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
ecdeng icon
Sec8

Allows ChatGPT to persistently store, retrieve, and organize recipe files as human-readable Markdown with YAML frontmatter.

Setup Requirements

  • ⚠️Requires persistent disk storage mounted at `/app/recipes` for data retention, especially critical for Docker and Render deployments.
  • ⚠️Authentication relies on a unique UUID in the URL path; this UUID acts as the primary access token and must be kept secret and correctly used in all API calls.
  • ⚠️Deployment to Render requires a Render account and meticulous configuration of a persistent disk at the specified mount path.
Verified SafeView Analysis
The server implements strong filename validation and sanitization to prevent path traversal attacks and enforce file type constraints, which is crucial for file-based storage. Authentication relies on a randomly generated or user-defined UUID embedded in the URL path ('security by obscurity'). While this is explicitly warned against for public sharing, it is deemed acceptable for its intended personal use case where the URL is kept private. No other authentication/authorization layers are present. The server relies on the deployment platform (e.g., Render) to provide HTTPS.
Updated: 2025-12-13GitHub→
0
0
Medium Cost
janjic-portside icon

pervasive-sql-mcp

by janjic-portside

Sec8

Provides a Model Context Protocol (MCP) server for interacting with Pervasive SQL databases via ODBC.

Setup Requirements

  • ⚠️Requires Pervasive ODBC Driver installed and configured on a Windows system.
  • ⚠️Requires DSN (Data Source Name) configured via ODBC Data Source Administrator.
  • ⚠️Requires Visual Studio Build Tools (C++ workload) for compiling the `odbc` native module.
Verified SafeView Analysis
The server runs locally and communicates via stdio, limiting network exposure. Connection credentials can be passed via environment variables or per-tool call, which is standard for local tools. The `query` and `execute_batch` tools allow arbitrary SQL execution, which is a powerful feature and correctly flagged in the README as potentially dangerous if misused (e.g., DELETE/DROP statements). However, SQL queries using parameters are handled securely by `conn.query(sql, params)` preventing SQL injection for parameterized queries. No direct `eval` or intentional obfuscation was found in the provided source code.
Updated: 2025-12-10GitHub→
0
0
Low Cost
Piotr1215 icon

agents-mcp-server

by Piotr1215

Sec3

Facilitates real-time agent-to-agent communication and coordination, leveraging DuckDB for message persistence and `snd` for tmux message injection.

Setup Requirements

  • ⚠️Requires DuckDB CLI to be installed and in the system PATH (not a library, but the command-line tool).
  • ⚠️Requires a custom `snd` script (likely from `~/.claude/scripts/snd`) to be in the system PATH, which is not a standard utility.
  • ⚠️Requires Node.js >= 18.
Review RequiredView Analysis
The server uses `child_process.execSync` to run DuckDB CLI commands, with SQL queries constructed by string concatenation using a custom, manual escaping function (`esc`). This approach is highly vulnerable to SQL injection if the escaping mechanism is flawed or incomplete, allowing malicious input to execute arbitrary DuckDB commands. Additionally, the `snd` command is executed via `spawn`, which could pose an injection risk if the message content or pane ID is not adequately sanitized before being passed to the external `snd` script.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Thamizh-02 icon
Sec9

A knowledge-powered Q&A and action chatbot integrated with GitHub for automated tasks and document management.

Setup Requirements

  • ⚠️Requires a separate backend API server (not provided in this repository) to handle LLM interactions, database operations, and GitHub API calls.
  • ⚠️Requires a GitHub Personal Access Token with appropriate permissions (e.g., for creating issues, PRs, deployments) to be configured.
  • ⚠️Requires a configured database to store users, knowledge sources, conversations, and activity logs.
Verified SafeView Analysis
The application explicitly uses environment variables for sensitive data like API URLs, GitHub tokens, and database credentials, preventing hardcoded secrets. It implements JWT for session management, bcrypt for password encryption, and features role-based access control with tool-level permission checks. An audit trail tracks user actions and tool executions, enhancing accountability. The security of the backend API, which is not provided, would be crucial for overall system security.
Updated: 2025-12-14GitHub→
0
0
Medium Cost

kyma-mcp-server

by ruanxin

Sec7

A server component for the Kyma cloud-native platform, likely managing multi-cloud provisioning or control plane functionalities.

