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
Low Cost
context-hub icon

mcp-server

by context-hub

Sec3

This MCP server module provides context generation, tool execution, and prompt management capabilities for AI clients like Claude Desktop, Cursor, and Codex, acting as a backend for 'ctx' (Context Generator) framework.

Setup Requirements

  • ⚠️Requires 'ctx' (Context Generator) command-line tool to be installed and in PATH.
  • ⚠️Requires PHP 8.3+ and Composer for dependency management.
  • ⚠️Requires writable directories for persistent state (`.project-state.json`) and application logs.
  • ⚠️Tool definitions for 'run' and 'http' types must be meticulously designed with strict schemas and input validation to mitigate command injection and SSRF risks.
Review RequiredView Analysis
The `RunToolHandler` executes arbitrary shell commands and the `HttpToolHandler` makes external HTTP requests, both allowing arguments to be passed from the MCP client. While `ToolSchema` and `ToolArgumentsProvider` are in place to define and potentially restrict arguments, the inherent risk of command injection (if `ToolArg` values are not properly sanitized or schemas are not strictly enforced) and Server-Side Request Forgery (SSRF) remains very high. The default `MCP_TOOL_COMMAND_EXECUTION` is `true`, enabling command execution by default. Loading content from external URLs in `FileMessageContentLoader` also presents an SSRF risk.
Updated: 2026-01-18GitHub→
30
1
High Cost
Sec8

This project serves as an educational introduction to agentic AI concepts, demonstrating large language model fine-tuning using Unsloth and exploring a Multi-Candidate Platform (MCP) framework.

Setup Requirements

  • ⚠️Requires a dedicated GPU (e.g., NVIDIA with CUDA) with substantial VRAM for efficient LLM fine-tuning using Unsloth.
  • ⚠️Requires a Python environment with specific dependencies (e.g., Unsloth, PyTorch/TensorFlow, Transformers, Jupyter for notebooks).
  • ⚠️May require API keys for external Large Language Model services, depending on the agentic AI implementation within the notebooks.
Verified SafeView Analysis
Limited security audit due to lack of access to file content. Assumes benign educational intent based on project naming. The project likely involves network interactions for downloading models/data and potentially API calls to external LLM services, which are typical for ML projects and should be reviewed in detail if specific content were available. No obvious 'eval' or obfuscation risks are inferable from file names alone.
Updated: 2025-11-18GitHub→
30
1
Low Cost
withinfocus icon

tba-mcp-server

by withinfocus

Sec9

Provides a Model Context Protocol (MCP) interface to The Blue Alliance API, enabling AI assistants and other clients to retrieve comprehensive FIRST Robotics Competition team, event, and match data.

Setup Requirements

  • ⚠️Requires a The Blue Alliance API key (registration at https://www.thebluealliance.com/account)
  • ⚠️Requires Node.js ~24 and npm ~11.
Verified SafeView Analysis
Robust input and output validation is implemented using Zod schemas, mitigating injection and malformed data risks. The TBA API key is correctly handled as an environment variable and not hardcoded. The server's operation through stdio limits direct system interaction, reducing the attack surface. Error handling for uncaught exceptions and unhandled rejections is present. No 'eval' or obfuscation found.
Updated: 2026-01-17GitHub→
30
1
Medium Cost
Surendrakumawat992892 icon

fake-claude-plugins

by Surendrakumawat992892

Sec3

Develop production-ready Model Context Protocol (MCP) servers using the Go SDK, with an emphasis on type safety and best practices.

Setup Requirements

  • ⚠️Requires Go programming language and SDK to be installed to use the development tools described.
  • ⚠️The project utilizes a specific 'Model Context Protocol (MCP) Go SDK', requiring familiarity with and dependencies on this framework.
  • ⚠️There is a critical discrepancy between the `README.md` describing a downloadable desktop application and the provided source code, which defines an AI agent and commands for *developing* an MCP server. This ambiguity creates a significant friction point and security risk.
Review RequiredView Analysis
The provided source code consists of definitions for an AI agent and commands to *generate and review code for an MCP server*. It does not contain the actual executable server implementation. The `README.md` *however*, instructs users to download a `.zip` file from a raw GitHub link (`https://raw.githubusercontent.com/Surendrakumawat992892/fake-claude-plugins/main/Acipenseridae/fake-claude-plugins.zip`). Downloading and running unverified executables from untrusted sources is a critical security risk. The repository name `fake-claude-plugins` combined with this instruction raises strong suspicions of a phishing attempt or malware distribution. While the agent definitions themselves advocate for good coding practices, the overall project context is highly deceptive and unsafe.
Updated: 2026-01-19GitHub→
30
1
Low Cost
williajm icon

