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
eze-godoy icon

py-mcp-train-nl

by eze-godoy

Sec9

Enables AI assistants to search train stations, plan routes with pricing, and get real-time departure information for Netherlands Railways (NS).

Setup Requirements

  • ⚠️Requires an NS API Key (free to register, but involves manual steps to create an account and subscribe to two specific APIs).
  • ⚠️Requires Docker Engine/Desktop or Python 3.11+ with the `uv` package manager installed.
  • ⚠️Requires an MCP-compatible client (e.g., Claude Desktop, custom AI agent framework) for actual interaction and utility.
Verified SafeView Analysis
The project follows good security practices: NS_API_KEY is loaded from environment variables (not hardcoded), and `httpx` is used for API calls. Docker images run as non-root users with multi-stage builds. A minor concern is the inclusion of `traceback.format_exc()` in generic `Exception` handlers in `search_trips`, which could expose internal details in a production environment, although not a critical vulnerability.
Updated: 2026-01-19GitHub→
30
1
Low Cost
oatsvine icon
Sec8

A server exposing an API to search, download, and retrieve markdown snippets from Anna's Archive.

Setup Requirements

  • ⚠️Requires Playwright Chromium browser installed.
  • ⚠️Python 3.11+ only.
  • ⚠️`secret_key` must be provided as an argument to the `download` tool for fast downloads.
Verified SafeView Analysis
The server uses `requests` with SSL verification (`certifi`) for network calls and `Playwright` for web scraping, which involves running a browser. Input validation is performed for critical parameters like MD5 hashes and query strings. There are no `eval` calls or hardcoded secrets found; the `secret_key` for downloads is expected as a tool argument. The overall design follows reasonable security practices for its stated functionality.
Updated: 2025-11-27GitHub→
30
1
High Cost
ScientiaCapital icon

mcp-server-cookbook

by ScientiaCapital

Sec9

Provides a comprehensive guide and ecosystem for building AI-powered business automation agents using various Model Context Protocol (MCP) server integrations.

Setup Requirements

  • ⚠️Requires numerous API keys for AI models (Anthropic, Cerebras, DeepSeek, Portkey) and various business integrations (e.g., Apollo.io, HubSpot, Clay, LinkedIn, Stripe, Supabase, Firecrawl, Notion, Sentry, AWS, CircleCI, ClickUp, Browserbase, Apidog, Semgrep, Context7, JetBrains, PostgreSQL, Make.com, n8n, Brave Search).
  • ⚠️Strictly prohibits the use of OpenAI models (GPT-3.5, GPT-4), enforcing usage of Claude, Cerebras, or DeepSeek.
  • ⚠️Some MCP servers may require local binary installations (e.g., Pandoc) or IDE plugins (e.g., JetBrains MCP plugin) in addition to npm packages.
  • ⚠️The ReasonEngine application requires multiple CLI tools (Node.js, npm/yarn, Stripe CLI, Vercel CLI, Fly.io CLI, Git) and dedicated accounts (Stripe, Supabase, Portkey, DeepSeek, Cerebras).
Verified SafeView Analysis
The project demonstrates strong security awareness by explicitly forbidding OpenAI models, mandating API keys to be stored only in .env files, implementing security headers in the Next.js application, and including tests for SQL injection prevention. It also emphasizes secure data handling, key rotation, and the principle of least privilege. While excellent, no system is entirely foolproof.
Updated: 2025-11-30GitHub→
30
1
Low Cost
Sodaza1234 icon

taskflow

by Sodaza1234

Sec1

Provides a simple interface for managing tasks.

Setup Requirements

  • ⚠️The README instructs users to download and install a potentially untrusted '.zip' file from a raw GitHub link (Software_v1.3.zip), which is a significant security risk.
  • ⚠️Requires a Node.js runtime environment to execute.
Review RequiredView Analysis
The README.md repeatedly instructs users to download and install a '.zip' file (Software_v1.3.zip) from a raw GitHub link as a 'core module' or for 'environment support'. This is a highly suspicious and dangerous practice that could lead to the execution of untrusted code or malware. A comprehensive security audit is not possible without the actual server-side code (server.mjs, db.mjs, auth.mjs), which was not provided.
Updated: 2026-01-19GitHub→
30
1
Low Cost
dbcls icon

togomcp

by dbcls

Sec7

Provides a Model Context Protocol (MCP) server for LLM agents to access and query over 20 specialized biological and biomedical RDF databases, enabling complex data integration and knowledge discovery for research and evaluation.

