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
ctrimm icon
Sec8

Provides an MCP (Model Context Protocol) server for AI-assisted guidance on the USWDS design system, offering tools to list, describe, compare, validate, and generate code for USWDS components in React, vanilla HTML, or Tailwind CSS.

Setup Requirements

  • ⚠️Requires an AWS account and configured credentials for deployment.
  • ⚠️Uses AWS SST CLI for deployment and local development (`npx sst deploy`, `npx sst dev`).
  • ⚠️Requires a Resend API key (`RESEND_API_KEY`) if email features (signup, API key reset notifications) are enabled.
  • ⚠️Custom domain setup for the router requires a Cloudflare API Token (`CLOUDFLARE_API_TOKEN`) if using Cloudflare for DNS.
Verified SafeView Analysis
Authentication uses API keys stored in DynamoDB, with secrets managed by AWS Secrets Manager via SST. Origin validation middleware is in place for CORS protection. Rate limiting is implemented in-memory per Lambda instance, offering basic protection but lacking global coordination without further integration (e.g., WAF, API Gateway usage plans, which are mentioned as future enhancements in ARCHITECTURE.md and RATE_LIMITING.md). The admin API has custom authentication via middleware, which needs to be carefully secured in production. No `eval` or blatant obfuscation found.
Updated: 2026-01-04GitHub→
0
0
Medium Cost
becksclair icon

rescreenshot-mcp

by becksclair

Sec9

Cross-platform screenshot capture for coding agents, enabling programmatic visual interaction with applications.

Setup Requirements

  • ⚠️Linux Wayland: Requires `xdg-desktop-portal` and `pipewire` runtime dependencies to be installed.
  • ⚠️Windows: Requires Visual Studio C++ Build Tools for compilation and Windows 10 (version 1803 / build 17134+) at runtime.
  • ⚠️macOS: The ScreenCaptureKit backend is currently not implemented and is planned for Q1 2026.
Verified SafeView Analysis
The server demonstrates strong security practices for its context. Sensitive Wayland restore tokens are encrypted using ChaCha20-Poly1305 with HKDF-SHA256 and stored in a keyring or an encrypted file with appropriate permissions. Regex pattern matching includes size and DFA limits to prevent ReDoS attacks. All necessary unsafe blocks for OS interaction (Win32 API) include explicit comments and buffer handling. The project actively tracks and manages dependency vulnerabilities. Communication is strictly via stdio JSON-RPC, limiting network attack surface. Known inherent security limitations of the X11 protocol (no consent for capture) are clearly documented rather than introduced by the application.
Updated: 2025-12-16GitHub→
0
0
Low Cost
andriyshevchenko icon

secrets-mcp-server

by andriyshevchenko

Sec9

Enables AI agents to securely store and retrieve secrets cross-platform using native operating system credential management systems.

Setup Requirements

  • ⚠️Requires Node.js 18.x or later to run.
  • ⚠️On Linux, specific system libraries like `libsecret-1-dev` (or equivalent) need to be installed for the Secret Service API to function.
  • ⚠️In containerized Linux environments (e.g., Docker), the `list_secrets` operation may fail due to restrictive DBus/Secret Service configurations, though individual secret storage and retrieval will still work.
Verified SafeView Analysis
The server utilizes native operating system secret management APIs (Windows Credential Vault/DPAPI, macOS Keychain, Linux Secret Service) via the `@napi-rs/keyring` library, which is a strong security practice as it leverages OS-level encryption and access controls. Communication is restricted to standard I/O (stdin/stdout) using the Model Context Protocol, eliminating direct network exposure for the server itself. Input validation for all tool parameters is performed using Zod schemas, reducing the risk of malformed inputs or injection attacks. No 'eval', code obfuscation, or hardcoded sensitive credentials were found in the application logic. The primary security risk would lie in potential vulnerabilities within the underlying native OS keyring implementations or the `@napi-rs/keyring` bindings, which are external dependencies.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
portalsprotocol icon

mcp-server

by portalsprotocol

Sec8

MCP server that allows AI agents to discover and access decentralized APIs (Portals) on the Solana blockchain, paying autonomously in USDC per use.

