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
bugzy-ai icon
Sec9

This server integrates Azure DevOps Work Item Tracking with AI assistants like Claude, enabling them to search, create, update, and manage work items.

Setup Requirements

  • ⚠️Requires Azure DevOps organization URL (`AZURE_DEVOPS_ORG_URL`) to be set as an environment variable.
  • ⚠️Requires an Azure DevOps Personal Access Token (`AZURE_DEVOPS_PAT`) with `vso.work` and `vso.work_write` scopes to be set as an environment variable.
  • ⚠️Requires Node.js version 20.0.0 or higher.
Verified SafeView Analysis
Configuration relies on `AZURE_DEVOPS_PAT` environment variable, which is a sensitive credential. The `AzureDevOpsClient` includes `sanitizeForLog` to redact sensitive information (like PATs) from debug logs, which is a good security practice. The implementation includes retry logic and timeout handling for network requests. No 'eval' or obvious obfuscation detected. Network requests are made to the configured Azure DevOps URL.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
masa061580 icon
Sec8

Integrates PubMed and CiNii Research APIs to provide a unified search and retrieval service for academic literature (English and Japanese) via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires NCBI API Key (optional but recommended for higher rate limits).
  • ⚠️Requires CiNii APP ID for Japanese literature search functionality (usage limited to academic research purposes).
  • ⚠️Standard Python 3 environment and pip dependencies are needed.
Verified SafeView Analysis
API keys are loaded from environment variables, which is a good practice. Rate limiting is implemented for external API calls. XML parsing is used but from trusted external sources (NCBI). The `download_pdfs` tool allows specifying an `output_dir`, which could be a minor risk in a highly untrusted multi-user environment if the LLM were to hallucinate a malicious path, but for typical LLM integration, it's generally considered acceptable.
Updated: 2025-11-26GitHub→
0
0
High Cost

hakan-personal-mcp

by sudohakan

Sec3

A self-healing and self-improving multi-agent AI system designed to manage GitBook documentation, Postman collections, perform database and system operations, cross-instance monitoring, and automatic GitHub backups.

Setup Requirements

  • ⚠️Requires a local Ollama instance running or external OpenAI/Anthropic API keys.
  • ⚠️System Optimization tools require Windows with Administrator privileges and specific local PowerShell scripts.
  • ⚠️Database tools require corresponding database servers (PostgreSQL, MySQL, MSSQL, SQLite) to be accessible.
Review RequiredView Analysis
The server features extensive use of `execAsync` and `spawn` for executing shell commands and external processes, including database backups/restores (`pg_dump`, `mysqldump`), system commands (`robocopy`, `npm build`, `git`), and even arbitrary process spawning for inter-MCP communication (`mcp_connect`). Many of these commands directly interpolate AI-generated or user-provided input, creating a significant risk for command injection if input is not perfectly sanitized. The `systemOptimizationTools` explicitly elevate privileges (`runAsAdmin`) to perform powerful system modifications, which is a high risk if compromised. While self-improvement has `restrictedPaths` and an 'approval workflow' as mitigations, the overall design grants high operational power, making it critically important to run in an isolated environment with trusted inputs.
Updated: 2025-11-28GitHub→
0
0
Low Cost
haman211fsdfsd icon
Sec8

Deploying a remote Model Context Protocol (MCP) server on Cloudflare Workers, providing calculator tools without requiring authentication, primarily for demonstration and integration with clients like Cloudflare AI Playground or Claude Desktop.

Setup Requirements

  • ⚠️Requires a Cloudflare account for deployment to Cloudflare Workers.
  • ⚠️Requires the Cloudflare Wrangler CLI (`wrangler`) to be installed and configured for deployment or local development.
  • ⚠️For connecting local MCP clients (e.g., Claude Desktop), the `mcp-remote` npm package needs to be installed and used as a proxy.
Verified SafeView Analysis
The provided source code for the calculator tools is simple and does not contain obvious code-level malicious patterns, obfuscation, or direct `eval` usage. Input validation for tool arguments is handled using Zod schemas. However, the server is explicitly designed to be 'authless' as indicated by its name and README, meaning it lacks any authentication or authorization mechanisms. Deploying this server in a production environment or with sensitive tools without implementing proper authentication would expose its functionalities to the public Internet, posing a significant security risk.
Updated: 2025-12-14GitHub→
0
0
High Cost
AsamiShingo icon

mcp-server-test

by AsamiShingo

Sec3

Facilitate natural language querying and analysis of internal company organizational structures, employee data, and performance evaluation records via a Large Language Model (LLM).

