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)

0
0
Medium Cost
caffeineflo icon

portainer-mcp

by caffeineflo

Sec9

Enables AI assistants to manage Docker containers and resources through the Portainer API.

Setup Requirements

  • ⚠️Requires a running Portainer instance and a valid API key.
  • ⚠️Write operations (e.g., starting/stopping containers, deploying stacks) are disabled by default and must be explicitly enabled via the `PORTAINER_WRITE_ENABLED=true` environment variable.
  • ⚠️Network connectivity from the MCP server to the Portainer instance is required.
Verified SafeView Analysis
Write operations are explicitly disabled by default (`PORTAINER_WRITE_ENABLED=false`) and must be enabled via an environment variable, significantly reducing potential harm from accidental or malicious AI actions. Input validation via Zod is used for all tool arguments. Sensitive API keys are passed via environment variables, not hardcoded. The `PortainerClient` handles common HTTP errors (401, 403, 404) and connection issues gracefully. Docker log stripping handles multiplexed streams correctly to prevent data interpretation issues.
Updated: 2025-12-17GitHub→
0
0
Medium Cost
andrewkroh icon

fleetpkg-mcp

by andrewkroh

Sec6

Enables LLMs to query low-level metadata about Elastic Fleet integration packages from a SQLite database.

Setup Requirements

  • ⚠️Requires a local checkout of the `elastic/integrations` Git repository (`-dir` argument).
  • ⚠️The database is rebuilt each time the server starts, which can take ~10 seconds on a fast machine.
  • ⚠️Requires a Go environment to build and run from source (`go run` or `go install`).
Review RequiredView Analysis
The server allows LLMs to execute arbitrary SQLite queries against a read-only database via the `fleetpkg_execute_sql_query` tool. While the database is read-only, preventing data modification, this design poses risks: 1. **Resource Exhaustion (DoS)**: Malicious or poorly optimized queries crafted by an LLM could consume significant CPU and memory, leading to a denial of service. 2. **Information Leakage**: Complex queries could potentially extract unintended correlations or meta-information from the database schema that might not be intended for direct exposure. 3. **Path Disclosure**: Although the database is opened in `mode=ro`, certain SQLite features (if enabled in the `modernc.org/sqlite` driver's build, e.g., `readfile()`) could theoretically be exploited to read files on the system, though this is less likely with standard builds. Without explicit query sandboxing, validation, or rate-limiting for the `fleetpkg_execute_sql_query` tool, allowing untrusted LLMs to issue arbitrary SQL queries is a significant security risk. The `mode=ro` on the database connection is a strong mitigation against data corruption but not against resource abuse or some forms of information exposure.
Updated: 2025-12-23GitHub→
0
0
Medium Cost

mcp-server-remoto

by ivanleituga

Sec5

A remote server application, likely implemented in Node.js, designed to provide backend services or manage remote operations, with integrated CI/CD processes.

Setup Requirements

  • ⚠️Requires Node.js runtime and npm/yarn for dependency management.
  • ⚠️Jenkins CI/CD server is assumed for automated build/deployment processes.
  • ⚠️Specific environment variables, external services, or database dependencies are unknown without code review or a complete README.
Review RequiredView Analysis
Cannot confirm absence of 'eval' or obfuscation without code review. As a server application, it inherently involves network communication and potential security risks if not properly secured (e.g., exposed APIs, unpatched dependencies). The presence of Jenkinsfile suggests CI/CD, which requires secure configuration.
Updated: 2025-11-18GitHub→
0
0
Low Cost
Shylesh1640 icon

MCP-Server

by Shylesh1640

Sec9

Provides an MCP-compliant API server exposing basic tools, resources, and prompts for various functionalities.

Setup Requirements

  • ⚠️Python 3.12+ only
Verified SafeView Analysis
The provided code snippet does not contain 'eval', obfuscation, hardcoded secrets, or obvious malicious patterns. It relies on standard Python functions and the `fastmcp` library. Security largely depends on the `fastmcp` implementation and proper deployment practices.
Updated: 2025-11-28GitHub→
0
0
Low Cost
maciejkra icon

multirepo-claude

by maciejkra

Sec3

Provides a server implementation for the Minecraft Protocol, enabling custom game experiences or client interactions, though specific details are unknown due to missing source code.

Review RequiredView Analysis
The source code for this server was not provided in the prompt, making a comprehensive security audit impossible. The score reflects the inability to assess potential vulnerabilities like 'eval', hardcoded secrets, or network risks without code visibility.
Updated: 2026-01-16GitHub→
0
0
High Cost
estebanstifli icon

stifli-flex-mcp

by estebanstifli

Sec5

Transforms a WordPress site into an AI-powered Model Context Protocol (MCP) server, exposing 117 tools for AI agents like ChatGPT and Claude to manage WordPress and WooCommerce content.

