' as a core dependency, which may have its own PHP extension requirements for AMP-based transports (HTTP/WebSocket).
  • ⚠️For background tasks (e.g., PeriodicPingJob), Laravel's queue system must be configured and queue workers running.
Verified SafeView Analysis
The server implements comprehensive security features including CORS, rate limiting, input sanitization, security headers (CSP, XSS, Frame Options), and suspicious activity detection (SQLi, XSS, Path Traversal, Command Injection patterns). Authentication supports OAuth 2.1, Bearer tokens, and API keys with scope-based authorization. A potential risk exists if the 'mcp.authorization.bearer.valid_tokens' or 'mcp.authorization.api_key.valid_keys' configurations are empty while authorization is enabled, as it would allow any non-empty token/key to authenticate. It is crucial to configure valid tokens/keys in production environments.
Updated: 2025-11-25GitHub→
30
1
Low Cost
la-rebelion icon

mcp-website

by la-rebelion

Sec9

Public site for the Headless API (HAPI) Stack for Model Context Protocol (MCP), providing guidance, clarifying limitations, and offering practical advice for making existing APIs AI-ready.

Setup Requirements

  • ⚠️Requires Node.js ≥ 20
  • ⚠️Uses Bun as the preferred package manager (though npm/yarn may also work)
Verified SafeView Analysis
This repository hosts a static Docusaurus website. The primary security risks are limited to client-side vulnerabilities (e.g., XSS through maliciously crafted blog content, though Docusaurus's Markdown parsing helps mitigate this) and potential vulnerabilities in its third-party dependencies (e.g., Docusaurus itself, React, or embedded scripts like HubSpot and Google Analytics). No server-side vulnerabilities are present as it is a static site. No hardcoded sensitive secrets were identified in the provided source code snippets. The forms on the site are handled client-side for tracking or simulated submission, with no direct server-side processing from this codebase.
Updated: 2026-01-16GitHub→
30
11
Low Cost
jritsema icon

mcp-cli

by jritsema

Sec9

A command-line interface tool for managing Model Context Protocol (MCP) server configuration files across various AI tools.

Setup Requirements

  • ⚠️Requires `mcp-compose.yml` (Docker Compose specification) for server configurations.
  • ⚠️Relies on environment variables for sensitive data (e.g., API keys, client secrets), which can be loaded from the system environment or a `.env` file.
  • ⚠️If using containerized MCP servers (via the `image` property in `mcp-compose.yml`), Docker or a compatible container runtime (e.g., Finch, Podman) is required.
Verified SafeView Analysis
The CLI tool is written in Go, which generally provides better memory safety and reduced risk of common scripting vulnerabilities. It processes local YAML/JSON files and environment variables. Network calls are made for OAuth token acquisition for remote MCP servers, using standard HTTP client practices. There are no indications of 'eval' or malicious patterns. A warning is explicitly provided in the `mcp ls -c` command documentation that its output (expanded commands with environment variables) 'may expose sensitive data such as API keys'. This is a disclosure risk if the output is mishandled by the user/agent, but not an inherent vulnerability in the CLI's execution logic.
Updated: 2026-01-03GitHub→
30
1
Low Cost
detailobsessed icon

unblu-mcp

by detailobsessed

Sec8

A Model Context Protocol (MCP) server providing AI assistants with token-efficient access to Unblu API endpoints through progressive disclosure and Kubernetes integration.

Setup Requirements

  • ⚠️Requires `kubectl` to be installed and authenticated for Kubernetes deployments.
  • ⚠️`PATH` environment variable needs explicit configuration in MCP client (e.g., Claude Desktop on macOS) to ensure `unblu-mcp` and `kubectl` are found.
  • ⚠️For the default provider, `UNBLU_BASE_URL` and `UNBLU_API_KEY` (or `UNBLU_USERNAME`/`UNBLU_PASSWORD`) environment variables are mandatory.
  • ⚠️`PyYAML` is an optional dependency but required if using custom K8s environment configuration files.
  • ⚠️`eunomia-mcp` is an optional dependency (requiring `pip install unblu-mcp[safety]`) but highly recommended for server-side policy enforcement.
Verified SafeView Analysis
The server uses `subprocess` for `kubectl` commands, which is necessary for Kubernetes integration but requires careful validation of inputs. The `call_api` tool acts as a proxy, passing parameters directly to `httpx.AsyncClient`, which could be a vector for malicious inputs if an AI agent or user crafts vulnerable `operation_id` or parameters (e.g., SQL injection, XSS), though `operation_id` must exist in the OpenAPI spec. Optional server-side policy enforcement via Eunomia is available and recommended for restricting API access. No hardcoded secrets, obfuscation, or `eval` usage was found.
Updated: 2026-01-16GitHub→
30
1
Low Cost
Dasix icon
Sec8

Provides shared memory capabilities and tooling for multiple AI agent instances, backed by Git for version control and persistence. It offers a boilerplate structure for building Model Context Protocol (MCP) servers.