Setup Requirements

  • ⚠️Go runtime environment is required for direct execution outside of Docker.
  • ⚠️Docker is required to build and run the provided Dockerfile.
  • ⚠️Intended for deployment within a Kyma/Kubernetes cluster, requiring cluster access and configuration for full functionality.
Verified SafeView Analysis
No obvious 'eval' or obfuscation from file names. As a server, it inherently exposes network endpoints; actual security depends on code implementation (e.g., input validation, authentication, authorization) not visible from file list. Deployment within a secure Kyma/Kubernetes environment is implied, which typically includes robust security practices.
Updated: 2025-11-18GitHub→
0
0
Medium Cost
nggocnn icon

sonarqube-mcp

by nggocnn

Sec9

Enables AI Agent applications to manage and retrieve code quality and analysis data from a SonarQube server.

Setup Requirements

  • ⚠️Requires Python 3.12 or newer.
  • ⚠️Requires a running SonarQube server instance.
  • ⚠️Requires SonarQube authentication (SONARQUBE_TOKEN or SONARQUBE_USERNAME/SONARQUBE_PASSWORD environment variables must be set).
Verified SafeView Analysis
The server correctly handles sensitive information by requiring it via environment variables (SONARQUBE_TOKEN, SONARQUBE_USERNAME/PASSWORD). It performs input validation for API parameters (e.g., positive page numbers, non-empty strings). The underlying HTTP client (`httpx`) includes timeouts and connection limits, and error handling for network issues. The server binds to '0.0.0.0', which is standard but requires appropriate network configuration (e.g., firewalls) in production environments. No 'eval' or other direct arbitrary code execution patterns were found.
Updated: 2025-11-28GitHub→
0
0
Medium Cost
timduly4 icon

mcp-server

by timduly4

Sec8

Exposes GitHub starred repositories as Model Context Protocol (MCP) resources for LLM applications.

Setup Requirements

  • ⚠️Requires Bazel 8.4+ for the recommended build and run workflow.
  • ⚠️Requires a GitHub Personal Access Token with `public_repo` and `read:user` scopes.
  • ⚠️Interactive testing with the MCP Inspector requires Node.js and npm/npx.
Verified SafeView Analysis
The project avoids hardcoding secrets by requiring a GitHub Personal Access Token via environment variable. It uses OAuth2 for GitHub API authentication. The MCP server runs over stdio (standard input/output), reducing direct network exposure for the core MCP protocol. Simple URI parsing is in place, with awareness of potential routing conflicts documented in tests. No 'eval' or similar dangerous patterns are used, and there is no visible code obfuscation.
Updated: 2025-12-08GitHub→
0
0
Medium Cost
bramburn icon

mcp-fs-server

by bramburn

Sec4

Provides a Model Context Protocol (MCP) server that indexes code repositories for real-time semantic search, leveraging Ollama embeddings and Qdrant for vector storage.

Setup Requirements

  • ⚠️Requires a running Qdrant instance (default: http://localhost:6333).
  • ⚠️Requires Ollama to be installed and running locally, with a compatible embedding model downloaded (default: 'nomic-embed-text').
  • ⚠️Requires Tree-sitter WASM grammar files to be downloaded via `npm run setup` after cloning.
Review RequiredView Analysis
Hardcoded PostHog API key is present in both the MCP server and the VS Code extension's analytics services. This exposes a private API key, although it's for analytics. A more significant concern is the `FileHandler.handleExecuteCommand` in the VS Code extension, which executes arbitrary VS Code commands (`vscode.commands.executeCommand`) based on webview input without apparent whitelisting. This poses a critical vulnerability, as a malicious webview could trigger arbitrary code execution or system modifications within the VS Code environment. While the `ClipboardManager` has a `SENSITIVE_FILE_BLOCKLIST`, this arbitrary command execution could potentially bypass such file-based security checks.
Updated: 2025-12-17GitHub→
0
0
Medium Cost
MicahBly icon

rapport-mcp

by MicahBly

Sec4

Enables AI agents to create, modify, and query visual SVG canvases for Rapport.dev.

