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(379)

100
3277
Medium Cost
antvis icon
Sec8

Generates various data visualization charts (including common charts and maps) using the AntV engine, facilitating data analysis and presentation through a Model Context Protocol server.

Setup Requirements

  • ⚠️Relies on an external AntV chart generation service (`VIS_REQUEST_SERVER`) for rendering charts; charts are not generated locally by this server.
  • ⚠️Geographic visualization tools (`generate_district_map`, `generate_path_map`, `generate_pin_map`) are limited to map generation within China due to AMap service integration.
  • ⚠️Requires Node.js to run directly via `npx` or `node`.
Verified SafeView Analysis
No direct 'eval' or code obfuscation found. The server relies on an external AntV chart generation service (`VIS_REQUEST_SERVER`) for rendering, which implies trust in that external service. The `streamable` HTTP transport uses `cors` with `origin: '*'`, which is a broad policy that allows cross-origin requests from any domain. If publicly exposed, this endpoint should be protected with additional authentication/authorization layers.
Updated: 2025-12-05GitHub→
100
37809
Medium Cost
sansan0 icon

TrendRadar

by sansan0

Sec8

News aggregation, trend analysis, and multi-channel notification based on user-defined keywords, with AI analysis capabilities.

Setup Requirements

  • ⚠️GitHub Actions users must adhere to strict resource limits (e.g., ~10 platforms, 30-minute minimum interval) to avoid account suspension risks.
  • ⚠️Sensitive credentials (Webhook URLs, API keys) must be stored in GitHub Secrets or Docker `.env` files, NOT in `config/config.yaml` if the repository is public.
  • ⚠️AI analysis features require locally accumulated news data; users must run the main TrendRadar crawler first to generate `output` directory data before using AI tools.
  • ⚠️Docker deployment is recommended for unrestricted usage, as GitHub Actions may have limitations.
Verified SafeView Analysis
The project emphasizes secure handling of sensitive credentials (Webhook URLs, API keys, email passwords) by recommending GitHub Secrets or `.env` files, rather than committing them to public `config.yaml`. The MCP server, when run via Docker Compose, is securely bound to `127.0.0.1` by default. HTML content is escaped to mitigate basic XSS risks. The application makes extensive use of external APIs, which is an inherent network risk, but the calls appear to be standard HTTP/S requests with timeouts. No direct use of `eval` or intentional obfuscation was observed.
Updated: 2025-12-06GitHub→
100
8156
Low Cost
open-metadata icon

OpenMetadata

by open-metadata

Sec9

Exposes REST APIs for managing Apache Airflow DAGs and OpenMetadata workflow definitions, enabling programmatic deployment and lifecycle management of data pipelines.

Setup Requirements

  • ⚠️Requires Apache Airflow to be pre-installed, specifically version `2.3.3`.
  • ⚠️Requires installing a Python package (`openmetadata-airflow-managed-apis`) in the Airflow scheduler and webserver Python environments.
  • ⚠️Requires specific configuration in `airflow.cfg` under `[openmetadata_airflow_apis]`.
Verified SafeView Analysis
The UI code interacts with backend APIs using JWT for authentication, a standard and generally secure practice. Connection configurations (e.g., AWS credentials, database passwords) are defined in schemas, implying they should be securely provided at deployment/runtime, not hardcoded. No direct 'eval', obfuscation, or malicious patterns were observed in the provided UI code snippets. Assumes secure configuration of underlying Airflow and OpenMetadata services.
Updated: 2025-12-06GitHub→
100
1942
Medium Cost
grafana icon

mcp-grafana

by grafana

Sec9

Provides an MCP interface to Grafana, enabling AI assistants to interact with dashboards, datasources, Prometheus, Loki, incidents, alerting, OnCall, Sift, Pyroscope, and admin functionalities for observability and automation.

