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
openpharma-org icon

who-mcp

by openpharma-org

Sec9

Provides AI assistants and applications access to the World Health Organization's Global Health Observatory (GHO) data via its OData API for searching, retrieving, and analyzing health indicators and statistics.

Setup Requirements

  • ⚠️Requires Node.js version 18.0.0 or higher.
  • ⚠️A build step (`npm run build`) is required to copy source files to the 'build' directory before execution.
  • ⚠️Data retrieval methods like `get_health_data` and `get_cross_table` can return large datasets, potentially leading to high token usage if not limited by the 'top' parameter.
Verified SafeView Analysis
The server leverages the Model Context Protocol (MCP) SDK which enforces strict input schema validation, significantly reducing common injection vulnerabilities. API calls to the WHO OData endpoint are constructed carefully, although direct string interpolation for OData filter parameters exists. However, OData's parsing mechanism typically treats these as data values, reducing the risk of code injection compared to SQL. No 'eval' or direct command execution found. The XML parsing utility is included but not used by the core logic, thereby avoiding potential XML-related vulnerabilities. No hardcoded sensitive credentials detected.
Updated: 2025-12-16GitHub→
0
0
Medium Cost

mcp-sqlite

by rosch100

Sec8

An MCP server enabling interaction with SQLCipher-encrypted SQLite databases, offering features for schema exploration, data querying, and CRUD operations.

Setup Requirements

  • ⚠️Requires Java 21+ JDK for local installation.
  • ⚠️Secure passphrase management for SQLCipher databases requires either macOS Keychain integration or manually setting the `MCP_SQLITE_ENCRYPTION_KEY` environment variable.
  • ⚠️Docker usage for encrypted passphrases has specific command-line flag ordering requirements (`-e` before `-v`).
Verified SafeView Analysis
The `execute_sql` tool allows arbitrary SQL execution without parameterization, posing a SQL injection risk if used with untrusted input; users are explicitly warned about this. However, the server prioritizes robust security for passphrases using AES-256-GCM encryption, macOS Keychain integration, and environment variables, including strong key validation. Other tools include SQL identifier validation.
Updated: 2025-11-17GitHub→
0
0
Low Cost
AdamBien icon
Sec9

Provisions a serverless remote Model Context Protocol (MCP) server using AWS Bedrock Agent Core Gateway, AWS Lambda, and Amazon Cognito for authenticated API access.

Setup Requirements

  • ⚠️Requires JDK 21 or later and Apache Maven for building Java components.
  • ⚠️AWS CDK must be bootstrapped in the target AWS account and region (`cdk bootstrap aws://ACCOUNT-ID/REGION`).
  • ⚠️Requires AWS credentials configured (e.g., via AWS CLI or environment variables) to deploy and interact with AWS services.
  • ⚠️Manual steps (web UI or AWS CLI) are required to create a user account and obtain a JWT token for authentication before interacting with the deployed server.
Verified SafeView Analysis
The architecture uses standard AWS security best practices, including Cognito for JWT-based authentication and IAM roles with least privilege for Bedrock Agent Core Gateway and Lambda interaction. No 'eval' or obvious malicious patterns are present. Configuration via ZCfg and system properties helps avoid hardcoded secrets. The Cognito User Pool has a removal policy of 'DESTROY', meaning all user data will be lost if the stack is deleted. This is common for development but requires consideration for production environments.
Updated: 2025-12-13GitHub→
0
0
High Cost
amsajaj icon
Sec3

An AI-powered web application for generating, editing, and exporting test cases, integrating with tools like Zephyr and PostgreSQL.

Setup Requirements

  • ⚠️Docker is required to run the application via `docker-compose`.
  • ⚠️PostgreSQL database is a mandatory dependency.
  • ⚠️AI models (Qwen3, Gemma) are used, implying potential API costs or local resource requirements, though specific integration details are not provided in the truncated code.
Verified SafeView Analysis
The `docker-compose.yml` file hardcodes default PostgreSQL credentials (`postgres:postgres`) for both the API connection string and the database service environment variables. The database port (5433) is also exposed to the host. This setup is highly insecure for production environments, as it allows trivial unauthorized access to the database. It is critical to change these default credentials immediately for any deployment outside of isolated local development. Additionally, all download/repository links in the README point to a direct `.zip` file download, which is unusual for a GitHub project and could be a security concern regarding the integrity of the downloaded binaries if not explicitly verified.
Updated: 2026-01-19GitHub→
0
0
Low Cost
cuongpo icon
Sec9

A Model Context Protocol (MCP) server enabling seamless interaction with the Hyperion blockchain for querying, transacting, and managing assets via standardized APIs.

