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
ArshavirH icon

k_base

by ArshavirH

Sec8

A persistent, semantic memory layer for AI agents and human teams to store, retrieve, and evolve project context over time.

Setup Requirements

  • ⚠️Requires Java 21
  • ⚠️Requires Docker and Docker Compose for local PostgreSQL with pgvector
  • ⚠️Requires OpenAI API Key (Paid service for embeddings)
  • ⚠️Requires Node.js for MCP Inspector if testing via 'npx'
Verified SafeView Analysis
The application uses Spring Boot's `@Valid` for input validation. Database credentials for local setup are hardcoded in `application.yaml` and `docker-compose.yaml` (username: postgres, password: user123), which are expected for development but should be externalized for production. CORS is wide open by default (`allowedOriginPatterns("*")`) which is generally not recommended for production. Filter expressions in `KnowledgeQueryService` use string escaping (`s.replace("'", "''")`) for project codes and tags, which is an effort to prevent injection but relies on the underlying `PgVectorStore` to correctly parameterize queries.
Updated: 2025-11-29GitHub→
0
0
Medium Cost
kiket-dev icon

kiket-mcp-server

by kiket-dev

Sec2

Provides AI tools to interact with Kiket issues, comments, projects, and users, enabling AI assistants to manage Kiket programmatically via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires `KIKET_API_URL` and `KIKET_API_KEY` to be set as environment variables.
  • ⚠️Requires a running Kiket instance for API interactions.
  • ⚠️Setting `KIKET_VERIFY_SSL=false` can pose a security risk in production by disabling SSL certificate validation.
Review RequiredView Analysis
The `start-server.sh` script, part of the provided source, contains a hardcoded `KIKET_API_KEY`. This is a critical security vulnerability as it directly exposes sensitive credentials within the repository. Additionally, the `KIKET_VERIFY_SSL` environment variable can be set to `false`, which disables TLS/SSL certificate verification and can make the server vulnerable to man-in-the-middle attacks if used in a production environment.
Updated: 2025-12-13GitHub→
0
0
Low Cost
AyushSingh7404 icon

test-remote-server-mcp

by AyushSingh7404

Sec9

An HTTP server for tracking personal expenses, allowing users to add, list, and summarize financial transactions through an API.

Setup Requirements

  • ⚠️Requires Python 3.13+ as specified in pyproject.toml.
  • ⚠️Expense data stored in expenses.db within a temporary directory (tempfile.gettempdir()) may not persist across server or system restarts.
  • ⚠️Requires 'fastmcp' and 'aiosqlite' libraries to be installed, typically handled by 'uv' or 'pip'.
Verified SafeView Analysis
The code uses parameterized queries, effectively preventing SQL injection. No hardcoded secrets or dangerous functions like 'eval' are present. Error messages could be more generalized to prevent potential information leakage in a high-security context, but for a simple expense tracker, this is a minor concern. The use of tempfile.gettempdir() for the database path means data persistence might be an issue across server/system restarts, which is a functional rather than a direct security vulnerability.
Updated: 2025-11-19GitHub→
0
0
High Cost
wstone0011 icon

my_gdb_mcp_server

by wstone0011

Sec1

Enables AI models to interact with GDB for automated debugging and code analysis by exposing GDB operations and system shell commands via an MCP server.

Setup Requirements

  • ⚠️Requires Python 3.12+
  • ⚠️Requires fastmcp library
  • ⚠️Requires pexpect library
Review RequiredView Analysis
CRITICAL VULNERABILITY: The `run_shell_command` tool allows arbitrary system shell commands to be executed with `subprocess.run(command, shell=True)` without sanitization. Additionally, the `start_debugging` tool allows arbitrary commands to be passed to `pexpect.spawn`. Since the server binds to `0.0.0.0:8000`, any entity with network access to the server can execute arbitrary code on the host system. This poses an extreme risk of remote code execution (RCE) if exposed. The `command` parameters for these tools are directly sourced from user/model input without proper validation or sanitization.
Updated: 2025-11-26GitHub→
0
0
Low Cost
Xioto-ytb icon
Sec8

An MCP server acting as an adapter for a Minesweeper game, enabling an agent to interact with the game via defined tools.