Setup Requirements

  • ⚠️Requires Grafana version 9.0 or later for full functionality (some API endpoints are missing in older versions).
  • ⚠️Requires a Grafana API key (service account token) or username/password for authentication, which must be configured via environment variables or HTTP headers.
  • ⚠️Docker is required to run the provided Docker image or for integration tests.
Verified SafeView Analysis
The server correctly uses environment variables for sensitive credentials (API keys, passwords) and supports TLS configuration for both client (connecting to Grafana) and server (Streamable HTTP transport) connections. Access control is delegated to Grafana's RBAC system, requiring specific permissions for each tool, which is well-documented. The use of `gval` for JSONPath evaluation is a controlled query language, not arbitrary code execution. The `--tls-skip-verify` flag is explicitly marked as insecure and intended for development/testing purposes, not production use. No 'eval' or obvious malicious patterns were found in the provided source code.
Updated: 2025-12-05GitHub→
99
800
Medium Cost
golf-mcp icon

golf

by golf-mcp

Sec4

Golf is a Python framework for building MCP (Model Context Protocol) servers, allowing developers to define tools, resources, and prompts as Python files to create runnable AI agent backends.

Setup Requirements

  • ⚠️Requires Python 3.10+ (recommended, `pyproject.toml` specifies `>=3.8`).
  • ⚠️Strict dependency on `fastmcp==2.12.5` (or `>=2.11.0` for auth features).
  • ⚠️OAuth proxy authentication (an advanced feature) requires a separate `golf-mcp-enterprise` package.
  • ⚠️Requires external LLM API keys (e.g., OpenAI, Anthropic) if using `sample` or `elicit` utilities.
Review RequiredView Analysis
The `src/golf/examples/basic/tools/calculator.py` tool uses `eval()` to evaluate mathematical expressions. While it attempts to sanitize input with a character whitelist, `eval()` is inherently dangerous when processing untrusted input as it can lead to arbitrary code execution if not handled with extreme care and robust sanitization. The framework dynamically loads and executes user-provided `startup.py`, `middleware.py`, `health.py`, and `readiness.py` files, which means the overall security of a deployed server heavily depends on the security practices within the user's own project code. A default PostHog API key for anonymous telemetry is hardcoded in `src/golf/core/telemetry.py`, though it's a public client-side key and can be overridden by an environment variable. OAuth configurations include robust URL validation to mitigate SSRF and enforce HTTPS in production, which is a good security practice.
Updated: 2025-11-24GitHub→
99
963
High Cost
openops-cloud icon

openops

by openops-cloud

Sec7

A No-Code FinOps automation platform that helps organizations reduce cloud costs and streamline financial operations by providing customizable workflows to automate key FinOps processes like allocation, unit economics, anomaly management, workload optimization, and safe de-provisioning.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for deployment.
  • ⚠️Requires PostgreSQL and Redis databases.
  • ⚠️Default placeholder secrets (e.g., API keys, passwords) in `values.yaml` must be changed immediately for production environments.
  • ⚠️Requires Node.js v18 or v20 for development and build processes.
  • ⚠️Integrations with cloud providers (AWS, Azure, Google Cloud) and various third-party services will require their respective API keys and configurations, potentially incurring additional costs and setup complexity.
Verified SafeView Analysis
The project demonstrates strong security awareness, including password hashing (bcrypt, firebase-scrypt), encryption of sensitive data (AES-256-CBC), input sanitization for CLI commands (shell-quote), and webhook signature verification for Slack. Crucially, it employs `isolated-vm` for sandboxing code execution, a critical measure for a platform running user-provided code. Logging includes redaction of sensitive patterns. However, the extensive number of external integrations (AWS, Azure, Google Cloud, Microsoft Graph, Slack, Jira, etc.) significantly expands the attack surface. Default CORS settings allowing all origins ('*') can be a security risk if not mitigated by external proxies or strict API key usage. While `isolated-vm` is a robust control for code execution, the presence of `eval` and `Function` constructor in some sandbox modes (e.g., no-op) requires careful scrutiny to ensure they are not used in high-privilege contexts. Default placeholder secrets in configuration files (`values.yaml`) must be changed immediately for production deployment.
Updated: 2025-12-05GitHub→
98
615
Low Cost
bgauryy icon

octocode-mcp

by bgauryy

Sec9

Enables AI assistants to conduct deep, secure, and token-efficient code research across GitHub repositories by providing structured access and analysis tools.