Setup Requirements

  • ⚠️Extended IP address data (ASN, host, organization, etc.) from the `ip_get_details` tool requires an `IPAPI_API_TOKEN` environment variable; without it, only basic information is retrieved.
  • ⚠️The server currently supports only STDIO transport; attempting to start it in SSE (HTTP/SSE) mode will result in an explicit error as it is not yet implemented.
  • ⚠️To utilize the full 'shared memory' features described in the `README.md` (e.g., Git-backed persistence, project metadata), the `GIT_REPO_URL`, `GIT_REPO_PATH`, and `PROJECT_META_PATH` environment variables would need to be configured.
Verified SafeView Analysis
The provided code snippets, primarily focusing on an IP address lookup tool, demonstrate good security practices including input validation (Zod schemas, service-level checks for private/reserved IPs), proper API interaction (URLSearchParams for query parameters, `fetch` utility with error handling), and safe file system operations for configurations and logging (using `path.join`). There are no direct uses of `eval` or arbitrary shell command execution. Hardcoded sensitive data is avoided, relying on environment variables or config files for API tokens. However, a full security audit of the core 'shared memory' functionality (Git operations, template system, client authentication with `SHARED_MEMORY_TOKEN`) cannot be completed as the corresponding source code for these features was not provided. The `README.md` mentions 'File path sanitization prevents directory traversal' and 'Template validation before saving' which indicates an awareness of these concerns for the unexamined parts.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
insightfinder icon

insightfinder-mcp-server

by insightfinder

Sec9

This server enables Large Language Models (LLMs) to interact with the InsightFinder platform, providing capabilities for incident management, anomaly detection, system monitoring, and deployment analysis.

Setup Requirements

  • ⚠️Requires Python 3.8 or higher.
  • ⚠️InsightFinder credentials (`X-IF-License-Key`, `X-IF-User-Name`) must be provided via HTTP headers on each request, not as server environment variables.
  • ⚠️For secure operation, the MCP server's `HTTP_API_KEY` (or other configured authentication credentials) should be explicitly set via environment variables, though it generates a default if missing.
Verified SafeView Analysis
The server implements robust authentication (API Key, Bearer, Basic), rate limiting, and IP whitelisting. InsightFinder and JIRA API credentials are securely passed via request headers, not stored in server configuration, enhancing multi-tenancy and isolation. It handles proxy headers, limits request/response sizes, and uses secure token generation for defaults. A deprecated JIRA tool function contains hardcoded values, but this function is not actively used by exposed tools and is explicitly marked for removal.
Updated: 2026-01-16GitHub→
30
1
Medium Cost
QuentinCody icon

datacite-mcp-server

by QuentinCody

Sec9

A Model Context Protocol (MCP) server that enables AI assistants to query the DataCite GraphQL API for rich metadata about research outputs, including DOIs, datasets, software, publications, and their connections within the PID Graph.

Setup Requirements

  • ⚠️Requires deployment to Cloudflare Workers or local emulation using `wrangler dev`.
  • ⚠️For non-local or sandboxed clients, the `MCP_ALLOWED_ORIGINS` environment variable must be configured to allow specific origins, due to enforced origin validation.
  • ⚠️Relies on a Cloudflare Durable Object (implicitly backed by SQLite) for staging large responses, which requires a Cloudflare account setup and Durable Object binding for full functionality.
Verified SafeView Analysis
The server implements origin validation for incoming MCP requests, enhancing security. It uses Cloudflare Durable Objects (SQLite-backed) for staging large responses, which is a managed and secure storage solution in a serverless environment. External GraphQL API calls are directed to a known DataCite endpoint. There is no observed use of `eval` or other dangerous dynamic code execution, and no sensitive hardcoded secrets are present.
Updated: 2025-12-01GitHub→
30
1
High Cost
slamer59 icon

mcp-seo

by slamer59

Sec8

A server providing comprehensive SEO analysis, keyword research, competitor intelligence, PageRank calculations, and internal link structure analysis, primarily leveraging the DataForSEO API and Kuzu graph database.