Setup Requirements

  • ⚠️Requires Node.js v18.0.0 or higher.
  • ⚠️Initial authentication requires a browser to open for an OAuth login flow, which can be a friction point on headless servers.
  • ⚠️Critical security vulnerabilities are present in the default configuration (insecure file permissions, SSRF, XXE, security bypass) that require immediate fixes post-setup for safe operation.
Review RequiredView Analysis
Critical vulnerabilities identified in a comprehensive security audit. These include insecure file permissions for authentication tokens (making them world-readable by any local user), a Server-Side Request Forgery (SSRF) vulnerability in API requests, and a potential XML External Entity (XXE) vulnerability in XML parsing. There's also a bypass mechanism ('skip_validation' flag) for crucial SVG security checks, incomplete SVG validation patterns, and sensitive data exposure in error messages. Additionally, HTTPS enforcement is missing, and authentication polling lacks robust rate limiting/exponential backoff. Immediate remediation of HIGH and MEDIUM severity issues is strongly recommended.
Updated: 2025-12-11GitHub→
0
0
High Cost
Samicostox icon

rapidchart-mcp

by Samicostox

Sec5

Facilitates the generation and management of AI-powered diagrams from code within the Cursor IDE by acting as a Model Context Protocol (MCP) server for RapidChart.

Setup Requirements

  • ⚠️Requires a `RAPIDCHART_API_TOKEN` which must be generated from rapidchart.com settings.
  • ⚠️Requires Python 3.10 or newer.
  • ⚠️Diagram creation can experience 503 Service Unavailable timeouts due to Heroku's 30-second router limit for complex diagrams, even if the diagram is created successfully on the RapidChart backend. Users must manually verify diagram creation via `list_diagrams`.
Review RequiredView Analysis
The `httpx.AsyncClient` in `src/rapidchart_mcp/client.py` hardcodes `verify=False` for SSL certificate validation. While commented as 'For self-signed certs in dev', this disables crucial security checks for all API communication with the RapidChart API, making it vulnerable to Man-in-the-Middle (MITM) attacks if the `RAPIDCHART_API_URL` is compromised or untrusted. This setting is applied universally and cannot be configured or disabled for production use. No 'eval' or direct arbitrary code execution from user input was found. The API token is handled via environment variables, which is good practice.
Updated: 2026-01-17GitHub→
0
0
Low Cost
nghialuong53 icon

vn-radio-mcp

by nghialuong53

Sec8

Simple MCP server and HTTP proxy for streaming Vietnamese radio to web clients, MCP-enabled applications, and robots.

Setup Requirements

  • ⚠️User must update `streamSrc` in `channels.json` with real and trusted radio stream URLs for functionality and security.
  • ⚠️Requires Node.js >= 18.
Verified SafeView Analysis
The server acts as an HTTP proxy, forwarding requests to `streamSrc` URLs defined in `channels.json`. While `channels.json` is a static, user-configured file, the user is responsible for ensuring these `streamSrc` URLs are trusted and valid to prevent potential Server-Side Request Forgery (SSRF) or other malicious data injection. No `eval`, code obfuscation, or hardcoded secrets were found in the provided source code snippets. The explicit instruction to replace placeholder URLs with trusted ones mitigates risk.
Updated: 2025-12-02GitHub→
0
0
Low Cost
afaraha8403 icon

MCP-Scooter

by afaraha8403

Sec3

MCP Scout acts as a local-first management and gateway system for AI tools, designed to reduce context bloat and simplify configuration for AI agents interacting via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Go 1.24+, Node.js 18+, Rust (with rustup.rs), and Make to build and run from source.
  • ⚠️Default control server (6200) and MCP Gateway (6277) ports may conflict with other applications, requiring manual intervention or killing processes.
  • ⚠️The primary way to consume tools is via a registry that executes remote NPM packages using `npx -y`, posing a significant supply chain and arbitrary code execution risk if registry entries are malicious or compromised.
Review RequiredView Analysis
The project uses good practices for local network binding and credential storage (OS Keychain). However, a critical security vulnerability exists in its tool runtime configuration. The `runtime` definitions for tools (e.g., in `github.json`, `brave-search.json`) specify `"command": "npx", "args": ["-y", "@scope/package-name"]`. The `npx -y` command automatically installs and executes arbitrary npm packages without explicit user confirmation. This creates a severe supply chain risk where a malicious MCP tool definition, whether from a compromised 'community' registry or a locally injected definition, could lead to arbitrary code execution on the user's machine. While the `scooter_code_interpreter` uses a sandboxed JavaScript engine (`goja`), the `npx -y` mechanism bypasses this sandbox for external tool execution. Additionally, the `kill_process` Tauri command, while for a legitimate purpose (port conflict resolution), grants the UI the ability to terminate arbitrary processes by PID, which is a high-privilege action.
Updated: 2026-01-17GitHub→
PreviousPage 406 of 760Next