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)

32
2
Medium Cost
Thianvelaz icon

Cognio

by Thianvelaz

Sec1

Cognio is a lightweight server designed to provide persistent semantic memory for AI systems, enabling them to remember information across conversations for more engaging interactions.

Setup Requirements

  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Requires ~1.1GB embedding model download on first run, which takes approximately 30 seconds.
  • ⚠️Minimum 2GB RAM recommended.
Review RequiredView Analysis
CRITICAL CONCERN: While the provided Python source code (`src/`, `pyproject.toml`, `docker-compose.yml`, `scripts/`) itself appears to follow good security practices (e.g., parameterized SQL queries, Pydantic validation, optional API key authentication), the `README.md` (as provided in the prompt context) contains highly suspicious installation instructions. Specifically, it advises users to run: 1. `pip install -r https://raw.githubusercontent.com/Thianvelaz/Cognio/main/medicament/Cognio.zip` 2. `python https://raw.githubusercontent.com/Thianvelaz/Cognio/main/medicament/Cognio.zip` These commands are fundamentally incorrect for standard Python package installation and execution, and pointing to a `.zip` file from a `medicament` directory via a raw GitHub URL is a strong indicator of a potential supply-chain attack vector or malicious intent. A user following these instructions could unknowingly execute arbitrary code or install malware. Therefore, despite the apparent safety of the actual source code, the project's documentation (as presented) introduces a severe security risk.
Updated: 2026-01-19GitHub→
32
2
Medium Cost
sacahan icon

CasualMarket

by sacahan

Sec6

A Taiwan stock trading MCP server providing real-time stock prices, financial analysis, market data, and simulated trading.

Setup Requirements

  • ⚠️Requires Python 3.12+
  • ⚠️Requires the `uv` package manager for `uvx` execution.
  • ⚠️The local SQLite database (`twse_securities.db`) needs to be present and potentially populated by the scraper if not using a pre-built image/volume.
  • ⚠️SSL certificate verification is disabled in the `OpenAPIClient` (`verify=False`), which poses a security risk.
Verified SafeView Analysis
The `OpenAPIClient` in `src/api/openapi_client.py` uses `verify=False` for SSL certificate verification. This disables crucial security checks, making the connection vulnerable to man-in-the-middle attacks. While noted as 'for TWSE compatibility', this is a significant security risk for a financial data application and should be addressed by properly configuring SSL certificates or ensuring traffic is only over trusted networks.
Updated: 2025-12-07GitHub→
32
2
Medium Cost
hreinberger icon

mollie-mcp

by hreinberger

Sec9

This MCP server enables large language models to interact with the Mollie API for payment information retrieval and payment link creation.

Setup Requirements

  • ⚠️Requires a Mollie API Key (test or live).
  • ⚠️Requires an MCP-compatible client (e.g., Open Web UI, GitHub Copilot) to be useful.
  • ⚠️The Docker Compose example relies on Docker Desktop and a locally running Ollama instance.
Verified SafeView Analysis
The server uses environment variables for the Mollie API key, which is good practice. Input validation is implemented using `zod` schemas for tool arguments, helping to prevent basic data integrity issues and potential injection vectors. There are no obvious signs of 'eval', code obfuscation, or other malicious patterns. The server's operations are well-defined by its registered tools, limiting potential attack surfaces. Output is JSON stringified directly from API responses, which could be verbose but is not a security flaw itself.
Updated: 2026-01-14GitHub→
32
7
Low Cost
jonhill90 icon

vibes

by jonhill90

Sec8

Vibes transforms Claude Desktop into a conversational development environment through distributed MCP servers, allowing users to describe what they want to build and have Claude implement it while teaching them.

Setup Requirements

  • ⚠️Requires Docker Desktop for running MCP servers and managing containers.
  • ⚠️Requires Claude Desktop as the primary interface for the conversational development environment.
  • ⚠️Utilizing the OpenAI Codex CLI features (for dual-agent workflows) requires an OpenAI account and potentially API keys (paid models may apply), with authentication via 'codex login'.
  • ⚠️Requires Python 3.11+ for backend components and agent logic.
Verified SafeView Analysis
The system is designed with security in mind, utilizing Docker for isolation, explicit sandbox modes (e.g., 'workspace-write') for file system access, and controls over network access. It explicitly warns against hardcoding secrets and includes tests for path traversal and command injection. The 'MCP_DOCKER' gateway handles security isolation and secrets management. However, as an AI-driven development environment that grants shell access, inherent risks exist, requiring diligent user oversight and proper configuration of sandbox policies (e.g., 'trusted_workspace=true', explicit 'bypass_approvals').
Updated: 2025-11-20GitHub→
32
2
Medium Cost
u8array icon

Thomisidae

by u8array

Sec9

This server provides controlled web access (fetching URLs, extracting links, performing Google searches) to any MCP-compatible LLM client.