Setup Requirements

  • ⚠️Requires DataForSEO API credentials (DATAFORSEO_LOGIN, DATAFORSEO_PASSWORD), which is a paid service.
  • ⚠️Relies on Kuzu graph database (requires 'kuzu' Python package), which may require specific system dependencies or setup for optimal performance.
  • ⚠️Performs web crawling (uses 'aiohttp' and 'BeautifulSoup4'), potentially consuming network bandwidth and requiring robust error handling for various HTML structures.
Verified SafeView Analysis
The server's core functionality involves extensive external API calls (DataForSEO) and web crawling (LinkGraphBuilder uses aiohttp, BeautifulSoup4). While API credentials are correctly handled via environment variables and standard authentication methods (Basic Auth), and no direct 'eval' or hardcoded secrets were found, web crawling inherently involves processing arbitrary external content, which can introduce risks from malformed or malicious data. The Kuzu database is managed locally via temporary files. The overall design follows good practices for its intended purpose.
Updated: 2025-11-27GitHub→
30
1
Low Cost
sbroenne icon

mcp-server-obs

by sbroenne

Sec8

Control OBS Studio's recording, streaming, and scene management from VS Code using AI assistants.

Setup Requirements

  • ⚠️Requires Windows OS.
  • ⚠️Requires OBS Studio with WebSocket server enabled and configured (port, optional password).
  • ⚠️Requires .NET 10 Runtime for standalone server operation, or .NET 8 Runtime for the VS Code extension to acquire it.
  • ⚠️Requires VS Code 1.106.0 or later and an MCP-compatible AI assistant (e.g., GitHub Copilot).
Verified SafeView Analysis
The server runs as a local .NET executable and connects to OBS Studio via its WebSocket server, primarily on localhost. Connection details (host, port, password) are managed through VS Code settings or environment variables, preventing hardcoded secrets. No 'eval' or obvious obfuscation is present in the provided JavaScript components. The core .NET server's source code was not provided for a full audit, but it is stated to use the 'obs-websocket-dotnet' library, which is a standard open-source client. The overall security relies heavily on the user configuring OBS Studio's WebSocket server securely (e.g., strong password, not exposing it to the public internet).
Updated: 2026-01-12GitHub→
30
1
High Cost
IDragos94 icon

codemesh

by IDragos94

Sec1

CodeMesh acts as an intermediary MCP server that allows AI agents to write and execute TypeScript code to orchestrate tools and data from multiple configured MCP servers, featuring a self-improving augmentation system for documentation.

Setup Requirements

  • ⚠️Requires Node.js 18+ and pnpm (or npm) for development and running.
  • ⚠️Requires a `.codemesh/config.json` file in the project root to define the MCP servers it will orchestrate.
  • ⚠️The core `vm2` dependency, used for sandboxed code execution, is deprecated and has known critical security vulnerabilities, making it unsafe for production or untrusted code execution.
Review RequiredView Analysis
The project relies on `vm2@3.9.19` for sandboxed TypeScript code execution. The `pnpm-lock.yaml` explicitly marks this dependency as "deprecated: The library contains critical security issues and should not be used for production! The maintenance of the project has been discontinued. Consider migrating your code to isolated-vm." This poses a significant security risk, as a malicious agent or crafted input could exploit these vulnerabilities to break out of the sandbox. While `eval: false` and `wasm: false` are configured, these do not mitigate the underlying `vm2` security issues. Environment variable handling for sub-servers correctly uses substitution to prevent hardcoding secrets.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
zcebupelka icon

graphql-mcp-bridge

by zcebupelka

Sec9

Facilitates seamless integration between GraphQL APIs and Model Context Protocol (MCP) compatible AI systems by converting GraphQL schemas into type-safe, validated MCP tools.

Setup Requirements

  • ⚠️Requires Node.js version 24.0.0 or higher.
  • ⚠️Expects a valid GraphQL schema string as input for `schemaParser`.
  • ⚠️Intended for integration with an external Model Context Protocol (MCP) server, requiring additional setup for the MCP server itself (e.g., `@modelcontextprotocol/sdk/server/mcp`).
  • ⚠️To execute generated GraphQL queries, a separate GraphQL client library (e.g., `@apollo/client`, `graphql-request`) is needed.
Verified SafeView Analysis
The library employs Zod for comprehensive input and output validation, significantly reducing common injection risks. GraphQL queries are generated using variables (`$var`) rather than direct string interpolation of user data, preventing GraphQL injection vulnerabilities. No direct use of `eval` or `child_process` detected at runtime. The `schemaParser` includes configurable limits (`maxOperations`, `maxFields`, `maxSchemaDepth`) to mitigate potential Denial-of-Service attacks from overly complex or large GraphQL schema inputs, though proper configuration is required for very large/malicious schemas.
Updated: 2026-01-19GitHub→
PreviousPage 214 of 760Next