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
bans1mp icon

mcp-server

by bans1mp

Sec3

The server provides an agent-callable interface for interacting with Spotify's API to retrieve top songs and for updating local notes.

Setup Requirements

  • ⚠️Requires a valid Spotify Access Token for the `GetTopSongs` tool, which must be provided to the `auth` package (likely via environment variable).
  • ⚠️The server requires write permissions to a local 'assets' directory for the `UpdateNotes` tool.
Review RequiredView Analysis
The `auth.SpotifyAccessToken` variable used for Spotify API authorization is directly accessed without its origin being shown. If this token is hardcoded within the `auth` package (which is part of the same repository), it represents a critical security vulnerability, exposing a sensitive secret. Ensure this token is loaded securely, ideally from environment variables, and never hardcoded. The `UpdateNotes` tool writes user-provided content to a local file (`notes.txt`); while this is contained, it could lead to integrity issues for that specific file if the input is untrusted. No 'eval' or obfuscation found.
Updated: 2025-11-29GitHub→
0
0
Low Cost
dvansari65 icon

anchor-mcp-server

by dvansari65

Sec3

An MCP server that enables programmatic deployment of Anchor programs to various Solana networks via a defined tool interface.

Setup Requirements

  • ⚠️Requires the 'anchor' CLI tool to be installed and accessible in the system's PATH.
  • ⚠️Requires Rust and Cargo to be installed for building and running the server.
  • ⚠️Requires network access to the specified Solana cluster (devnet, testnet, mainnet-beta, localnet) for program deployment.
Review RequiredView Analysis
The 'deploy_program' function in `src/anchor/mod.rs` directly invokes the 'anchor deploy' command using `std::process::Command` with user-supplied `program_path` and `network` arguments. This design introduces a critical command injection vulnerability if inputs from the MCP client are not thoroughly validated and sanitized. A malicious actor could potentially craft inputs to execute arbitrary commands on the host system.
Updated: 2025-11-22GitHub→
0
0
Low Cost
Mado1968 icon

TTiA

by Mado1968

Sec9

This repository provides the source code for a modern marketing website for 'TTiA', a company specializing in Model Context Protocol (MCP) servers, digital transformation, and consulting services, showcasing their offerings and allowing potential clients to get in touch.

Setup Requirements

  • ⚠️Node.js (>=18 is recommended by dependencies like esbuild, vite, google-auth-library)
  • ⚠️GEMINI_API_KEY environment variable is required if the integrated Google GenAI features are fully implemented and utilized for interactive AI functionality.
Verified SafeView Analysis
The provided source code is for a client-side React application and primarily handles UI rendering and client-side form submission simulation. There are no direct server-side components or custom server logic that would introduce common backend vulnerabilities. Hardcoded secrets are not present; `GEMINI_API_KEY` is correctly handled as an environment variable via Vite. The `@google/genai` dependency is a legitimate library for AI interaction, and its usage within the application, if implemented, would require secure handling of prompts and responses to prevent prompt injection or data leakage. Given that the contact form's submission is simulated (`setTimeout`) and no actual API calls are shown for sensitive data, the current code snippet itself has a high security posture for a static site. Potential risks would lie in any actual backend APIs this frontend interacts with (not provided here) or vulnerabilities in its dependencies.
Updated: 2025-12-14GitHub→
0
0
Medium Cost

dixa-mcp-server

by Dixa-public

Sec9

This server provides tools for interacting with the Dixa API to manage conversations, tags, end users, agents, and analytics.

Setup Requirements

  • ⚠️Requires a Dixa API Key, implying a Dixa account and potential costs from Dixa for API usage.
  • ⚠️Requires Node.js and npm to install dependencies and run the server.
  • ⚠️The Claude integration requires manually specifying the absolute path to the server's entry point (`/PATH/TO/FOLDER/dixa-mcp-server/src/tools/index.ts`).
Verified SafeView Analysis
The server primarily acts as a wrapper for the Dixa API, requiring an API key. No 'eval' or obfuscation is apparent. The main security consideration is the secure handling and storage of the DIXA_API_KEY. If exposed publicly, the FastMCP server itself would require proper authentication and authorization.
Updated: 2025-11-17GitHub→
0
0
Medium Cost

mcp-servers

by zchee

Sec5

This repository appears to contain different server implementations focused on memory management, sequential thinking, and vector database integration for AI agents.

