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)

30
1
Low Cost
techmaharaj icon
Sec2

Allows an AI model (Claude) to remotely control a Kubernetes cluster by exposing kubectl commands as Model Context Protocol (MCP) tools.

Setup Requirements

  • ⚠️Requires `kubectl` to be installed and configured with access to a Kubernetes cluster.
  • ⚠️For remote access, an `ngrok` account and `Claude Pro` subscription are necessary.
  • ⚠️CRITICAL: The server has no authentication configured, making it highly insecure if exposed to the internet.
Review RequiredView Analysis
CRITICAL: The server exposes direct `kubectl` command execution via MCP tools without any authentication mechanism, as explicitly stated in the README. Anyone with access to the server's endpoint (e.g., via ngrok) can execute arbitrary `kubectl` commands (create, delete pods, get cluster info) on the connected Kubernetes cluster. This poses a severe security risk, allowing for potential unauthorized access, resource manipulation, or denial of service.
Updated: 2025-12-03GitHub→
30
1
Medium Cost
TonisOrmisson icon

limesurvey-mcp

by TonisOrmisson

Sec9

A Model Context Protocol (MCP) server that exposes LimeSurvey Remote API functionality as MCP tools for standardized interaction.

Setup Requirements

  • ⚠️Requires a running LimeSurvey instance with its RemoteControl2 API enabled and accessible via the configured URL.
  • ⚠️Requires valid LimeSurvey API credentials (username and password) with appropriate permissions for the operations to be performed.
  • ⚠️Requires Node.js (version 18 or higher is recommended by the SDK's engine configuration) if not run via Docker.
Verified SafeView Analysis
The server correctly uses environment variables for sensitive credentials (API URL, username, password) and does not hardcode them. It implements a 'read-only' mode as a security feature. The codebase itself does not contain 'eval', obfuscation, or obvious malicious patterns. Network risks are primarily dependent on the security of the underlying LimeSurvey instance (e.g., use of HTTPS for LIMESURVEY_API_URL) and the environment in which this server is deployed. The server manages a session key for the LimeSurvey API, releasing it on shutdown, which is good practice.
Updated: 2025-12-01GitHub→
30
1
Low Cost
Sec8

Extends ClickSend's messaging capabilities into modern AI ecosystems, enabling AI agents to send SMS without custom code.

Setup Requirements

  • ⚠️Requires Node.js version 18 or higher.
  • ⚠️Mandatory `CLICKSEND_USERNAME` and `CLICKSEND_API_KEY` environment variables from a ClickSend account.
  • ⚠️Specific configuration steps are required to integrate with Claude for Desktop, involving manual editing of a JSON configuration file.
Verified SafeView Analysis
The server itself appears to be a local adapter for an AI client to an external messaging API. No explicit 'eval' or obfuscation is mentioned. The primary security considerations involve the secure handling of ClickSend API credentials by the user, as the server will use these to interact with the ClickSend API. The README provides good warnings about securing credentials. Assuming the official package is not compromised, it's safe to run when credentials are kept private.
Updated: 2025-11-17GitHub→
30
1
High Cost
SnappStats icon

kg-mcp

by SnappStats

Sec8

Provides tools to extract, search, and insert sports-associated information into a knowledge graph, and to generate scout reports for players using AI agents.

Setup Requirements

  • ⚠️Requires Python 3.12+ (managed with pyenv).
  • ⚠️Requires extensive Google Cloud setup, including a project, location, and service account credentials for Vertex AI (Gemini API) and Cloud Trace.
  • ⚠️Requires an active MongoDB instance (MONGO_URI) and an external Knowledge Graph service (KG_URL).
Verified SafeView Analysis
No direct use of 'eval' or obvious hardcoded secrets. Environment variables are managed via dotenv and Doppler (recommended). Relies on external services (Google GenAI, MongoDB, Hudl API, DDGS). The Cloud Run deployment configuration specifies `--allow-unauthenticated`, meaning the API endpoint is public; proper authentication/authorization must be handled by the consuming client or FastMCP's internal mechanisms, or an external layer. The prompt engineering for AI agents is detailed, which helps mitigate risks associated with generative AI output.
Updated: 2025-11-28GitHub→
30
1
Low Cost
aserper icon

