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
vtnhogg icon

mcp-server

by vtnhogg

Sec8

Provides client-side auto-configuration for AI assistants to access 306+ APIs through APIVerve's remotely hosted Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires signup and an API key from APIVerve for authentication (OAuth 2.0).
  • ⚠️The provided source code is a client configurator, not a local MCP server; the actual APIVerve MCP server is hosted remotely.
  • ⚠️Requires an existing MCP-compatible client (e.g., Claude Desktop, VS Code with Cline, Cursor) to be installed.
Verified SafeView Analysis
The provided source code for 'mcp-server' (specifically `bin/install.js` for NPM and `apiverve_mcp/__init__.py` for PyPI) functions solely as an installer/configurator for MCP-compatible clients (Claude Desktop, VS Code, Cursor). Its purpose is to modify local user configuration files to add an entry pointing to APIVerve's *remotely hosted* MCP server at `https://api.apiverve.com/v1/mcp`. The actual server logic that processes MCP requests and bridges to APIVerve's 306+ APIs is not present in the provided source code. For instance, the `index.js` file, hinted at in `npm/package.json` for a local server setup, is absent. The installer scripts themselves are straightforward JSON manipulators for known configuration paths and do not use dangerous functions like `eval` or obfuscation, nor do they contain hardcoded secrets. The primary action is modifying user configuration files, which is its stated purpose.
Updated: 2026-01-19GitHub→
0
0
Low Cost
ClarkSauce icon

allowed-servers

by ClarkSauce

Sec10

To define and manage a curated list of allowed Managed Code Platform (MCP) servers for an organization, specifying their metadata and execution details.

Setup Requirements

  • ⚠️Requires Node.js and npm/npx to execute the referenced MCP servers (e.g., Playwright's test server).
Verified SafeView Analysis
The provided source code consists solely of a README and a JSON configuration file. It contains no executable logic, 'eval' statements, obfuscation, hardcoded secrets, or direct network operations, making it inherently safe on its own. Any potential risks would stem from the security posture of the external MCP servers it configures (e.g., the 'playwright' package), which is outside the scope of this repository's code.
Updated: 2025-11-25GitHub→
0
0
High Cost
GlacierEQ icon
Sec2

Orchestrates cross-platform AI tools, integrates with numerous APIs, provides infinite memory, and deploys multi-engine AI workflows for complex automation.

Setup Requirements

  • ⚠️Requires numerous API keys for various paid AI services (OpenAI, Anthropic, DeepSeek, Groq, Perplexity) and integration platforms (GitHub, Notion, Supermemory, Mem0, Jira, ElevenLabs, Pinecone), which must be configured as environment variables.
  • ⚠️Contains hardcoded API keys in `aspen_grove_network_integration.py` that MUST be removed or replaced with environment variables for security before deployment.
  • ⚠️Requires Node.js and npm (for `npx install-mcp` commands specified in `aspen_grove_network_integration.py`) for full MCP client integration capabilities.
Review RequiredView Analysis
CRITICAL VULNERABILITY: The `aspen_grove_network_integration.py` file contains hardcoded API keys for Supermemory and Mem0. These keys are sensitive and should always be loaded from environment variables or a secure vault. Additionally, the `terminal.exec` tool, while attempting sandboxing with allowed/blocked commands, introduces a risk of arbitrary code execution if security constraints are bypassed or misconfigured. This combination of hardcoded secrets and command execution capabilities severely impacts the security posture.
Updated: 2025-11-23GitHub→
0
0
Low Cost
nbjoin icon

resolve-tools

by nbjoin

Sec8

Provides a versioned Retrieval-Augmented Generation (RAG) knowledge base for DaVinci Resolve documentation, integrating with AI assistants like Claude Desktop and VS Code via an MCP server for accurate, cited information.

