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
Low Cost
icy-r icon

jira-mcp

by icy-r

Sec9

Enables AI assistants to manage Jira Cloud issues, sprints, projects, and other entities via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Jira Cloud instance with a valid Atlassian API Token (not password).
  • ⚠️Requires Node.js 20.0.0 or higher to run the server.
  • ⚠️Requires an MCP-compatible AI client (e.g., Claude Desktop, Cursor) to interact with the server.
Verified SafeView Analysis
Credentials (JIRA_API_TOKEN, JIRA_EMAIL) are exclusively loaded from environment variables, preventing hardcoding. Input validation for tool parameters is rigorously performed using Zod schemas. The Jira client implements rate limiting and robust error handling for external API interactions. An audit log tracks all destructive actions (create, update, delete, transition, assign, link, move), and a 'dryRun' mode is available to preview changes without execution. Project access can be optionally restricted via a configurable `JIRA_PROJECTS_FILTER`.
Updated: 2025-12-17GitHub→
0
0
Low Cost
cafaray icon
Sec9

A Go-based client serving as an MCP server or HTTP API for a Historical Places service, integrating multiple data sources and optimized for AI model interaction and cloud deployment.

Setup Requirements

  • ⚠️Requires Go 1.22+ to build and run locally.
  • ⚠️Requires Docker for containerized deployment (local or cloud).
  • ⚠️An external 'Historical Places service' must be running and accessible at the configured `HISTORICAL_PLACES_BASE_URL` as this client is a proxy/client for it.
Verified SafeView Analysis
The source code demonstrates good security practices: no 'eval' or dynamic code execution, no hardcoded secrets (environment variables are used for sensitive configuration like `HISTORICAL_PLACES_BASE_URL`), and input validation is present for API parameters. Error handling and logging are robust. The deployment scripts correctly use environment variables and robust shell scripting. The Cloud Run deployment option explicitly allows unauthenticated access, which is a design choice making the HTTP API public, not a vulnerability in the code itself, but a consideration for deployment context. The MCP mode uses stdin/stdout for communication, implying the interacting AI model/process is trusted.
Updated: 2025-11-21GitHub→
0
0
Low Cost
Steverino17 icon

elitemindset-mcp

by Steverino17

Sec8

The server provides a single Model Context Protocol (MCP) tool to help users overcome overwhelm and identify a time-boxed next action, intended for use by an AI agent.

Setup Requirements

  • ⚠️Requires the @modelcontextprotocol/sdk for interaction and development.
  • ⚠️The 'railway-server.js' variant requires specific image files (e.g., .png) in an 'images' directory relative to the server for resource handling.
  • ⚠️Primarily designed as a backend tool for an AI agent (e.g., ChatGPT app), not a standalone user-facing application.
Verified SafeView Analysis
The server handles user input by trimming and type conversion (string, number). The `api/mcp.js` and `server.js` endpoints directly interpolate user-provided `goal` and `blocker` into the action string. While the `railway-server.js` variant outputs a JSON stringified object, consuming clients should still sanitize outputs if they are rendered directly to a user interface to prevent potential cross-site scripting (XSS), though this is less critical for consumption by an LLM agent. No hardcoded secrets or malicious patterns (e.g., 'eval') were detected in the provided code.
Updated: 2026-01-19GitHub→
0
0
High Cost
pxl-research icon

tai-mcp-memory

by pxl-research

Sec8

The MCP Memory Server provides persistent, semantic memory for LLM agents, combining structured storage (SQLite) and vector-based semantic search (ChromaDB) with automatic LLM-based summarization for efficient retrieval.

Setup Requirements

  • ⚠️Requires a valid OpenRouter API Key for summarization, which is a paid service; summarization functionality will not work without it.
  • ⚠️The 'openai' library, a core dependency for LLM interaction, is used in the code but is noted as missing from 'requirements.txt' and will require manual installation.
  • ⚠️Dual writes to SQLite and ChromaDB are not atomic, meaning partial failures can lead to data inconsistency between the two storage layers.
Verified SafeView Analysis
The server correctly uses environment variables for API keys and database paths, avoiding hardcoded secrets. SQLite foreign key constraints are explicitly enabled, improving data integrity. While direct `traceback.print_exc()` is used in some exception handlers (less ideal than structured logging for preventing accidental sensitive data exposure), the overall approach to security is reasonable for an internal tool. The primary non-security risks are data consistency issues due to non-atomic dual writes across SQLite and ChromaDB and potential high LLM token usage.
Updated: 2025-12-11GitHub→
0
0
Low Cost
ferazzeid icon

mcp-server

by ferazzeid

Sec8

Provides a Model Context Protocol (MCP) server for ChatGPT apps, enabling voice-controlled interaction with FastNow, a health and fitness application for tracking fasting, nutrition, and weight.