jellyseerr-mcp

by aserper

Sec4

Provides an MCP (Model Context Protocol) interface for LLM clients to interact with Jellyseerr, enabling media search and request functionality.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Requires a running Jellyseerr instance with an API key.
  • ⚠️Requires `JELLYSEERR_URL` and `JELLYSEERR_API_KEY` environment variables.
Review RequiredView Analysis
The presence of the `get-pip.py` file, which is largely obfuscated (using base85 encoding) and performs complex system-level operations (like monkeypatching pip internals), significantly raises security concerns. While it might be the official get-pip script, its direct inclusion and obfuscation within the project's source code make it difficult to audit and introduces a large, opaque attack surface. Additionally, the `raw_request` tool allows LLMs to perform arbitrary HTTP methods (GET, POST, PUT, DELETE) against any endpoint of the configured Jellyseerr API, which could be abused to trigger unintended actions or retrieve sensitive data if the LLM client is compromised or poorly constrained.
Updated: 2025-12-12GitHub→
30
1
Low Cost
AojdevStudio icon

simple-memory-mcp

by AojdevStudio

Sec9

This server provides persistent AI memory and knowledge graph storage, enabling AI assistants to maintain context across sessions and integrate with tools like Obsidian for visualization.

Setup Requirements

  • ⚠️Node.js v18+ is required to run the server.
  • ⚠️Requires write permissions to the configured MEMORY_PATH (default: ~/.cursor/memory.json) for persistent storage.
  • ⚠️For full utility, an MCP-compatible AI client (e.g., Claude Desktop, Cursor IDE) is necessary.
Verified SafeView Analysis
The server is designed for local, user-permissioned operation, primarily using file system operations (read/write JSON) for persistence. It includes JSON schema validation for MCP tool inputs. The `SECURITY.md` file indicates a strong awareness of best practices, emphasizing private disclosure for vulnerabilities, and warning against exposing the server over a network due to lack of built-in authentication. There are no obvious malicious patterns or dynamic code execution from untrusted input (like `eval`). Risks primarily involve file system permissions for the configured memory and Obsidian vault paths, and the absence of data encryption for local storage.
Updated: 2025-12-05GitHub→
30
1
Low Cost
bwalheim1205 icon

aws-mcp-gateway

by bwalheim1205

Sec8

Exposes AWS Lambda functions as MCP-compatible tools, allowing them to be discovered, listed, and invoked programmatically via an HTTP gateway.

Setup Requirements

  • ⚠️Requires Go 1.21 or higher if running as an executable.
  • ⚠️Requires an AWS account with configured Lambda functions to expose.
  • ⚠️Requires AWS credentials (via IAM role or environment variables) for Lambda invocation.
  • ⚠️Requires a YAML configuration file (`tools.yaml`) detailing the Lambda functions to expose as MCP tools.
Verified SafeView Analysis
Relies on standard AWS SDK credential chain (IAM roles, environment variables) for Lambda authentication. Input payload is passed directly to Lambda functions; the security of the invoked Lambda function is paramount. No hardcoded secrets or obvious malicious patterns found in the gateway's source code. The server can be configured to run over SSE or Stream mode, and the exposed port (default 8080) should be properly secured in deployment.
Updated: 2026-01-16GitHub→
30
1
Medium Cost
lesleslie icon

session-buddy

by lesleslie

Sec9

The MCP server provides comprehensive session management, conversation memory, quality monitoring, and developer tooling integration for Claude Code projects, aiming to reduce token usage and enhance development workflows. It integrates with various LLM providers, Git worktrees, and code quality tools like Crackerjack.