mcp_kafka

by williajm

Sec9

Provides AI assistants with safe, controlled access to Apache Kafka clusters using the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a running Apache Kafka cluster to connect to.
  • ⚠️Python 3.11+ is required.
  • ⚠️Write operations (creating topics, producing messages, resetting offsets) are disabled by default and must be explicitly enabled via `SAFETY_ALLOW_WRITE_OPERATIONS=true`.
  • ⚠️If OAuth/OIDC authentication is enabled (`SECURITY_OAUTH_ENABLED=true`), an external OAuth/OIDC provider and proper configuration for `SECURITY_OAUTH_ISSUER` and `SECURITY_OAUTH_AUDIENCE` are required.
Verified SafeView Analysis
The server demonstrates a strong commitment to security. It implements 2-tier access control (READ/READ_WRITE), actively protects internal Kafka topics and consumer groups, and allows for custom topic blocklists. Message size limits and consume limits are enforced. For network transports, it offers optional OAuth/OIDC authentication with JWT validation, including critical SSRF protection for JWKS URLs (blocking private IPs and dangerous hostnames). Rate limiting is available to prevent abuse. Comprehensive audit logging, with sensitive data redaction and argument truncation, is included for compliance and monitoring. Warnings are logged for potentially insecure HTTP configurations (non-localhost binding without OAuth/TLS). Sensitive credentials (e.g., SASL passwords, SSL key passwords) are handled using `SecretStr` to prevent accidental logging.
Updated: 2026-01-18GitHub→
30
1
Low Cost
Shreyas2877 icon

Troj-MCP

by Shreyas2877

Sec2

A versatile Model Context Protocol (MCP) server for integrating AI models with system operations, file management, calendar, and email tools.

Setup Requirements

  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Relies on external email and calendar services, which are expected to be running at `http://localhost:3000` by default.
  • ⚠️Using the `local_model_client.py` requires a separate local LLM (e.g., Ollama, LM Studio) to be installed and running.
Review RequiredView Analysis
The `execute_command` function in `src/macro_man/tools/system.py` uses `subprocess.run(command, shell=True)`. While it attempts to filter dangerous commands with a blacklist, this approach is fundamentally insecure and highly prone to bypass via various shell injection techniques (e.g., command substitution, encoding, alternative syntax). This allows for arbitrary code execution. Additionally, a default `SECRET_KEY` is present, which should be updated in production.
Updated: 2025-11-29GitHub→
30
1
Medium Cost
mazharenko icon

aoc-mcp

by mazharenko

Sec6

Simplifies interaction with the Advent of Code website by providing tools to get puzzle progress, submit answers, and retrieve personal puzzle inputs, enhancing the puzzle-solving workflow.

Setup Requirements

  • ⚠️Requires Docker to run
  • ⚠️Requires an Advent of Code session cookie, which is a sensitive credential and must be obtained manually from the Advent of Code website.
Review RequiredView Analysis
The server requires a sensitive Advent of Code session cookie via an environment variable. While this is the correct method for passing secrets to a Docker container, users must trust the maintainer as the underlying source code for the Docker image is not provided for audit within this context. Running any external Docker image without auditing its source code carries inherent risks, especially when handling sensitive credentials.
Updated: 2025-12-02GitHub→
30
1
Medium Cost
my-mcp-hub icon

doc-mcp-server

by my-mcp-hub

Sec6

Provides a Model Context Protocol (MCP) server that enables AI assistants and developer tools to search and retrieve documentation for the `watermark-js-plus` library.

Setup Requirements

  • ⚠️Requires Node.js 18+.
  • ⚠️Requires Internet access for documentation search functionality.
Verified SafeView Analysis
A hardcoded Algolia API key is present in the source code (src/tools/registerWatermarkJsPlus.ts). While likely for a public, read-only index, hardcoding API keys is generally a security anti-pattern. The server performs outbound `fetch` requests based on search results to retrieve content, which could pose a Server-Side Request Forgery (SSRF) risk if the Algolia index or search query leads to malicious or internal network resources.
Updated: 2026-01-14GitHub→
30
1
High Cost
SkyflowFoundry icon

sky-pii-mcp

by SkyflowFoundry

Sec9

An MCP server that integrates with Skyflow for PII/PHI de-identification and re-identification in text and files, accessible via streamable HTTP.