Setup Requirements

  • ⚠️Requires Docker Compose.
  • ⚠️Requires an NVIDIA GPU with drivers for Ollama (`runtime: nvidia`).
  • ⚠️Demands manual creation of `logininfo.json` (containing plain text credentials), `url.json` (containing system URLs), and `intermediate.crt` (an SSL certificate) on the local filesystem, which is a significant security risk.
  • ⚠️Requires access to an external 'target site' (implied 'NeWarp' system) for data retrieval, with specified intermediate certificates.
Review RequiredView Analysis
CRITICAL: The setup explicitly requires storing sensitive login credentials (username, password) and specific URLs for an external 'NeWarp' system in plain text JSON files (`logininfo.json`, `url.json`) on the filesystem. An intermediate certificate (`intermediate.crt`) is also stored locally. This method of credential management poses a severe security risk, as any entity with filesystem access to the mounted volumes can read these sensitive details. There is no indication of secure secret management practices (e.g., environment variables, secret managers). No `eval` or similar dangerous patterns were found in the provided Python code snippets.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
agiprolabs icon

devpattern

by agiprolabs

Sec7

An MCP server enabling AI clients to perform structured problem-solving, maintain context, manage tasks, and generate documentation across thinking sessions.

Setup Requirements

  • ⚠️Requires Node.js runtime (version >=20) or Docker for execution.
  • ⚠️Relies on a persistent `DATA_PATH` for session, thought, and task storage; without proper configuration, data may be ephemeral.
  • ⚠️Designed to be used by an MCP-compatible client (e.g., Claude Desktop, Cline) or via direct HTTP calls, not as a standalone user-facing application.
Verified SafeView Analysis
The server primarily uses file-based persistence, which inherently carries risks if the `DATA_PATH` environment variable is misconfigured to a sensitive system directory. However, the code itself properly uses `path.join` and does not expose direct 'eval' or command injection vulnerabilities. Input validation for tools is handled by Zod. In a containerized setup (Docker), specifying a dedicated volume for `/data` mitigates this risk by sandboxing file operations.
Updated: 2025-12-03GitHub→
0
0
Low Cost
DaoiestFire icon

streamable-http-mcp

by DaoiestFire

Sec9

Implements a basic StreamableHTTP MCP (Multi-Agent Communication Protocol) server with a weather information tool.

Verified SafeView Analysis
CORS is configured to allow all origins ('*'), which is suitable for demonstration or development but generally not recommended for production environments. No other critical vulnerabilities or malicious patterns were found.
Updated: 2025-11-24GitHub→
0
0
Medium Cost
rossella icon

fleet-mcp

by rossella

Sec7

Enables AI assistants to programmatically manage and monitor GitOps capabilities and resources within a Fleet-managed Kubernetes environment.

Setup Requirements

  • ⚠️Requires Go 1.21 or later
  • ⚠️Requires a Kubernetes cluster with Fleet installed
  • ⚠️Requires Rancher bearer token (R_token header) and Rancher server URL (R_url header) for each request, or kubeconfig for local runs
Verified SafeView Analysis
The server acts as a powerful gateway to Kubernetes, requiring a Rancher bearer token ('R_token' header) with potentially broad RBAC permissions for its operations. This means the server operates with the permissions of the provided token; therefore, securing the token and limiting its scope is critical. While TLS is supported, the local development setup allows 'INSECURE_SKIP_TLS=true', which should not be used in production. The Kubernetes deployment manifest includes extensive ClusterRole permissions (full CRUD for many Fleet resources), which should be reviewed and potentially restricted based on specific use cases. There are no obvious code execution vulnerabilities like 'eval' or hardcoded secrets.
Updated: 2025-12-05GitHub→
0
0
Medium Cost
pankajshakya627 icon

File-MCP-server

by pankajshakya627

Sec9

A comprehensive Model Context Protocol (MCP) server providing local utilities for file operations, directory management, text processing, and mathematical calculations, ideal for integration with AI agents like Claude Desktop.