Setup Requirements

  • ⚠️Requires external Weaviate instance (local Docker, self-hosted, or cloud) for vector database operations.
  • ⚠️Specific runtime environments (e.g., Python, Node.js, Go) for server components are unknown due to lack of a README.
  • ⚠️No setup instructions or documentation available, making initial setup highly challenging and speculative.
Review RequiredView Analysis
Cannot inspect code directly, but the project includes server components (`sequential-thinking-server`, `weaviate`) without a README, increasing unknown network exposure risks and making it impossible to audit for 'eval' or obfuscation. Lack of documentation makes it difficult to assess security posture.
Updated: 2025-11-17GitHub→
0
0
Low Cost
HiteshKumarMeghwar icon

expense-tracker-mcp

by HiteshKumarMeghwar

Sec9

A local MCP server for tracking and managing personal or business expenses, designed for integration with client applications like Claude Desktop.

Setup Requirements

  • ⚠️Requires 'uv' package manager for setup and running.
  • ⚠️Requires Python 3.11 or newer.
  • ⚠️Intended for use with Claude Desktop for full intended functionality (implied by README).
Verified SafeView Analysis
SQL injection is prevented by using parameterized queries. No 'eval' or similar dangerous functions are used. No hardcoded secrets or significant network risks identified within the provided source code. The database is a local SQLite file.
Updated: 2025-11-27GitHub→
0
0
High Cost
pchavez2029 icon

cailculator-mcp

by pchavez2029

Sec6

Provides AI agents with high-dimensional mathematical analysis and financial trading tools using 'pathological' Cayley-Dickson and Clifford algebras.

Setup Requirements

  • ⚠️Requires a paid API key from the CAILculator portal (https://cailculator-mcp-production.up.railway.app/).
  • ⚠️Depends on an external authentication server for API key validation.
  • ⚠️Python 3.10+ is required.
  • ⚠️Aiohttp is needed for HTTP transport mode (`pip install cailculator-mcp[http]`).
Verified SafeView Analysis
The companion `auth_server` (part of the same repository) uses a broad `allow_origins=["*"]` for CORS, which is a significant security risk for an authentication service if deployed without restriction in production. Additionally, the Stripe webhook handler has a development fallback that bypasses signature verification if `STRIPE_WEBHOOK_SECRET` is not set. The core MCP server itself avoids direct execution of user-supplied code (e.g., `eval`, `exec`) and relies on `os.getenv` for sensitive configurations, but the external authentication dependency introduces a potential single point of failure.
Updated: 2025-12-05GitHub→
0
0
Medium Cost
CeeArEx icon
Sec9

An autonomous Model Context Protocol (MCP) server designed for LLMs to build, debug, and maintain Rust projects, specifically architected to help LLMs create other MCP servers.

Setup Requirements

  • ⚠️Requires Rust and Cargo to be installed on the host system.
  • ⚠️Requires the 'rust-docs' component to be added via `rustup component add rust-docs` for full documentation search functionality.
  • ⚠️Requires an initialized Git repository in the working directory for `git_operations` to function.
  • ⚠️Client configuration needs an absolute path to the compiled `mcp-rust-builder` executable.
Verified SafeView Analysis
The server uses `std::process::Command` extensively to run `cargo` and `git` commands. Inputs to these commands are generally validated and constrained (e.g., specific project paths, crate names, predefined git operations, regex-validated error codes), limiting arbitrary command injection. Path arguments are explicitly converted to `PathBuf` and checked for existence. The `patch_file` tool operates with a first-match replacement and provides diagnostics for whitespace errors rather than full file overwrites, enhancing safety. 'cargo add' and 'cargo test' inherently involve network requests to crate registries, which is expected behavior for a Rust development agent. No direct use of 'eval' or hardcoded secrets found. The overall design prioritizes controlled execution within a development context.
Updated: 2025-11-25GitHub→
0
0
High Cost
mindfulent icon

slashAI

by mindfulent

Sec9

A privacy-aware Discord AI assistant and MCP server that provides persistent memory, scheduled reminders, Minecraft build recognition, and agentic tools.