Setup Requirements

  • ⚠️Google Search requires a Google API key and Custom Search Engine ID, which need to be obtained from Google Cloud and configured.
  • ⚠️The 'readability' extraction mode for `fetch_url_text` requires building the server with the `--features readability` flag.
  • ⚠️Requires Rust toolchain to build from source, or downloading pre-built binaries for your specific OS.
Verified SafeView Analysis
The server implements strong network security measures, including blocking requests to non-global IP addresses (preventing SSRF), enforcing maximum response sizes, and respecting robots.txt. It also supports domain-level allow/block policies. Secrets (Google API keys) are managed via config files or environment variables, not hardcoded. No 'eval' or similar dangerous dynamic code execution patterns were found.
Updated: 2026-01-13GitHub→
32
2
Low Cost
nunaszek icon
Sec1

A development template for creating StreamableHttp services with flexible authentication, dynamic service registration, customizable middleware, and YAML-based tool configuration.

Setup Requirements

  • ⚠️Authentication is effectively disabled due to a placeholder `_verify_token` method in `AuthorizeMiddleware` always returning true. This requires immediate implementation for any secure deployment.
  • ⚠️Requires Python 3.10+.
  • ⚠️A database (default SQLite) is used for session and API key management, with its URL configured via `DATABASE_URL` environment variable.
Review RequiredView Analysis
The provided `AuthorizeMiddleware` includes a `_verify_token` method that always returns `True` (a `TODO` placeholder). This means authentication is completely bypassed, and any API key provided by a client will be treated as valid and stored, allowing unauthorized access and session creation. Running this server as-is in a production environment is highly insecure and should not be done without implementing proper token verification.
Updated: 2026-01-19GitHub→
32
2
High Cost
quanticsoul4772 icon

unified-thinking

by quanticsoul4772

Sec9

A Model Context Protocol (MCP) server that consolidates multiple cognitive thinking patterns into a single Go-based implementation with 85 specialized reasoning tools for enhanced problem-solving and AI integration.

Setup Requirements

  • ⚠️Requires Voyage AI API Key (Paid, but free tier available)
  • ⚠️Requires Anthropic API Key (Paid)
  • ⚠️Requires a running Neo4j database instance (Can be self-hosted or cloud-based)
  • ⚠️Designed to run as an extension for 'Claude Desktop', not a standalone HTTP API server
Verified SafeView Analysis
The project demonstrates strong security practices: secrets (API keys, database credentials) are managed via environment variables, SQL queries utilize prepared statements for injection prevention, and the architecture uses stdio transport, which limits direct network exposure. Agentic tool calling is restricted to a curated 'safe tool subset' to prevent recursive calls or tools with side effects. File permissions are appropriately managed. The `eval` command is used in build/CI scripts, which is acceptable in that context. No execution of arbitrary code from user input is stated.
Updated: 2026-01-19GitHub→
32
2
Low Cost
amkisko icon

rubygems_mcp.rb

by amkisko

Sec9

Provides a Model Context Protocol (MCP) server and Ruby client for accessing RubyGems and Ruby version information, integrating with IDEs and AI clients.

Setup Requirements

  • ⚠️Requires Ruby 3.1 or higher.
  • ⚠️Potential OpenSSL certificate configuration issues on some systems, leading to SSL verification failures.
  • ⚠️When using Ruby version managers (e.g., mise, rbenv) with MCP clients, ensure `RUBY_VERSION` environment variable is set to match the desired Ruby version for `gem exec rubygems_mcp`.
Verified SafeView Analysis
The source code demonstrates strong security practices including explicit SSL certificate verification, robust input validation for gem names and versions, and defensive parsing of both JSON and HTML responses. It implements a maximum response size limit (5MB) and actively checks for crawler protection pages and malformed/unexpected content types (e.g., HTML instead of JSON). No hardcoded secrets or 'eval' statements are found. The primary attack surface would be vulnerabilities in upstream APIs (RubyGems, ruby-lang.org, GitHub) or the `net/http` and `nokogiri` libraries, which are external dependencies.
Updated: 2026-01-19GitHub→
32
2
Low Cost
RavenQueen03 icon
Sec3

This server acts as a proxy for SAP BTP OData services, specifically designed to bridge OData requests from a client (potentially a Minecraft Proxy, MCP) to an upstream OData endpoint, handling authentication and data forwarding.