Setup Requirements

  • ⚠️Requires Node.js v18 or higher to run.
  • ⚠️Requires access to a Hyperion blockchain RPC endpoint (configured via HYPERION_RPC_URL).
  • ⚠️For any transaction or contract deployment, a funded private key for Hyperion (HYPERION_PRIVATE_KEYS) is required.
  • ⚠️Using the Telegram bot integration requires additional API keys (TELEGRAM_BOT_TOKEN, SMITHERY_API_KEY, SMITHERY_PROFILE).
Verified SafeView Analysis
The server demonstrates good security practices by loading sensitive information (private keys, API keys) from environment variables, rather than hardcoding them. Wallet management functions correctly mask private keys when listing wallet information. The core dependencies (ethers.js, axios) are widely used and generally considered secure. There are no obvious signs of malicious patterns or use of dangerous functions like 'eval'. The primary security consideration for users is ensuring `HYPERION_PRIVATE_KEYS` and any integrated API keys are securely managed and that the `HYPERION_RPC_URL` points to a trusted endpoint.
Updated: 2025-11-30GitHub→
0
0
Low Cost
Sec2

Provides a persistent PowerShell execution environment for AI agents within Claude Code, with tools for script execution, iterative development, and advanced output analysis via AgentBricks.

Setup Requirements

  • ⚠️Requires .NET 8.0 SDK for building.
  • ⚠️Requires Windows x64 operating system due to PowerShell SDK dependency.
  • ⚠️Requires manual configuration of the executable path in .mcp.json or ~/.claude/settings.json after building.
Review RequiredView Analysis
Allows arbitrary PowerShell script execution and external command execution via 'pwsh' and 'dev_run' tools. No sandboxing or Just Enough Administration (JEA) constraints are implemented in the current version, making it a high-risk server if used with untrusted inputs. JEA integration is a planned future enhancement.
Updated: 2025-11-19GitHub→
0
0
Low Cost
konokenj icon
Sec8

Serves AWS CDK API references and integration test code as static resources via the Model Context Protocol (MCP), enabling offline access for coding agents.

Setup Requirements

  • ⚠️Requires Python 3.8+ to run (Python 3.13+ recommended for development).
  • ⚠️The recommended usage command `uvx` requires the 'uv' tool to be installed.
  • ⚠️The `cdk_api_downloader` (used for populating documentation) performs GitHub API calls; unauthenticated requests might hit rate limits.
Verified SafeView Analysis
The cdk_api_downloader component securely downloads content from a fixed HTTPS GitHub URL (aws/aws-cdk). It includes explicit URL validation for HTTPS. The zip file extraction process, while coming from a trusted source, does not fully sanitize paths against advanced directory traversal attacks, but a basic mitigation is present by stripping the top-level directory. No 'eval', obfuscation, or hardcoded secrets were found in the provided source.
Updated: 2026-01-19GitHub→
0
0
Low Cost
PrithiviPM2580 icon

lekhanX

by PrithiviPM2580

Sec8

Backend API for an AI-powered blogging platform with user authentication, role-based permissions, and content management.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for local development setup (backend and MongoDB services).
  • ⚠️Requires a MongoDB instance for data persistence.
  • ⚠️Critical environment variables must be configured (.env.development for dev, production env vars for prod).
Verified SafeView Analysis
The server demonstrates good security practices including password hashing with bcrypt, JWTs for authentication (secrets from environment variables), refresh token management (stored in DB with user agent and IP), HTTP-only and secure cookies, input validation with Zod, rate limiting, and a comprehensive global error handler that specifically catches and processes JWT-related errors. There are no obvious hardcoded secrets or dangerous patterns like 'eval'. The use of `req.ip` for rate limiting and token tracking relies on proper proxy configuration for accurate client IP in production environments.
Updated: 2025-11-20GitHub→
0
0
High Cost
HarshavardhanaNaganagoudar icon

Business-Location-Scouter

by HarshavardhanaNaganagoudar

Sec2

Identifies and ranks optimal business locations by integrating real-time search, macroeconomic indicators, cost metrics, and AI-powered insights.