Setup Requirements

  • ⚠️Requires an Anthropic API Key (paid service for Claude models).
  • ⚠️Requires a Voyage AI API Key (paid service for embeddings).
  • ⚠️Requires a PostgreSQL database with the pgvector extension.
  • ⚠️Requires DigitalOcean Spaces API Keys and Bucket for image storage (paid service).
  • ⚠️Requires configuring a Discord Bot application and retrieving its token and the owner's Discord ID.
Verified SafeView Analysis
The project demonstrates strong security practices: API keys and sensitive configurations are managed via environment variables. Webhook endpoints are protected with an API key. SQL interactions use parameterized queries to prevent injection. GitHub documentation access is restricted to a hardcoded repository and validated paths to prevent traversal. A robust privacy model segregates memories by channel type and user ownership, with explicit validation for 'global safe' facts. Agentic tools for Discord actions are restricted to a configurable owner ID. Image processing limits (size, dimensions) mitigate some risks. Regular updates of external dependencies are crucial for maintaining security.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
arunselvarajdb icon

ynab-mcp-server

by arunselvarajdb

Sec9

A read-only Model Context Protocol (MCP) server for interacting with YNAB budgets, providing tools and resources for querying financial data and generating spending insights.

Setup Requirements

  • ⚠️Requires a YNAB Personal Access Token (Free, but requires YNAB account and setup)
  • ⚠️Requires 'uv' package manager for dependency management and running (not pip)
  • ⚠️Requires Python 3.11 or higher
Verified SafeView Analysis
The server demonstrates strong security practices, including Pydantic-based environment variable validation (specifically checking for placeholder YNAB_API_TOKEN), a read-only design, and comprehensive security documentation detailing API token handling, dependency auditing (Bandit, pip-audit), pre-commit hooks (detect-secrets), and a vulnerability reporting policy. CORS is set to allow all origins in debug mode for HTTP, which is noted to be restricted in production. No 'eval' or other highly dangerous patterns were found.
Updated: 2025-11-23GitHub→
0
0
Low Cost
cloudaeon-pvt-ltd icon

mcp-servers

by cloudaeon-pvt-ltd

Sec5

This server enables sending emails through Microsoft Outlook/Office 365 using the Microsoft Graph API, triggered by an MCP-compatible client.

Setup Requirements

  • ⚠️Requires an existing Microsoft 365/Azure AD tenant.
  • ⚠️Requires Azure App Registration with specific 'Mail.Send' application permissions and administrative consent.
  • ⚠️Requires Python 3.12+.
  • ⚠️Sensitive credentials (SENDER_EMAIL_ID, TENANT_ID, CLIENT_ID, CLIENT_SECRET) must be securely managed as environment variables.
Review RequiredView Analysis
The server retrieves sensitive credentials (CLIENT_ID, CLIENT_SECRET, TENANT_ID) from environment variables, which is good practice. However, the `send_email` function allows an MCP client to specify an `attachment_file_path`. While `os.path.normpath` is used for cleanup, the server attempts to open and base64 encode *any* path provided by the client if it has read access. This poses a significant Local File Inclusion (LFI) risk, allowing a malicious MCP client to potentially read and email arbitrary files from the server's filesystem. Additionally, the `Mail.Send` application permission, as highlighted in the README, allows sending emails as *any* user in the tenant, which is a powerful capability that could be misused by an untrusted client. There are no obvious `eval` or obfuscation patterns.
Updated: 2025-12-10GitHub→
0
0
Medium Cost
amiralamox icon

mcp-servers

by amiralamox

Sec8

Enables an AI agent (Claude) to interact with Jira, retrieving and analyzing project management data via JQL queries.

Setup Requirements

  • ⚠️Python 3.12+ required
  • ⚠️Jira account with API access (username/API token) required
  • ⚠️Claude Desktop configuration required to connect the MCP server
  • ⚠️Environment variables (.env file) must be set for Jira credentials and may need adjustment for custom field IDs specific to your Jira instance
Verified SafeView Analysis
The server loads Jira credentials and custom field IDs from environment variables using `python-dotenv`, which is good practice. It runs locally (127.0.0.1:5000), limiting network exposure. JQL queries are passed directly to the Jira API via `requests`. While direct JQL passing is the core functionality, it relies on the Jira API's sanitization; the server itself does not appear to execute arbitrary system commands or `eval` client-provided strings.
Updated: 2025-12-04GitHub→
PreviousPage 317 of 760Next