Setup Requirements

  • ⚠️Requires manual placement of DaVinci Resolve PDF manuals (e.g., 'DaVinci-Resolve-19-manual.pdf') in the repository root.
  • ⚠️The example MCP client configuration (for Claude Desktop) contains a hardcoded path (`/Users/nick/Documents/GitHub/nbjoin/resolve-tools`) that users must adjust to their local repository location.
  • ⚠️Requires initial 'build_kb.py' execution to process PDFs and populate the knowledge base before the server can be used.
Verified SafeView Analysis
The server appears generally safe for its intended use as a local RAG system. It utilizes standard Python libraries (pymupdf, chromadb, sentence-transformers) for PDF parsing, vector storage, and embeddings. File operations are confined to user-provided PDFs and a local persistence directory. There are no clear indicators of 'eval' or other direct code injection vulnerabilities. The use of `sys.path.insert` in `mcp_server/server.py` is noted but for internal module resolution, not directly exploitable in this context. The primary security consideration would be potential vulnerabilities in underlying third-party libraries (e.g., PyMuPDF when parsing untrusted PDFs), which is outside the scope of the custom server logic.
Updated: 2026-01-19GitHub→
0
0
Low Cost
pixelaw icon
Sec10

Provides expert-level documentation and guidance for PixeLAW application development on Starknet using the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Node.js and npm for installation and execution.
  • ⚠️Requires manual configuration of the absolute path to the server's executable (`dist/index.js`) in the Claude Code or Claude Desktop MCP settings.
Verified SafeView Analysis
The server reads hardcoded local Markdown files based on tool requests, limiting risk. No dynamic code execution, external network requests (beyond MCP protocol), or hardcoded sensitive credentials were detected in the provided source. It operates via standard I/O, which is a secure local transport for this documentation-focused use case.
Updated: 2025-12-05GitHub→
0
0
Low Cost
ineersa icon

mcp-sql-server

by ineersa

Sec2

An MCP server for executing SQL queries against various configured databases.

Setup Requirements

  • ⚠️Requires `DATABASE_CONFIG_FILE` environment variable to be set, pointing to a Doctrine DBAL YAML configuration.
  • ⚠️Requires specific PHP PDO extensions (e.g., `pdo_mysql`, `pdo_pgsql`, `pdo_sqlsrv`, `pdo_sqlite`) depending on configured databases.
  • ⚠️Requires Docker for running and testing with MySQL, PostgreSQL, and SQL Server containers.
  • ⚠️SQL Server extension (`pdo_sqlsrv`) may require manual installation and specific drivers depending on the operating system.
Review RequiredView Analysis
CRITICAL SQL INJECTION VULNERABILITY: The `QueryTool` directly executes user-provided SQL queries via `Doctrine\DBAL\Connection::executeQuery($query)`. If the `$query` argument is sourced from untrusted input without rigorous sanitization or parameter binding, this exposes the system to severe SQL injection attacks. Attackers could read, modify, or delete arbitrary data, and potentially execute database-level commands. Hardcoded Secrets: `databases.yaml` contains a hardcoded password. While `DATABASE_CONFIG_FILE` uses environment variables, the referenced configuration files should avoid embedding secrets directly in the repository. The `databases.test.yaml` also includes hardcoded credentials for test databases, which, while for testing, sets a risky pattern.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
raja-aiml icon

air

by raja-aiml

Sec8

Provides a comprehensive Go framework for building production-ready AI agents and MCP (Model Context Protocol) servers with integrated observability, testing, and infrastructure management.

Setup Requirements

  • ⚠️Requires Go 1.24+ runtime.
  • ⚠️Docker and Docker Compose are explicitly required for local infrastructure management.
  • ⚠️Requires either an OpenAI API Key or an Anthropic API Key (paid services) for full Natural Language Processing (NLP) capabilities.
Verified SafeView Analysis
The project uses environment variables for sensitive configurations (e.g., database URLs, JWT secrets, API keys) which is good practice. The use of `os.exec.Command` and direct SQL query execution (`db.query`, `db.shell`) is present, but primarily within developer tools and testing infrastructure, where such operations are expected and justified. LLM integrations use tool-calling with structured schemas, which mitigates arbitrary code injection via natural language input. Local Docker Compose configurations use default 'test' credentials, which should not be used in production. Network services in local dev are exposed to 0.0.0.0, requiring users to secure production deployments appropriately.
Updated: 2025-11-24GitHub→
0
0
High Cost
Sec8

An optimized MCP server for intelligently batching and caching Google Maps API calls to find nearby places and calculate distances.