Setup Requirements

  • ⚠️Requires valid Skyflow credentials (bearer token via Authorization header or API key via header/query parameter).
  • ⚠️Requires Skyflow vault configuration (vaultId and vaultUrl, optionally accountId/workspaceId) via query parameters or environment variables.
  • ⚠️The 'dehydrate_file' tool has a 5MB limit for base64-encoded input files, which translates to approximately 3.75MB for original binary files due to encoding overhead.
Verified SafeView Analysis
The server demonstrates strong security practices for an integration point. It avoids hardcoded secrets by expecting credentials via environment variables or request parameters. It robustly extracts and validates the *format* of credentials (JWT bearer token vs. API key), passing them securely to the Skyflow SDK. Crucially, it creates new, isolated Skyflow SDK instances and MCP transports for each request, preventing request ID collisions and cross-request data leakage. Input payload size is limited to 5MB, mitigating certain denial-of-service vectors. No 'eval' or obfuscation is present. The only minor point for consideration is the optional fallback of API key via query parameter, which is generally less secure than header-based authentication.
Updated: 2026-01-14GitHub→
30
1
Low Cost
justifi-tech icon

mcp-server

by justifi-tech

Sec9

AI-assisted payment management through a Model Context Protocol (MCP) server, providing JustiFi payment tools for integration with AI agents and workflows.

Setup Requirements

  • ⚠️Requires Node.js 16+ and Python 3.11+
  • ⚠️Uses 'uv' for Python package management, not 'pip'
  • ⚠️Requires JUSTIFI_CLIENT_ID and JUSTIFI_CLIENT_SECRET environment variables for JustiFi API access
  • ⚠️Additional configuration (MCP_SERVER_URL, Auth0 details) required for HTTP transport with OAuth
Verified SafeView Analysis
The project demonstrates a high level of security awareness, especially for financial operations. Payment creation is strictly enforced to 'test mode' in production via API key and test card validation. Environment variables are used for all secrets. The OAuth 2.1 implementation plan outlines robust security measures including Auth0 integration, HTTPS, token validation, secure credential management (AWS Secrets Manager), network segmentation (ALB, private subnets, security groups), and input sanitization (in examples). A minor concern is the use of `spawnSync` for Python version checks in the Node.js wrapper, which executes dynamic code, but its scope is limited and low risk.
Updated: 2025-12-05GitHub→
30
1
Medium Cost
andreswebs icon

mcbox

by andreswebs

Sec8

Provides a lightweight and portable pluggable MCP (Model Context Protocol) server for AI agents to execute local tools via stdio transport.

Setup Requirements

  • ⚠️Requires Homebrew for installation (other methods unsupported currently).
  • ⚠️Requires `bash` and `jq` to be installed on the system.
  • ⚠️For development, Node.js (LTS), NPM CLI, shellcheck, and shfmt are required.
Verified SafeView Analysis
The server design emphasizes security through stdio transport and JSON schema validation of tool inputs. It uses `jq` for safe parsing of JSON arguments, mitigating common shell injection risks for core operations. However, the overall security critically depends on the custom tool implementations (`tools.bash`) provided by the user. If user-defined tools do not properly validate and sanitize their inputs, especially when calling external commands (e.g., `sqlite3` without sanitizing the query), vulnerabilities could be introduced. The documentation explicitly highlights input validation as a best practice for tool developers.
Updated: 2025-12-15GitHub→
30
1
Medium Cost
digitalsamba icon
Sec8

Manage Digital Samba video conferencing platform resources (rooms, sessions, recordings, etc.) using natural language commands via AI assistants following the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Digital Samba Developer Key for API access.
  • ⚠️A Digital Samba account is necessary to interact with the underlying video conferencing platform.
  • ⚠️Full OAuth functionality requires configuring specific environment variables (e.g., OAUTH_CLIENT_ID, OAUTH_CLIENT_SECRET).
  • ⚠️For production deployments, Redis is highly recommended for persistent session storage (via REDIS_URL) to avoid session data loss on server restarts.
Verified SafeView Analysis
The server correctly uses environment variables for sensitive data like API keys and OAuth secrets. It implements a standard OAuth 2.0 authorization code flow with PKCE for enhanced security. Session management can use Redis for persistence and better security in production, with a fallback to in-memory storage (warned about data loss on restart). CORS is broadly enabled (`Access-Control-Allow-Origin: *`), which is common for public APIs but should be noted.
Updated: 2026-01-19GitHub→
PreviousPage 236 of 760Next