Setup Requirements

  • ⚠️Requires WordPress Application Passwords for authentication setup, replacing custom tokens from prior versions.
  • ⚠️WooCommerce plugin must be installed and active for all 61 WooCommerce-specific tools to function, otherwise only WordPress tools are available.
  • ⚠️The primary exposure of 117 tool definitions via 'tools/list' results in a large payload (potentially thousands of tokens), which will consume a significant portion of an AI agent's context window on each initialization or list request.
Review RequiredView Analysis
The plugin contains several instances of direct database queries (e.g., using `$wpdb->query`, `$wpdb->get_var`, `$wpdb->delete`, `$wpdb->update`) without consistently utilizing `$wpdb->prepare()` for dynamic parts of the SQL, as indicated by multiple 'WordPress.DB.PreparedSQL.NotPrepared' errors in the `checktest.md` file. While some dynamic table names are derived from internal WordPress variables, this pattern can lead to SQL injection vulnerabilities if user input were to influence any part of these unprepared queries. The 'fetch' tool allows making HTTP requests to arbitrary URLs. Although it requires an authenticated user with 'edit_posts' capability and client-side confirmation, the lack of a more granular server-side capability check specifically for network access introduces a potential Server-Side Request Forgery (SSRF) risk. The use of `maybe_unserialize()` for messages stored in the plugin's queue table, while seemingly processing internal plugin-generated content, is a generally discouraged practice that could introduce PHP object injection vulnerabilities if the serialized data ever becomes controllable by an attacker. No hardcoded secrets or obvious obfuscation were found, and authentication is delegated to WordPress Application Passwords, which is a good practice.
Updated: 2026-01-07GitHub→
0
0
Low Cost
stephan-chiorean icon

bluekit-mcp-server

by stephan-chiorean

Sec8

The BlueKit MCP server provides tools for AI-assisted development, enabling the creation and management of code generation kits, structured blueprints, expert agents, system diagrams, and project walkthroughs, along with project initialization and git clone management.

Setup Requirements

  • ⚠️Requires `git` command-line tool to be installed and available in the system's PATH for clone management features.
  • ⚠️The `better-sqlite3` dependency is a native Node.js module, which may require build tools (e.g., `build-essential` on Linux, Xcode on macOS) if prebuilt binaries are not available for the specific environment.
  • ⚠️Mermaid diagram validation functionality (`bluekit_diagram_generateDiagram`) spawns a separate `npx` process (`@rtuin/mcp-mermaid-validator@latest`), which requires an internet connection to fetch the package if not cached, and may incur a slight startup delay or compatibility issues with specific Node.js environments.
Verified SafeView Analysis
The server uses `execSync` for git operations (`git clone`, `git checkout`) in `CloneTools.ts` and spawns external processes via `npx` for Mermaid validation in `MermaidValidatorClient.ts`. While `gitUrl`s are derived from local repositories during registration, rather than direct user input, and `npx` targets a specific known package, these interactions with external processes and fetching external code (git repos) introduce inherent supply-chain and execution risks. File system operations are extensive but generally confined to the project or user home directory, with path normalization applied to mitigate directory traversal. No obvious `eval` or direct arbitrary user command injection vulnerabilities were found, nor hardcoded sensitive secrets.
Updated: 2025-12-24GitHub→
0
0
Medium Cost
plantoncloud icon

mcp-server-planton

by plantoncloud

Sec9

Enables AI agents to query and manage Planton Cloud resources using user permissions via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Planton Cloud API Key, which must be obtained from the Planton Cloud Console and dictates user permissions.
  • ⚠️Developers must use Go 1.25+ for local development to avoid version mismatch issues with project dependencies.
  • ⚠️Requires access to Planton Cloud APIs (either the hosted `apis.planton.cloud:443` or a local instance `localhost:8080`).
Verified SafeView Analysis
The server implements robust per-user API key authentication, ensuring fine-grained authorization and audit trails. API keys are sourced from environment variables (for STDIO mode) or Authorization headers (for HTTP mode) and are not hardcoded. TLS is used for production gRPC endpoints. While a global API key storage workaround is used for HTTP mode due to a library limitation, it is well-documented and mitigated by the single-threaded nature of SSE connections per client, posing a low risk in typical usage. Overall, the project demonstrates strong security practices and clear documentation.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
Linkly-HQ icon