Setup Requirements

  • ⚠️Requires Google Maps API Key (Paid service with enabled billing and specific APIs: Places API (New), Distance Matrix API, Geocoding API).
  • ⚠️Claude Desktop configuration requires an absolute path to the 'batch-nearby-search-mcp' repository.
  • ⚠️Requires Python 3.10 or higher.
Verified SafeView Analysis
The server makes external network calls to Google Maps APIs and requires a GOOGLE_MAPS_API_KEY. It instructs users to set the key in a .env file, which is good practice for environment variable management. No mention of 'eval' or obfuscation, assuming standard Python code.
Updated: 2025-11-17GitHub→
0
0
Medium Cost
attilacsanyi icon

weather-mcp-server

by attilacsanyi

Sec9

Provides weather forecast and alert information by integrating with the National Weather Service (NWS) API, enabling external agents to query weather data for specific locations or states.

Setup Requirements

  • ⚠️Requires Node.js runtime (v16+)
  • ⚠️Requires build step (`npm run build`) before running
Verified SafeView Analysis
Input validation is performed using Zod schemas for 'state', 'latitude', and 'longitude' parameters. External API calls are made to the official NWS API over HTTPS. No hardcoded secrets or direct command execution are present. Error messages are generic, preventing information leakage. The implementation is straightforward and does not introduce obvious vulnerabilities.
Updated: 2025-12-01GitHub→
0
0
Medium Cost
cladjidane icon
Sec7

Provides an MCP (Model Context Protocol) interface for Claude to manage events and registrations in EventLite using natural language.

Setup Requirements

  • ⚠️Requires an EventLite API Key (EVENTLITE_API_KEY) to be set as an environment variable.
  • ⚠️The EventLite API URL (EVENTLITE_API_URL) must be configured; defaults to localhost but production requires the official URL.
  • ⚠️If installing via npm, Node.js v18+ is required. For building standalone binaries, Bun is required.
  • ⚠️On macOS, downloaded binaries may require manual execution permission (`chmod +x`) and quarantine removal (`xattr -d com.apple.quarantine`).
Verified SafeView Analysis
The server correctly uses environment variables for API keys. However, the `upload_image` tool allows fetching images from arbitrary public URLs provided by the AI, which introduces a potential Server-Side Request Forgery (SSRF) risk if the upstream AI model is not adequately secured against malicious inputs.
Updated: 2025-11-26GitHub→
0
0
Low Cost
script-dragonmkop8t icon

cryptopanic-mcp-server

by script-dragonmkop8t

Sec9

Provides AI agents with the latest cryptocurrency news by fetching data from the CryptoPanic API.

Setup Requirements

  • ⚠️Requires a CryptoPanic API Key and API Plan (external service, may be paid depending on plan).
  • ⚠️Requires Python 3.13 or higher.
  • ⚠️The provided `run_command` example uses `uv`, which needs to be installed (e.g., `pip install uv`).
Verified SafeView Analysis
The server correctly uses environment variables for API keys, preventing hardcoding. It uses the standard `requests` library for external API calls, and limits the number of pages fetched to 10, mitigating potential abuse or excessive resource usage. Basic error handling is present around API calls. No dangerous functions like `eval` or `exec` are used. The primary security consideration is reliance on an external API (CryptoPanic) for data, which is inherent to its functionality.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
hisinha-rakesh icon

postgresql-mcp-server

by hisinha-rakesh

Sec4

Manage and interact with a PostgreSQL database using natural language queries, enabling full DDL, DML, TCL, and backup/restore operations via an AI assistant.

Setup Requirements

  • ⚠️Requires Azure OpenAI API Key with Claude deployment (Paid Service)
  • ⚠️Requires a running PostgreSQL database
  • ⚠️Requires Python 3.8+
  • ⚠️PostgreSQL client tools (pg_dump, psql, pg_restore) must be installed and in PATH for full backup/restore functionality.
Review RequiredView Analysis
The application is a proof-of-concept for executing LLM-generated SQL, which is inherently dangerous. While the 'enterprise' server attempts to use structured tool calls with parameters for DML operations (reducing direct SQL injection risk), DDL operations still involve the LLM generating raw SQL which is then executed. The server also uses `subprocess.run` for `pg_dump`/`pg_restore` which, if arguments are not perfectly sanitized, could be vulnerable to command injection (though efforts are made to pass arguments safely). The project README explicitly highlights these critical security risks and strongly advises against production use without significant safeguards like human-in-the-loop validation, least privilege database users, and sandboxing.
Updated: 2025-12-14GitHub→
PreviousPage 715 of 760Next