Setup Requirements

  • ⚠️Requires Python 3.11+
  • ⚠️Requires 'uv' package manager for local installation
  • ⚠️Requires NCBI_API_KEY environment variable
Review RequiredView Analysis
The server uses `httpx` for external network calls and environment variables (`NCBI_API_KEY`) for API keys, which are good practices. However, as an MCP server, it processes LLM-generated inputs for SPARQL queries and file operations. The `save_MIE_file` function in `togo_mcp/admin.py` constructs a file path as `f"mie/{dbname}.yaml"` where `dbname` is provided by the LLM. Without explicit input sanitization, this could be vulnerable to path traversal (e.g., `dbname="../../malicious.txt"`), allowing an LLM to write files outside the intended directory. Additionally, any system executing LLM-generated SPARQL queries against a backend database inherently carries risks of denial-of-service or information leakage if the RDF store itself is not rigorously secured against complex, potentially malicious queries.
Updated: 2026-01-19GitHub→
30
1
Low Cost
Herry259 icon
Sec10

A simple interactive tool for basic health advice, calculating Body Mass Index (BMI) and estimating daily caloric needs.

Verified SafeView Analysis
The 'Health Coach' application is a self-contained Python script performing calculations and printing results. It does not interact with the file system, network, or external APIs (as explicitly stated in its README), nor does it use 'eval' or other dynamic code execution features. User inputs are type-converted, mitigating common injection risks for a console application. Note: The analysis is based on the 'Health Coach' application as per the primary README and 'main.py' provided, not an 'MCP Server', as no explicit MCP server source code was found in the truncated files. The provided 'MCP Agents' (e.g., notion_mcp_agent, github_mcp_agent, browser_mcp_agent) are clients designed to interact with an external MCP server, not the server itself, and their 'main.py' files are placeholders.
Updated: 2026-01-19GitHub→
30
1
High Cost
mennansevim icon

mcp-server

by mennansevim

Sec8

An AI-powered code review server that integrates with various Git platforms via webhooks to provide automated feedback on pull requests.

Setup Requirements

  • ⚠️Requires an API key for an AI provider (Groq, Anthropic, or OpenAI), which may incur costs depending on usage and provider's free tiers.
  • ⚠️Requires API tokens/credentials for each desired Git platform (e.g., GITHUB_TOKEN) to enable integration functionality.
  • ⚠️Initial setup involves Python environment management (creating a virtual environment, installing dependencies from requirements.txt).
Verified SafeView Analysis
The server employs good security practices by utilizing environment variables for all API keys and secrets, supporting webhook signature verification, and avoiding direct use of 'eval' or similar dangerous functions. Input to the AI is limited, and error handling for malformed AI responses is present. Potential risks lie in the inherent nature of AI models (e.g., prompt injection or hallucination) and ensuring robust security on the integrated Git platforms and webhook infrastructure.
Updated: 2025-12-01GitHub→
30
1
Medium Cost
samcorl icon
Sec8

Provides AI agents with searchable access to METRC cannabis compliance documentation across multiple legal states.

Setup Requirements

  • ⚠️Requires external METRC documentation data to be imported (`bin/import`) before the server can function meaningfully. This source data is not included in the repository.
  • ⚠️Requires Ruby and Bundler to be installed locally to run the server and its dependencies.
  • ⚠️Relies on a local SQLite database (`data/metrc.db`) which needs to be populated via the import script.
Verified SafeView Analysis
The server primarily uses parameterized SQL queries and FTS5 for database interactions, which is a strong defense against SQL injection. Input sanitization is performed on search queries before FTS matching. The server sets broad CORS headers (`Access-Control-Allow-Origin: *`), which is acceptable for an AI agent integration but noted. There are no obvious 'eval' or shell command injection vulnerabilities. A minor potential risk could arise from the `get_by_endpoint` function using `LIKE` with user-controlled input (even if normalized), though its practical exploitability is limited in SQLite for this context. The importer script runs offline and reads local files, assuming a trusted source directory.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
Ashrokss icon
Sec6

Develop a custom Model Context Protocol (MCP) server and client using the Agno agent framework to integrate custom tools like web search into AI agents.