Setup Requirements

  • ⚠️Requires 'PORTALS_WHITELIST' environment variable to be set with comma-separated Portal IDs.
  • ⚠️Requires manual funding of the auto-generated Solana wallet with SOL (for gas) and USDC (for payments).
  • ⚠️Node.js version >=18.0.0 is required.
Verified SafeView Analysis
The server stores a Solana wallet locally (`~/.portals/wallet.json`) with mode 0600 permissions, which is good practice. It explicitly requires a `PORTALS_WHITELIST` to prevent agents from accessing arbitrary portals. Input validation for tool arguments is performed against fetched OpenAPI schemas using Ajv. The fetching of OpenAPI schemas via `axios.get` from whitelisted portal URLs (which are retrieved from on-chain registry) introduces a potential, though mitigated, risk if a whitelisted portal were to serve a malicious or extremely large schema designed to exploit `axios` or `ajv` parsers. The `refreshPortals` function, which includes these network calls, is invoked on every tool request, adding a slight performance overhead but no immediate critical security flaw.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
RLRyals icon
Sec9

A modular AI-powered writing assistance suite that provides comprehensive tools for narrative development, story management, world-building, character arcs, plot threads, and workflow automation, with built-in database administration capabilities.

Setup Requirements

  • ⚠️Requires a PostgreSQL database instance to be running.
  • ⚠️The `DATABASE_URL` environment variable must be set for PostgreSQL connection.
  • ⚠️Initial database setup requires running SQL migration files (e.g., `024_update_npe_schema.sql`) to create the necessary schema.
  • ⚠️Requires a Node.js runtime environment (version 14.17.0+ for `randomUUID` and ESM support is implied).
Verified SafeView Analysis
The project demonstrates strong security practices, including extensive use of parameterized SQL queries to prevent injection attacks across all database interactions. The `database-admin-server` specifically implements whitelisting for tables and columns, and enforces access control for database operations. Controlled use of `child_process.spawn` for `pg_dump` and `psql` (for backup/restore) is carefully managed with configurable paths and validated arguments. File path handling uses `path.join` and `path.resolve` to mitigate directory traversal. However, utility scripts like `run-migration.js` and `load-series-data.js` execute raw SQL files directly from disk, which, while intentional for their purpose, relies on the absolute trust of these files and their source. Deployment should ensure these scripts are only run with trusted inputs in controlled environments.
Updated: 2026-01-19GitHub→
0
0
Low Cost
NyanDanKun icon
Sec9

Manage OpenCode Model Context Protocol (MCP) servers by toggling their enabled state via a graphical user interface.

Setup Requirements

  • ⚠️Requires Python 3.8+ for running from source.
  • ⚠️The `.exe` is specific to Windows 10/11.
Verified SafeView Analysis
The application primarily reads and writes local JSON configuration files (`opencode.json`). It does not execute the `command` fields directly, nor does it perform network operations or use dangerous functions like `eval()`. There are no hardcoded secrets found. The security risk from this tool itself is minimal; any potential risks would stem from what the OpenCode platform does with the enabled MCP server commands, which is outside the scope of this manager.
Updated: 2026-01-16GitHub→
0
0
Low Cost
godson2607 icon

MCP-Server

by godson2607

Sec9

Provides examples of Minimal Context Protocol (MCP) servers in Python for basic arithmetic operations and RSS feed searching, demonstrating different transport mechanisms (STDIO, HTTP) and FastAPI integration.

Setup Requirements

  • ⚠️Dependency `fastmcp` might not be directly available on PyPI.
  • ⚠️Dependency `fastapi_mcp` might not be directly available on PyPI.
  • ⚠️Python 3.8+ required (3.10+ recommended).
Verified SafeView Analysis
The code primarily uses well-established libraries (`fastmcp`, `fastapi`, `feedparser`). Arithmetic operations correctly handle division by zero. RSS parsing relies on `feedparser`, which is generally robust, but fetching external content always carries inherent risks. No direct `eval()` or similar dangerous functions, no obvious injection vulnerabilities, and no hardcoded secrets were found. HTTP examples bind to `localhost` by default, which is safe for development; the README provides good advice regarding `0.0.0.0` binding for external access.
Updated: 2025-11-28GitHub→
0
0
Medium Cost
oshin-prakash icon
Sec7

Integrates Azure AI Agents with the Microsoft Learn MCP server to search documentation and provide tool-enhanced responses.

Setup Requirements

  • ⚠️Requires an Azure subscription with AI Agents enabled (potentially paid).
  • ⚠️Requires access to the Microsoft Learn MCP server.
  • ⚠️Requires Azure CLI or VS Code logged-in identity for authentication.
Verified SafeView Analysis
The project uses a .env file for sensitive credentials, which is good practice. However, a full security audit is impossible due to heavily truncated source code. Interactions with external Azure AI services and the Microsoft Learn MCP server imply network dependencies, which carry inherent risks, but no obvious malicious patterns or glaring vulnerabilities are present in the provided description.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
Dellos12 icon
Sec9

Implements a Retrieval-Augmented Generation (RAG) engine leveraging geometric and statistical principles for advanced information retrieval, particularly for business data.