Setup Requirements

  • ⚠️Requires a Supabase project with specific database tables for OAuth (clients, authorization codes, apps) and FastNow data (e.g., fasting_sessions, food_entries, profiles).
  • ⚠️Requires deploying and managing 10+ Supabase Edge Functions for all 108 tool implementations, which encapsulate the core business logic.
  • ⚠️Requires publicly accessible domains (e.g., mcp.fastnow.app for the MCP server, go.fastnow.app for the OAuth authorization server) with proper DNS and SSL configuration (e.g., via Coolify/Traefik).
  • ⚠️Custom MCP connectors currently require 'Developer Mode' enabled in ChatGPT, limiting broader user access.
Verified SafeView Analysis
The server demonstrates good security practices by implementing OAuth 2.0 with PKCE, validating user tokens against a Supabase `oauth_apps` table using a service role key, and enforcing user data isolation via `user_id` in database queries. It also properly handles authentication errors with `WWW-Authenticate` headers. A noteworthy workaround is employed using an `X-OAuth-Token` custom header when proxying to Supabase Edge Functions to bypass Supabase's platform-level JWT validation, which is a known issue for non-JWT OAuth tokens. While CORS `origin: '*'` is used, which is acceptable for platform integrations, a tighter restriction could be considered for a strictly defined production environment. No hardcoded sensitive API keys or dangerous functions like `eval` were found.
Updated: 2025-11-30GitHub→
0
0
Low Cost
kirha-ai icon

iowrapper

by kirha-ai

Sec3

Wraps stdio-based programs, particularly MCP servers, and exposes them as an HTTP JSON-RPC API.

Setup Requirements

  • ⚠️Requires careful management and sanitization of `CLI_TOOL_COMMAND` and `CLI_TOOL_ARGS` for security and correct functioning.
  • ⚠️The wrapped CLI tool and its runtime dependencies (e.g., `npx`, `npm`) must be installed and available in the execution environment.
Review RequiredView Analysis
The application executes arbitrary commands specified via the `CLI_TOOL_COMMAND` and `CLI_TOOL_ARGS` environment variables. This mechanism introduces a significant remote code execution (RCE) risk if these environment variables are not strictly controlled and secured. There is no explicit sanitization or validation of the command or its arguments within the provided source code. If deployed in an untrusted environment or with vulnerable configuration, this could allow an attacker to execute arbitrary code on the host system.
Updated: 2025-11-20GitHub→
0
0
Low Cost
unk029-openconsultinguk icon

UNK029-MCP-SERVER

by unk029-openconsultinguk

Sec1

Analysis of the server's functionality is not possible as source code was not provided.

Setup Requirements

  • ⚠️Source code not available for review.
Review RequiredView Analysis
Source code was not provided for analysis. Therefore, a security audit cannot be performed. Without reviewing the code for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns, it is NOT safe to run any unknown server software.
Updated: 2025-11-25GitHub→
0
0
High Cost
grzetich icon

eyeson

by grzetich

Sec8

AI-powered UX analysis of websites through a natural language interface, primarily for Claude Desktop and other LLMs.

Setup Requirements

  • ⚠️Requires Node.js 18+.
  • ⚠️Requires a Google Gemini API Key (paid service, usage-based billing applies).
  • ⚠️The UX Analyst AI backend server must be running separately on `http://localhost:3005` (or configured URL) for the MCP server to function.
  • ⚠️Requires using an absolute path to the `index.js` file in Claude Desktop's configuration.
Verified SafeView Analysis
The MCP server itself acts as a proxy, and its direct security risks appear low. It uses standard `node-fetch` for backend communication and retrieves API keys from environment variables. The overall security of the system heavily relies on the backend, which handles browser automation (Puppeteer) and external AI calls. The backend configuration uses `--no-sandbox` arguments for Puppeteer, which reduces isolation but is common in containerized environments. The architecture plan, however, indicates efforts towards robust error handling, resource management, and circuit breakers, which are positive for stability and resilience against certain types of attacks or resource exhaustion.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
ShayYeffet icon

mcp_server

by ShayYeffet

Sec6

Transforms an MCP-compatible client (like Claude Desktop) into a comprehensive development environment for coding, DevOps, data processing, and automation tasks.