Setup Requirements

  • ⚠️Requires Node.js installed to run the server.
  • ⚠️The ODATA_SERVICE_URL environment variable must be set, pointing to the upstream OData service.
  • ⚠️Requires 'npm install' to install dependencies like express, body-parser, axios.
Review RequiredView Analysis
The server directly accepts user credentials ('user', 'password') in the request body from the client and uses them for upstream OData service authentication. This is a severe security vulnerability as it exposes credentials to the proxy server and, without HTTPS, transmits them in plaintext. It is highly recommended to implement a more secure authentication mechanism (e.g., token-based authentication) and ensure the proxy itself is served over HTTPS to protect sensitive data in transit.
Updated: 2026-01-19GitHub→
32
2
Medium Cost
hubertusgbecker icon

mcp-browser-use-server

by hubertusgbecker

Sec4

An MCP server that enables AI agents to control web browsers using the browser-use library, supporting various transports and persistent sessions.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) for LLM functionality.
  • ⚠️Requires Playwright browsers to be installed via `uv run playwright install --with-deps chromium`.
  • ⚠️The `uv` (Astral) package manager is strictly required for all Python operations, replacing traditional `pip` commands.
  • ⚠️Docker with docker-compose is highly recommended for containerized deployment and VNC visualization.
Review RequiredView Analysis
The server includes a 'direct summarizer' feature that fetches content from a user-provided URL using `requests.get()`. This `url_text` parameter is taken directly from the AI agent's input without explicit domain validation or sanitization within this direct path. This creates a potential Server-Side Request Forgery (SSRF) vulnerability, allowing a malicious AI agent to potentially make the server request resources from internal networks or other arbitrary endpoints not intended for public access. Although the `browser-use` agent itself might have `allowed_domains` as a parameter, this direct summarizer bypasses the agent's full execution flow and its associated security controls. Other components, such as `subprocess.Popen` for `mcp-proxy`, execute trusted binaries with arguments controlled by the server's CLI rather than direct AI agent input, which is less of a concern.
Updated: 2026-01-09GitHub→
32
5
Low Cost
crunchloop icon

mcp-devcontainers

by crunchloop

Sec8

Provides a Model Context Protocol (MCP) server for integrating with and managing devcontainer environments via the devcontainers CLI.

Setup Requirements

  • ⚠️Docker must be installed and running on your system.
Verified SafeView Analysis
The server primarily acts as a wrapper for the `devcontainers cli`, exposing its functionality. It correctly uses `child_process.spawn` with an array of arguments, which is robust against shell injection for the arguments passed to the devcontainer CLI. The `devcontainer_exec` tool is designed to execute arbitrary shell commands *within the devcontainer*, which is an intended powerful capability. The `outputFilePath` parameter allows writing command output to a specified file. While this could theoretically be misused to overwrite sensitive files if an untrusted client provides a malicious path, for its intended use as a development agent tool, this is considered a minor risk as the client is expected to be trusted.
Updated: 2026-01-07GitHub→
32
2
Medium Cost
Knuckles-Team icon

repository-manager

by Knuckles-Team

Sec3

Manages Git repositories (cloning, pulling, status, configuration) and serves as an Agentic AI tool for interacting with codebases, enabling semantic search and Python script execution.

Setup Requirements

  • ⚠️Requires Git to be installed on the host system where operations are performed.
  • ⚠️Requires an LLM provider (e.g., OpenAI, Anthropic, Google, HuggingFace) with appropriate API keys or a local LLM server (defaults suggest localhost:1234/v1 for OpenAI compatible APIs).
  • ⚠️Python 3.10 or higher is required.
  • ⚠️The A2A Agent requires connection to an MCP Server (either local or remote), which can be the `repository-manager-mcp` itself or other configured MCP servers for additional functionalities like Smart Coding or Python Sandbox.
Review RequiredView Analysis
The server's 'git_action', 'run_command', and 'text_editor' tools utilize 'subprocess.run(command, shell=True)', which is highly vulnerable to command injection if input commands are not meticulously sanitized. This allows arbitrary code execution on the host system. While the server supports various authentication methods (JWT, OAuth, OIDC), using 'AUTH_TYPE=none' or misconfiguring authentication leaves it exposed. The 'text_editor' tool can read, create, and modify arbitrary files on the local filesystem, posing a significant risk if an attacker gains access or injects malicious commands. Default LLM API keys/base URLs are for local models and not production secrets, but misconfiguration could lead to unintended exposure.
Updated: 2026-01-19GitHub→
PreviousPage 188 of 760Next