Setup Requirements

  • ⚠️Requires Python 3.10+ (pyproject.toml specifies >=3.11).
  • ⚠️The default file system operations are sandboxed to a specific directory (`/tmp/Dev_Pankaj` by default) for security, which might require understanding for expected file locations.
  • ⚠️If HTTP transport is explicitly enabled, careful consideration of host binding (`0.0.0.0` vs `127.0.0.1`) and network security is needed.
Verified SafeView Analysis
The server implements robust file system sandboxing via the `_get_safe_path` function, which redirects all file operations to a designated directory (defaulting to /tmp/Dev_Pankaj or a custom SANDBOX_DIR) and actively blocks path traversal attempts ('..'). The `calculate` function uses `eval`, but it is heavily sandboxed with a restricted `safe_dict` and an empty `__builtins__` to prevent arbitrary code execution. When running in HTTP mode (not default), it could bind to `0.0.0.0` potentially exposing it to the network, but the README provides explicit warnings and best practices for this scenario.
Updated: 2025-12-10GitHub→
0
0
Medium Cost
ashotchumore icon

my_new_mcp_server

by ashotchumore

Sec8

Provides a boilerplate for quickly developing Model Context Protocol (MCP) servers with TypeScript, featuring calculation and text-to-image generation tools.

Setup Requirements

  • ⚠️Requires `HF_TOKEN` environment variable to be set for the `text_to_image` tool to function.
  • ⚠️Requires Node.js and npm installed for dependency management, building, and execution.
  • ⚠️Designed to communicate via standard I/O, necessitating an MCP client to pipe input/output (e.g., configured via `.cursor/mcp.json` for Cursor IDE).
Verified SafeView Analysis
Uses reputable SDKs and libraries like @modelcontextprotocol/sdk and @huggingface/inference. Sensitive API keys (HF_TOKEN) are correctly handled via environment variables, preventing hardcoding. The server primarily communicates via standard I/O (StdioServerTransport), which limits direct network exposure from this specific server instance, relying on a secure external MCP client for interaction. No 'eval' or other highly dangerous patterns were observed.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
FlowTheTensor icon

github-mcp

by FlowTheTensor

Sec9

The GitHub MCP Server enables AI assistants (like Claude via LM Studio) to directly interact with GitHub for repository management, issue tracking, pull request workflows, and code analysis.

Setup Requirements

  • ⚠️Requires a GitHub Personal Access Token (PAT) with appropriate scopes (repo, read:org, gist).
  • ⚠️Requires Docker Desktop or Node.js/NPX to be installed and running.
  • ⚠️Requires LM Studio (version 0.3.0+) for AI integration.
Verified SafeView Analysis
The server's security is highly dependent on the secure handling of the GitHub Personal Access Token (PAT). The README explicitly advises using tokens with minimal necessary permissions, rotating them regularly, and never sharing them. No 'eval' or malicious patterns are visible in the provided README, which serves as a setup guide. Assuming the underlying official GitHub package is secure, the main risk is user mishandling of the PAT.
Updated: 2025-11-24GitHub→
0
0
Medium Cost
arbolescontract icon

codex-mcp-go

by arbolescontract

Sec9

Acts as an MCP (Model Context Protocol) server to wrap the OpenAI Codex CLI, allowing AI coding assistants to interact with Codex for coding tasks.

Setup Requirements

  • ⚠️Requires OpenAI's `codex` CLI to be installed and configured separately (e.g., via `npm i -g @openai/codex`).
  • ⚠️Requires an `OPENAI_API_KEY` to be configured for the underlying `codex` CLI (typically via environment variables).
  • ⚠️Go 1.24+ is required if building from source; otherwise, Node.js/npm is needed for the recommended `npx` installation.
Verified SafeView Analysis
The server itself is a thin wrapper over the external OpenAI Codex CLI. It explicitly defaults to 'read-only' sandbox mode, preventing direct file modifications by Codex unless overridden. It also prohibits arbitrary 'model' and 'profile' parameters unless allowlisted, enhancing security. Input prompts for the underlying Codex CLI are escaped for Windows environments to mitigate shell quoting issues. The recommended agent system prompts strongly advise agents to use 'read-only' mode and review/apply changes manually, further bolstering security. The primary security considerations shift to the trustworthiness and behavior of the underlying 'codex' CLI and the AI agent's adherence to the recommended safety protocols. The npm installation method downloads a pre-compiled binary, introducing a supply chain risk if the GitHub releases or repository were compromised.
Updated: 2026-01-19GitHub→
PreviousPage 737 of 760Next