Setup Requirements

  • ⚠️Node.js >= 18.12.0 is a prerequisite for running the server.
  • ⚠️Requires GitHub authentication (either GitHub CLI with 'gh auth login' or a Personal Access Token with `repo`, `read:user`, `read:org` scopes).
  • ⚠️By default, metadata about tool usage, errors, and rate limits is logged to an external Octocode service, which can be disabled by setting `LOG=false`.
Verified SafeView Analysis
The server employs robust security measures: comprehensive input validation to prevent prototype pollution and enforce size limits; extensive output sanitization using over 1000 regex patterns to redact sensitive data (API keys, tokens, PII) before it reaches the AI model; and masking of sensitive information in logs and error messages. It prioritizes GitHub CLI authentication for secure token management, with environment variable fallback. Session logging to an external endpoint (octocode-mcp-host.onrender.com) collects metadata (tool usage, repos, research goals, errors, rate limits); this is a potential privacy consideration, but it's explicit about not sending sensitive content and logging can be disabled via the `LOG` environment variable.
Updated: 2025-11-29GitHub→
92
93
Low Cost
mcp-shark icon

mcp-shark

by mcp-shark

Sec8

Aggregate multiple Model Context Protocol (MCP) servers into a single unified interface with a powerful monitoring UI, enabling real-time traffic capture, logging, and AI-powered security analysis.

Setup Requirements

  • ⚠️Requires Node.js 18+ to run the application.
  • ⚠️The 'Smart Scan' feature interacts with an external, potentially paid, AI security analysis service (smart.mcpshark.sh). An API token from this service is required to use the feature, and it will send MCP server metadata to the external service.
  • ⚠️Requires an existing Model Context Protocol (MCP) configuration file (e.g., `~/.cursor/mcp.json`) to function, as it acts as a monitoring proxy for existing MCP server setups, not as a standalone MCP server.
Verified SafeView Analysis
The application functions as a local proxy and monitoring tool for Model Context Protocol (MCP) traffic. It captures and displays all requests/responses between MCP clients and configured servers. A key feature, 'Smart Scan', sends MCP server metadata (such as tool schemas, resource URIs, and prompt arguments) to an external API hosted at `https://smart.mcpshark.sh` for AI-powered security analysis. While this data outflow is explicitly part of a feature, users should be aware that their MCP server configurations are shared with a third-party service. An API token, required for Smart Scan, is stored locally on the user's machine. Configuration files are read from and written to the local filesystem, utilizing Node.js `path.join` and `homedir()` for path resolution, which generally mitigate common path traversal vulnerabilities. The core MCP Shark server is spawned as a child process by the UI server, granting the UI process privileges to execute other programs locally. No direct `eval` calls or intentional code obfuscation were found in the provided source code snippets. The security considerations primarily revolve around the intentional data sharing with the external Smart Scan service and the local file system operations inherent to the tool's design, rather than specific code vulnerabilities.
Updated: 2025-12-06GitHub→
92
72
High Cost
mihaelamj icon

cupertino

by mihaelamj

Sec8

Local Apple Developer documentation crawler and Model Context Protocol (MCP) server for AI agents, providing offline access and structured API information.