Setup Requirements

  • ⚠️Requires a separate Minesweeper game server to be running on `http://localhost:5000`.
Verified SafeView Analysis
The server itself uses numeric inputs for coordinates ('row', 'col') and constructs URLs to a local game server safely. There is no direct 'eval' or obvious malicious patterns found in the provided code. However, the server relies on an external, unprovided HTTP server running on `http://localhost:5000` to handle game logic and image generation. The security of the overall system is dependent on this external component, which is outside the scope of this repository's code.
Updated: 2026-01-19GitHub→
0
0
Low Cost

mcp-taskwarrior-ai

by storypixel

Sec6

Provides an AI-native bridge for Taskwarrior, enabling natural language task management, context awareness, and integration with ticket systems for AI agents like Claude Code.

Setup Requirements

  • ⚠️Requires Taskwarrior to be installed and initialized ('task version').
  • ⚠️Requires Node.js v20 or later to be installed.
  • ⚠️The project must be built using `npm run build` before deployment, as the Claude Code configuration points to the compiled JavaScript in the `dist` directory.
  • ⚠️The Claude Code `mcpServers` configuration requires the absolute path to the `dist/index.js` file.
Verified SafeView Analysis
The server executes local Taskwarrior commands based on AI input. The `task_raw` tool allows for direct execution of arbitrary Taskwarrior commands, which could be a command injection risk if the AI's output is not strictly validated or if used in an untrusted environment. The natural language processing for `task_natural` also requires robust sanitization to prevent shell injection, though no explicit 'eval' or network risks beyond local command execution are apparent. It reads local project and ticket-related files.
Updated: 2025-11-17GitHub→
0
0
Low Cost
Harryc6 icon

ProxmoxMCP

by Harryc6

Sec9

The Proxmox MCP server provides read-only access to Proxmox cluster, guest, and storage information for agents to update documentation and monitoring systems.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️Requires a Proxmox API token with read-only permissions.
  • ⚠️The environment variables PROXMOX_API_URL, PROXMOX_API_TOKEN_ID, and PROXMOX_API_TOKEN_SECRET must be set.
  • ⚠️If Proxmox uses a self-signed TLS certificate, PROXMOX_TLS_INSECURE=1 must be set, which bypasses TLS verification.
Verified SafeView Analysis
The server is designed to be read-only, connecting to Proxmox via a dedicated API token with limited (e.g., PVEAuditor) permissions, which is a strong security practice. Secrets are handled via environment variables, preventing hardcoding. The `PROXMOX_TLS_INSECURE` flag allows bypassing TLS verification for self-signed certificates, which is noted in the README as a potential security risk if misused but provides flexibility for lab environments. No 'eval' or direct arbitrary code execution patterns are observed.
Updated: 2025-12-10GitHub→
0
0
Low Cost
ghaidaa-24 icon

stocks-mcp

by ghaidaa-24

Sec9

Access comprehensive stock market data and analysis tools, optimized for LLMs, including technical analysis, screeners, pivot points, and support for Turkish stocks.

Setup Requirements

  • ⚠️Requires Node.js version 18.0.0 or higher.
  • ⚠️Relies on Yahoo Finance data, which may be subject to rate limits or API changes that could affect data availability or accuracy.
Verified SafeView Analysis
The server utilizes the `yahoo-finance2` library for data retrieval, which handles external API interactions. Input arguments for tools are validated by schema types and simple checks (e.g., `count` parameter is capped at 50). A `getTicker` helper provides basic sanitization for stock symbols, including auto-detection for BIST tickers. No direct use of `eval`, obfuscation, or hardcoded secrets were identified in the provided source code. The `@ts-ignore` for suppressing a Yahoo survey notice is not a security concern.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
kairapavan icon
Sec9

Provides National Provider Identifier (NPI) data as an external tool for integration with Spring AI applications.