Setup Requirements

  • ⚠️Requires external API keys for LLMs (Claude/OpenAI) and search (Tavily). These are typically paid services.
  • ⚠️The server is remote (Hugging Face space); local deployment details are not provided.
  • ⚠️Client-side setup requires Node.js/npm for `npx mcp-remote`.
Review RequiredView Analysis
A critical security audit of the MCP server's source code is impossible as the provided content *only* includes the README. No server-side implementation details, code patterns, or dependencies were available for review. The instructions show configuring a client (Claude) to connect to a *remote* MCP server hosted on Hugging Face (`hf.space`) via `npx mcp-remote`. While `npx` is a standard tool, connecting to an unverified remote server without inspecting its source code introduces inherent security risks related to data privacy, execution environment integrity, and potential for malicious behavior. Therefore, without the server's actual source code, its security cannot be guaranteed.
Updated: 2025-11-30GitHub→
0
0
Medium Cost
PAIshanMadusha icon
Sec9

Provides a Model Context Protocol (MCP) server for AI models, demonstrating task and todo management functionalities, deployable on Cloudflare Workers for remote execution, and also offering local Node.js environments with STDIO transport and either file-based or MongoDB persistence.

Setup Requirements

  • ⚠️Deployment of the `mcp-cloudflare` server requires a Cloudflare account and using the `wrangler` CLI. Cloudflare KV storage, essential for this worker, may necessitate a paid Cloudflare plan.
  • ⚠️The `mcp-mongo` server requires a running MongoDB instance.
  • ⚠️The `mcp-basic` server requires manual copying of a seed file (`product.txt`) into its `build/seed` directory after compilation.
Verified SafeView Analysis
The implementation uses TypeScript with Zod for robust input validation, effectively preventing common injection vulnerabilities. It avoids direct use of `eval` or other dangerous code constructs. External calls to APIs (like GitHub in `mcp-basic`) and database/storage systems (Cloudflare KV, MongoDB) are handled via standard library functions with appropriate error checks. Critical configurations, such as database URIs (`MONGO_URI`) and Cloudflare KV bindings (`MCP_CLOUDFLARE_STORE`), are designed to be environment-variable or binding driven, preventing hardcoded secrets. The `JSON.parse` operations on data retrieved from KV are considered safe within the worker's controlled environment.
Updated: 2025-12-06GitHub→
0
0
Low Cost
Sec6

Provides an unauthenticated remote Model Context Protocol (MCP) server for integrating custom tools with AI models on Cloudflare Workers.

Setup Requirements

  • ⚠️Requires a Cloudflare account for deployment.
  • ⚠️Authentication is intentionally disabled, meaning the server is publicly accessible (suitable for demo, but a security consideration).
  • ⚠️Local MCP clients (e.g., Claude Desktop) require the `mcp-remote` proxy to connect to the deployed server.
Verified SafeView Analysis
The server is intentionally unauthenticated ('authless'), making it publicly accessible to anyone with the URL. This is suitable for a demo but insecure for production environments without additional authentication/authorization layers.
Updated: 2025-11-20GitHub→
0
0
Low Cost
KlausWeigele icon

mcp_lernen

by KlausWeigele

Sec9

This MCP server manages in-memory notes, allowing an AI agent to list, create, and delete notes via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Node.js runtime and is configured to use ES Modules, meaning '"type": "module"' must be present in package.json.
  • ⚠️The TypeScript compiler options (e.g., '"module": "Node16"', '"moduleResolution": "Node16"') in tsconfig.json are critical for correct compilation and module resolution.
  • ⚠️Integration with Claude Desktop or similar hosts requires manual configuration (e.g., 'claude_desktop_config.json') specifying an absolute path to the compiled 'build/index.js' and a full host restart.
Verified SafeView Analysis
The server operates an in-memory notes store, limiting the impact of data breaches to the current session. Input validation is performed using Zod, a good security practice. Destructive operations like 'delete_note' are present, and while they operate on non-persistent data in this project, in a real-world scenario, such actions would ideally require user elicitation for confirmation (as highlighted in the MCP documentation) to prevent unintended data loss. No hardcoded secrets or 'eval' calls were found. Communication uses Stdio, which is safer for local processes.
Updated: 2026-01-19GitHub→
PreviousPage 736 of 760Next