Setup Requirements

  • ⚠️Requires macOS 15+ (Sequoia)
  • ⚠️Requires ~2-3 GB of disk space for full documentation download
  • ⚠️Apple ID is required for fetching sample code directly from Apple (though GitHub mirror is an alternative)
Verified SafeView Analysis
The project uses standard macOS security features like WKWebView's sandbox for crawling and delegates Apple ID authentication to Safari, which is good practice. The MCP server operates locally via stdio, eliminating network exposure. Input for GitHub identifiers is sanitized to prevent path traversal. However, local storage of `.auth-cookies.json` for Apple sample code downloads, while typical for client tools, implies unencrypted storage which is a potential risk if the local machine's permissions are not properly managed. The `install.sh` script uses `sudo` for `/usr/local/bin` installation, which is standard but requires user trust.
Updated: 2025-12-06GitHub→
89
25
High Cost
VladyslavMykhailyshyn icon

ukrainian-stats-mcp-server

by VladyslavMykhailyshyn

Sec9

Provides AI models with structured access to Ukrainian statistical data from the State Statistics Service of Ukraine via their SDMX API v3, including comprehensive metadata and flexible data retrieval.

Setup Requirements

  • ⚠️Requires Node.js 18 or higher.
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json`.
  • ⚠️Requires internet connectivity to `https://stat.gov.ua` to fetch data.
Verified SafeView Analysis
The server code does not appear to contain malicious patterns, 'eval' usage, or hardcoded sensitive secrets. It acts as a proxy to a public SDMX API, converting XML responses to JSON. The installation script, while performing global npm operations, does not use suspicious commands. All tool arguments are passed directly, not evaluated as code, mitigating injection risks. The `baseURL` for the public Ukrainian Statistics API is hardcoded, which is acceptable for a public, non-credentialed service.
Updated: 2025-11-30GitHub→
88
22
Low Cost
clumsynonono icon

ethereum-mcp

by clumsynonono

Sec9

Ethereum data analytics for Research Incentive Group (RIG) research, covering Blob, DEX, Staking, MEV, BuilderNet, and L2 MEV metrics.

Setup Requirements

  • ⚠️Requires a Dune Analytics API Key (`DUNE_API_KEY`) to be set in the `.env` file.
  • ⚠️Most data tools require manual configuration of Dune Query IDs in `src/utils/queryConfig.ts` before they can fetch data.
  • ⚠️Requires `npm install` and `npm run build` to be executed once after cloning and after modifying `src/utils/queryConfig.ts`.
  • ⚠️Requires restarting the Claude Desktop application for configuration changes to take effect.
Verified SafeView Analysis
The server acts as a wrapper around the Dune Analytics API, making HTTP requests to `api.dune.com` using an API key. There are no 'eval' or arbitrary code execution vulnerabilities identified within the provided source. Input parameters for Dune queries (`query_id`, `limit`, etc.) are passed to the Dune API, not executed locally. The `DUNE_API_KEY` is loaded from an environment variable, which is good practice. The explicit `execute_query` tool requires user confirmation, mitigating accidental credit consumption.
Updated: 2025-11-27GitHub→
88
22
Low Cost
clumsynonono icon

ethereum-dune-mcp

by clumsynonono

Sec9

Ethereum blockchain data analytics and research for RIG (Research Incentive Group), providing metrics on Blob, DEX, Staking, MEV, and L2 activities via Dune Analytics.

Setup Requirements

  • ⚠️Requires a Dune API Key (free registration, but API calls can consume credits).
  • ⚠️Many tools require manual configuration of Dune Query IDs in `src/utils/queryConfig.ts` after finding them on Dune Analytics.
  • ⚠️Requires configuration within `claude_desktop_config.json` with the absolute path to the compiled `index.js` file.
Verified SafeView Analysis
The server loads the Dune API key from environment variables (`.env`), preventing hardcoding of secrets. Most data retrieval uses cached results, which are free. The `execute_query` tool, which can consume Dune API credits, explicitly requires a `confirm: true` argument, adding a layer of protection against unintended API usage and associated costs. No `eval` or other highly dangerous dynamic code execution patterns were found.
Updated: 2025-11-27GitHub→
PreviousPage 1 of 32Next