Setup Requirements

  • ⚠️Many tools (`image_process`, `pdf_manipulate`, `send_notification` email, `cloud_storage`, `code_format`) provide only basic/placeholder functionality or have simplified, potentially insecure implementations due to missing third-party libraries (e.g., `sharp`, `pdf-lib`, cloud provider SDKs, formatters, linters) which are expected to be installed by the user for full or secure operation.
  • ⚠️The `docker_manage` tool requires Docker to be installed and accessible on the host machine.
  • ⚠️The `MCP_ALLOWED_COMMANDS` environment variable is critical and must be carefully configured by the user, explicitly listing every command (e.g., `npm`, `git`, `python`) the AI is permitted to execute, to maintain security.
Verified SafeView Analysis
The server implements robust local filesystem sandboxing and command allowlisting (using `shell: false` with `spawn` for commands), which is critical for preventing directory traversal and arbitrary code execution locally. However, the `cloud_storage` and `image_process` tools contain 'placeholder' or 'simplified' implementations that lack proper SDKs and secure authentication mechanisms (e.g., using basic auth for cloud storage instead of proper Signature V4 signing), potentially exposing credentials or leading to insecure interactions with external services if used without installing recommended libraries or implementing robust security. The claim of 'military-grade sandboxing' for cloud storage is not met by the current simplified code. The `send_notification` tool's webhook functionality also relies on basic HTTP requests without inherent advanced security features. Therefore, while local operations are well-secured, interactions with external services require careful user configuration and potentially additional secure library installations.
Updated: 2025-12-20GitHub→
0
0
Low Cost
Stealinglight icon

StravaMCP

by Stealinglight

Sec9

A remote Model Context Protocol (MCP) server that enables AI assistants like Claude and ChatGPT to interact with a user's Strava data.

Setup Requirements

  • ⚠️Requires Bun runtime installed.
  • ⚠️Requires AWS SAM CLI installed and AWS CLI configured.
  • ⚠️Requires manual retrieval of Strava API Refresh Token via a local web server and browser interaction.
Verified SafeView Analysis
No 'eval' or code obfuscation found. Hardcoded secrets are avoided by loading all sensitive data (Strava API credentials, AUTH_TOKEN) from environment variables. All tool inputs are validated using Zod schemas, mitigating injection risks. Access to the Lambda function URL is secured by a Bearer token authentication middleware that validates against an `AUTH_TOKEN` environment variable. While a broad CORS policy (`AllowOrigins: '*'`) is configured, access remains protected by the required `AUTH_TOKEN`. The `StravaClient` handles OAuth 2.0 token refreshing securely and automatically.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
CodeKeanu icon

steam-mcp

by CodeKeanu

Sec8

Integrates Steam Web API with AI assistants to query game, player, and community data.

Setup Requirements

  • ⚠️Requires a Steam Web API Key (free to obtain).
  • ⚠️Requires your SteamID64 configured as STEAM_USER_ID for 'me'/'my' profile queries.
  • ⚠️Requires Python 3.12+ for developer setup.
  • ⚠️Designed to run as a Model Context Protocol (MCP) `stdio` server, typically integrated with AI assistants like Claude Desktop.
Verified SafeView Analysis
The server correctly uses environment variables for API keys, includes rate limiting and retry mechanisms for external API calls, and handles potential HTML error responses. Input sanitization for Steam IDs is performed. The `get_raw` client method, while general-purpose, is currently only used for specific public Steam Store review endpoints, mitigating immediate risk. HTML parsing within `_html_to_text` and the use of `strip_description_bbcode` help prevent injection, but HTML processing is always a potential area for subtle vulnerabilities.
Updated: 2025-12-31GitHub→
0
0
High Cost
seanshin0214 icon

qualai-mcp

by seanshin0214

Sec9

QualAI is an AI-powered qualitative research server that provides automated coding, thematic analysis, grounded theory building, and methodology selection via a community-driven, RAG-enhanced framework, designed for seamless integration with Claude Desktop.

Setup Requirements

  • ⚠️Requires Claude Desktop as the client to interact with the server.
  • ⚠️An OpenAI API Key (a paid service) is required for semantic search and RAG functionality (when Qdrant is enabled).
  • ⚠️A Qdrant vector database (either via Docker or Qdrant Cloud) is highly recommended for optimal methodology recommendations and RAG capabilities.
  • ⚠️Node.js version 18 or higher is a prerequisite for running the server.
Verified SafeView Analysis
The project demonstrates good security practices by utilizing prepared statements in its SQLite adapter to prevent SQL injection. External API keys for OpenAI, Qdrant, and GitHub are managed via environment variables (process.env) rather than being hardcoded. User research data is stored locally by default, enhancing privacy. There is no visible use of 'eval' or other obviously malicious patterns. Overall, the server appears safe to run.
Updated: 2025-11-28GitHub→
PreviousPage 536 of 760Next