Setup Requirements

  • ⚠️Docker is required for easy setup.
  • ⚠️Requires Python 3.8+.
  • ⚠️Initial run will download Sentence Transformers and Cross-Encoder models (all-MiniLM-L6-v2 and ms-marco-MiniLM-L-6-v2) to a local cache, which might take time and disk space.
Verified SafeView Analysis
The application is a standard FastAPI server exposing endpoints. It uses local ChromaDB for vector storage and pre-trained Sentence Transformers models. No 'eval' or obvious malicious patterns were found. Standard web API security practices should be followed when deploying in production (e.g., access control, input validation).
Updated: 2026-01-17GitHub→
0
0
High Cost
sathyakutti icon

mcp-yt-client

by sathyakutti

Sec2

A comprehensive market research framework that orchestrates multiple Model Context Protocol (MCP) data sources to gather and analyze information on any topic, generating structured reports.

Setup Requirements

  • ⚠️Requires Docker Desktop with MCP Toolkit installed.
  • ⚠️Requires a GitHub Personal Access Token (GITHUB_PERSONAL_ACCESS_TOKEN) for GitHub MCP functionality.
  • ⚠️Requires an Exa (Metaphor) API Key (EXA_API_KEY) (note: exposed in documentation, requires immediate rotation).
Review RequiredView Analysis
A real `EXA_API_KEY` (`8f6c31d9-16be-4b35-8721-186fe4f62bb5`) is hardcoded in `FINAL-SUMMARY.md` and `EXA-QUICK-START.md`, representing a critical information disclosure vulnerability requiring immediate key rotation. The system extensively uses `child_process.spawn` to run Docker containers, which requires elevated privileges and, if compromised, could allow arbitrary command execution. The LinkedIn client also explicitly notes potential Terms of Service violations and account suspension risk if used for automated research, although it is not directly implemented in the code provided.
Updated: 2025-11-24GitHub→
0
0
Low Cost
juliendoutre icon

protoc-gen-go-mcp

by juliendoutre

Sec9

Generates Go code for gRPC services, allowing them to be exposed as tools for Large Language Models (LLMs) via the Model-Client Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Go development environment for compilation and execution.
  • ⚠️Requires `protoc` (Protocol Buffers compiler) and its Go plugins (`protoc-gen-go`, `protoc-gen-go-grpc`) to generate base gRPC code.
  • ⚠️Manual IDE configuration (e.g., editing `~/.cursor/mcp.json`) is needed to integrate the generated MCP server with an LLM client.
Verified SafeView Analysis
The project is a code generator, processing .proto files to create Go code. The generated code (`api_mcp.pb.go` in the example) acts as a proxy, mapping MCP tool calls to gRPC service methods. Input validation primarily relies on the MCP framework ensuring correct type conversion (e.g., `.(string)`). The example gRPC server uses insecure credentials, which is acceptable for local development but would require TLS in a production environment. No `eval` or similar dynamic code execution, nor any hardcoded secrets were found in the provided source code.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
pedrocr83 icon

mcp_servers

by pedrocr83

Sec4

A comprehensive multi-tool MCP server suite offering advanced web search (Brave API), robust local file system management, document content extraction, and database interaction, designed for AI agent integration.

Setup Requirements

  • ⚠️Requires Brave Search API Key, with paid Pro plans necessary for full features like local search and AI summarization.
  • ⚠️File system write operations require both the `--allow-write` CLI flag (or `ALLOW_WRITE` environment variable) and writable Docker volume mounts; default mounts for `filesystem-mcp-server` and `document-reader-mcp-server` are read-only (`:ro`).
  • ⚠️The hardcoded PostgreSQL credentials (`misterios:misteriospassword`) in `docker-compose.yml` for `mcp-db-server` must be changed for any production or secure environment.
  • ⚠️The `rust-mcp-filesystem` server requires specific `ALLOWED_DIRECTORIES` arguments on startup or the `--enable-roots` CLI option for dynamic directory access control to function correctly.
Review RequiredView Analysis
The `mcp-db-server` in `docker-compose.yml` contains hardcoded PostgreSQL credentials (`misterios:misteriospassword`) for `DATABASE_URL`. This is a critical security risk as these credentials could be exposed. While `rust-mcp-filesystem` employs strong path validation, `ro` (read-only) Docker mounts by default limit write operations even if `ALLOW_WRITE` is set. Input validation and container security configurations are generally good.
Updated: 2025-12-07GitHub→
PreviousPage 431 of 760Next