mcp-server-linkly

by Linkly-HQ

Sec9

Manages URL shortening, link analytics, and custom domains for the Linkly platform through a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires Node.js runtime environment (npm/npx).
  • ⚠️A Linkly account is required to obtain API credentials.
  • ⚠️Mandatory environment variables: LINKLY_API_KEY and LINKLY_WORKSPACE_ID must be set for self-hosting.
Verified SafeView Analysis
The server's core functionality involves proxying requests to the Linkly API. It correctly uses environment variables (LINKLY_API_KEY, LINKLY_WORKSPACE_ID) for API authentication in the self-hosted `index.js` version. For the Cloudflare Worker version (`src/index.ts`), OAuth client credentials (LINKLY_CLIENT_ID, LINKLY_CLIENT_SECRET) are defined in `worker-configuration.d.ts`, but the runtime code accesses them via the `env` object, implying secure configuration as platform secrets rather than hardcoded values. No 'eval', code obfuscation, or obvious malicious patterns were found. The primary security risk lies in the secure handling and configuration of the required API keys/OAuth credentials in the deployment environment.
Updated: 2026-01-13GitHub→
0
0
High Cost
lkm1developer icon

mcp-servers-sse

by lkm1developer

Sec3

A scalable Express.js server that acts as an API gateway, hosting multiple Model Context Protocol (MCP) servers with real-time Server-Sent Events (SSE) support, route-based isolation, and JWT authentication for integrating various external APIs and tools.

Setup Requirements

  • ⚠️Requires API keys/tokens for potentially 20+ external services (e.g., Tavily, BuiltWith, NeverBounce, RocketReach, Apollo.io, FindyMail, Ocean.io, IcyPeas, HubSpot, SmartLead, Resend, Notion, Firecrawl, Hatch), many of which are paid services.
  • ⚠️Google Docs/Sheets require a path to a service account key file, and Gmail requires an OAuth2 access token, implying complex OAuth flow setup in addition to API keys.
  • ⚠️Requires `SUPABASE_URL` and `SUPABASE_SERVICE_ROLE_KEY`, indicating a dependency on a Supabase backend for persistent storage (e.g., sessions, configurations) which needs to be set up separately.
Review RequiredView Analysis
1. Hardcoded Secret: The 'EMAIL_API_KEY' in 'servers/meerkats/adapter.js' is hardcoded ('jhfgkjghtucvfg'), posing a critical security risk. 2. Unencrypted Network Communication: The 'EMAIL_SERVICE_URL' in 'servers/meerkats/adapter.js' uses plain HTTP ('http://34.46.80.154/api/email'), which allows eavesdropping and tampering with sensitive data. 3. DNS Rebinding Protection Disabled: 'enable_dns_rebinding_protection: false' in 'server.json' is a severe vulnerability that can allow attackers to bypass same-origin policies and attack internal network resources. 4. Sensitive Data in JWT: The server stores 'apiKey' or 'accessToken' directly within the JWT payload. If the 'JWT_SECRET' (an environment variable) is compromised, an attacker can forge tokens and gain full access to all integrated external APIs for any user. 5. Google API Credentials Handling: Google Sheets/Docs require a path to a service account key file, and Gmail requires an OAuth2 access token. The secure handling, storage, and refresh mechanisms for these credentials are critical and not fully detailed, posing a potential risk.
Updated: 2026-01-05GitHub→
0
0
Low Cost
v1nvn icon
Sec10

Provides a curated and categorized list of Model Context Protocol (MCP) server implementations, enabling AI models to securely interact with local and remote resources through standardized server integrations.

Verified SafeView Analysis
This repository serves as a curated list of Model Context Protocol (MCP) server implementations. The provided 'source code' is the README.md file, which is static documentation and does not pose direct security risks. However, users are strongly advised to exercise caution and perform thorough security audits on any *individual MCP server* they choose to deploy from this list, as those servers interact with various local and remote resources and may have different security postures.
Updated: 2026-01-19GitHub→
0
0
Low Cost
zmacks icon

tiny-mcp

by zmacks

Sec6

Facilitates real-time, peer-to-peer-like message exchange between connected WebSocket clients, acting as a simple message broker.

Setup Requirements

  • ⚠️Python 3.11+ required
Verified SafeView Analysis
The server lacks built-in authentication or authorization, meaning any client can connect and send messages. While it does not show direct code injection vulnerabilities (no 'eval' or similar), deploying it publicly without an external security layer would expose it to unrestricted access. Message content is not deeply validated beyond JSON parsing, relying on client-side sanity for message structures.
Updated: 2025-12-11GitHub→
PreviousPage 701 of 760Next