Setup Requirements

  • ⚠️Requires Java Development Kit (JDK) to build and run.
  • ⚠️The 'national_provider_identifier.json' file must be present at 'src/main/resources/static/' for successful application startup.
  • ⚠️The application will fail to start due to a JSON parsing error if any 'BigInteger' field in the 'Npi' record (e.g., Npi, Entity_Type_Code, Postal_Code, Telephone_Number, Fax_Number) corresponds to an empty string ('""') in the 'national_provider_identifier.json' file.
Verified SafeView Analysis
The code primarily loads and exposes static NPI data. No dynamic code execution (like 'eval') or obvious malicious patterns were found. No hardcoded secrets are present. The NPI data itself is publicly available, so exposing it via a tool is not a direct security risk, assuming appropriate access controls are implemented at the consuming Spring AI application level.
Updated: 2025-12-03GitHub→
0
0
High Cost
jonathanjacka icon

agent-trading-platform

by jonathanjacka

Sec8

An autonomous AI-powered stock trading platform featuring multiple AI agents with distinct trading strategies for researching markets, making trading decisions, and learning from experiences.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid service)
  • ⚠️Requires Polygon.io API Key (Paid service, Starter tier is 15-min delayed)
  • ⚠️Requires Brave Search API Key (Paid service)
  • ⚠️Requires Anthropic API Key (Paid service, implied for ConsultantAgent via AI SDK)
  • ⚠️API_SECRET environment variable is crucial for protecting server endpoints in production; otherwise, they are publicly accessible.
Verified SafeView Analysis
The application uses environment variables for all API keys and secrets, which is good practice. API key authentication is implemented for protected endpoints, and rate limiting is in place for expensive operations like AI trades. Global error handling suppresses detailed stack traces in production. A critical security note is that API_SECRET authentication is disabled if the environment variable is not configured, which could lead to unprotected endpoints in a production environment if overlooked.
Updated: 2025-12-24GitHub→
0
0
Medium Cost
clydewatts1 icon

prototype_chameleon

by clydewatts1

Sec7

A dynamic, self-modifying MCP server enabling autonomous AI agents to evolve their capabilities at runtime through database-backed tool, resource, and prompt management, complemented by an AI-powered debugger.

Setup Requirements

  • ⚠️Requires Python 3.12+.
  • ⚠️LLM integration for the client debugger (e.g., Google Gemini or Ollama) requires an API key or a locally running Ollama server, respectively.
  • ⚠️Using the SSE transport for the server requires installing additional Python packages: 'uvicorn' and 'starlette'.
Review RequiredView Analysis
The server uses `exec()` to dynamically run code from the database, which is an inherent high-risk operation allowing arbitrary code execution. This risk is extensively mitigated by: AST-based validation for Python code to block dangerous imports/functions (e.g., `subprocess`, `eval`, `os.system`); `sqlglot` AST parsing for mathematically verified read-only SQL queries and single-statement validation; SHA-256 hash integrity checks for all code; and a database-driven, configurable security policy system. Advanced data tools (e.g., `general_merge_tool` for upserts, `execute_ddl_tool` for schema changes) are provided but include robust input validation, require explicit confirmation for DDL, and leverage SQLAlchemy's secure parameter binding. The project's documentation transparently acknowledges these security implications and strongly advises additional OS-level sandboxing (e.g., Docker, VMs) for production environments with untrusted code. Hardcoded API keys are avoided, relying on environment variables or configuration files.
Updated: 2026-01-19GitHub→
0
0
Low Cost
LuluBeatson icon

mcp-test-repo-nov24

by LuluBeatson

Sec10

This repository serves as a test bed for an MCP server, designed to validate the functionality of 18 associated tools.

Verified SafeView Analysis
The provided source code consists only of a README.md file. This file contains no executable logic, sensitive information, or patterns like 'eval', obfuscation, or network calls. Therefore, no security risks are identifiable within the provided content. A comprehensive security audit of the actual MCP server or its tools would require their full source code, which is not provided.
Updated: 2025-11-24GitHub→
PreviousPage 318 of 760Next