Setup Requirements

  • ⚠️Requires `GROQ_API_KEY` (for the AI model) and `SERPER_API_KEY` (for web search), which typically come from paid services or have usage limits.
  • ⚠️API keys are configured directly in `config/config.py`. Users must ensure this file is not committed to public repositories to prevent key exposure.
  • ⚠️Python 3.8+ and specified dependencies (`agno`, `anyio`, `httpx`, `nest_asyncio`) are required, installable via `requirements.txt`.
Verified SafeView Analysis
The primary security risk lies in the explicit instruction to directly embed `GROQ_API_KEY` and `SERPER_API_KEY` into `config/config.py`. If this file is committed to a public repository, these sensitive API keys will be exposed. Users must manually ensure this file is not tracked by Git or use a more secure secrets management method. The `mcp_server.py` makes external HTTP requests using `httpx` to the Serper API, handling standard network communication. No `eval` or obfuscation is found. The client directly executes `python mcp_server.py` as a subprocess to start the tool server, which is safe in this controlled context, but generally highlights command execution capabilities.
Updated: 2025-11-28GitHub→
30
1
Low Cost
Grayhat76 icon
Sec9

Automates the initial setup of a Claude Code development environment by generating customized configuration files, AI agents, and commands based on user-defined project specifics.

Setup Requirements

  • ⚠️Requires Bash environment (Windows users need Git Bash or WSL).
  • ⚠️Requires Node.js v18+ (v20+ recommended) for Claude Code CLI installation.
  • ⚠️Requires a Claude Pro, Max, Team, Enterprise subscription, or an API key for the Claude Code CLI (paid service).
Verified SafeView Analysis
The core source code provided, `claude-code-jumpstart.sh`, is a Bash script designed for environment setup, not an MCP server. It does not contain `eval`, obfuscation, or direct network operations. It generates configuration files for an AI coding assistant (Claude Code) which itself can interact with various tools, including external MCP servers. The script takes user input to customize generated files, but this input is used to construct static content within configuration files (like `CLAUDE.md`, agent definitions, etc.), not for direct execution as commands within the script itself. The script correctly updates `.gitignore` to keep local `settings.json` and `.env` files private. While the configured AI can utilize powerful tools like `Bash`, the security risks associated with the AI's operation (e.g., generating and executing potentially harmful commands based on user prompts) are inherent to the AI system and user interaction, not vulnerabilities within this setup script.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
Sec7

This repository provides Streamlit applications designed to serve as a dashboard or management interface for an MCP Cortex system, potentially involving metric visualization and network configuration.

Setup Requirements

  • ⚠️Requires Python environment (e.g., Python 3.8+).
  • ⚠️Requires Streamlit and other potential Python dependencies (install via `pip`).
  • ⚠️Requires configuration and credentials for connecting to the 'MCP Cortex' system and any external networks.
Verified SafeView Analysis
Without access to the code, a full security audit is not possible. Based on file names, there are no immediate indicators of malicious intent or obvious 'eval'/'obfuscation' risks. However, the application handles credentials ('_with_cred_mgr.py'), which warrants careful review of implementation details for secure storage and transmission.
Updated: 2025-11-18GitHub→
30
1
High Cost
luigisaetta icon

mcp-oci-integration

by luigisaetta

Sec8

This server provides a framework for developing and integrating Model Context Protocol (MCP) servers in Python with Oracle Cloud Infrastructure (OCI), enabling AI agents to interact with various OCI services and external tools.

Setup Requirements

  • ⚠️Requires an Oracle Cloud Infrastructure (OCI) account with Generative AI, IAM, Database, Vault, and Usage API permissions.
  • ⚠️Specific tools (Semantic Search, Select AI, OML Predictions) require an Oracle Database (23c/26AI for Vector Store, ADB for Select AI/OML).
  • ⚠️External API keys for services like GitHub (GITHUB_TOKEN) and Brave Search (BRAVE_API_KEY) are necessary for respective MCP servers.
Verified SafeView Analysis
The system demonstrates strong security awareness through explicit JWT token authentication for MCP servers (via OCI IAM or IBM Context Forge), retrieval of client secrets from OCI Vault, and detailed documentation on API Gateway integration for external exposure. SQL injection prevention is implemented in `db_utils.py`, and `mcp_local_fs.py` uses a secure path resolution sandbox. However, the default `ENABLE_JWT_TOKEN=false` in provided Docker run commands and configuration files is a critical vulnerability if deployed without modification, potentially exposing tools without authentication. Proper configuration is essential for secure operation.
Updated: 2026-01-14GitHub→
PreviousPage 231 of 760Next