Setup Requirements

  • ⚠️Requires `uv` for Python package management. Users may need to install `uv` and run `uv sync --extra embeddings` for full functionality.
  • ⚠️Full LLM-powered features (e.g., entity extraction, AI agent recommendations) require API keys for cloud providers (e.g., `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`/`GOOGLE_API_KEY`) or a locally running Ollama server (`OLLAMA_BASE_URL`). These can incur costs.
  • ⚠️Crackerjack integration requires the `crackerjack` Python package to be installed.
  • ⚠️Uses embedded `DuckDB` for reflection and knowledge graph databases.
  • ⚠️Optional serverless mode features require `redis` and `boto3` dependencies.
Verified SafeView Analysis
The project demonstrates strong security awareness, particularly in handling subprocess execution (explicitly uses `shell=False` and includes input validation for commands, branch names, and paths) and database interactions (parameterized SQL queries). Hashlib usage for content deduplication is correctly flagged with `usedforsecurity=False`. Pydantic models are used for robust parameter validation, mitigating injection risks. API key handling includes masking for display. The project's security posture for common vulnerabilities like command injection and SQL injection is robust, with dedicated tests. One point deducted due to the inherent complexity of integrating with numerous external systems (LLMs, Git, external tools), which always presents a broader attack surface, though well-mitigated within the application's scope.
Updated: 2026-01-19GitHub→
30
1
High Cost
tblakex01 icon

mcp_troubleshooter

by tblakex01

Sec9

A Model Context Protocol (MCP) server that provides comprehensive system troubleshooting and diagnostic tools for developers and system administrators, enabling LLMs to diagnose system issues, monitor resources, check logs, and test connectivity.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Requires manual configuration of an absolute path in the Claude Desktop `claude_desktop_config.json` file.
  • ⚠️System calls via `psutil` or `subprocess` may require appropriate user permissions on the host system.
Verified SafeView Analysis
The project demonstrates a strong "Security First" design principle. It implements a strict command whitelist (`SAFE_COMMANDS`) for `troubleshooting_execute_safe_command`, preventing arbitrary code execution. All inputs are rigorously validated using Pydantic models with type checking, range constraints, and pattern validation. Critical operations include timeout protection to prevent denial of service. The `log_reader` tool enforces access restrictions to `ALLOWED_LOG_DIRS` and uses `Path.resolve()` to mitigate path traversal vulnerabilities. Environment variables containing sensitive patterns are masked during inspection. While the security measures are robust for its intended diagnostic purpose, the inherent risk of running any system commands via an LLM, even whitelisted ones, means vigilance is always required.
Updated: 2026-01-17GitHub→
30
1
Medium Cost
EdibleTuber icon

void-mcp-server

by EdibleTuber

Sec9

Provides a secure, sandboxed filesystem server for AI agents via the Model Context Protocol (MCP), enabling file and directory operations within a defined project root.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️A known issue in Void Editor may restrict MCP servers to Void's installation directory, requiring project relocation or a workaround for 'allowed_root'.
  • ⚠️Requires absolute paths for the Python executable and server script in Void Editor configuration.
Verified SafeView Analysis
The server implements robust security measures including path sandboxing via Path.resolve() and relative_to() checks, a comprehensive list of blocked patterns for sensitive files and directories, extension whitelisting, and configurable file size limits. Crucially, it explicitly states 'No Shell Access' and avoids dangerous functions like eval() or subprocess.run() for arbitrary command execution. This makes it highly secure for its stated purpose within the defined sandbox.
Updated: 2025-11-30GitHub→
30
3
Low Cost
alecf icon

airtop-mcp

by alecf

Sec9

Provides a Model Context Protocol (MCP) server to integrate AI agents with Airtop's browser automation and AI query services.

Setup Requirements

  • ⚠️Requires Airtop API Key (AIRTOP_API_KEY environment variable).
  • ⚠️Requires Node.js (version 18 or higher based on dependencies).
  • ⚠️Uses port 3456 by default, which might conflict with other services (configurable via PORT environment variable).
Verified SafeView Analysis
The server securely handles the Airtop API key by requiring it as an environment variable and uses Zod for input validation on tool arguments. It does not contain direct `eval` calls or other obvious malicious patterns. Network exposure is limited to standard HTTP/SSE endpoints. The primary security considerations would be the security of the Airtop API itself and proper management of the AIRTOP_API_KEY by the user.
Updated: 2026-01-07GitHub→
30
1
Low Cost
GitHub30 icon

dns-mcp-server

by GitHub30

Sec8

Provides DNS lookup capabilities as a Model Context Protocol (MCP) server.

Verified SafeView Analysis
The server uses `dnspython` for DNS lookups. While `dnspython` is generally robust, any public DNS lookup service could potentially be used in DDoS amplification/reflection attacks if not properly secured at a higher network layer. The application code itself does not show immediate vulnerabilities like `eval`, hardcoded secrets, or command injection flaws through its direct use of `dnspython`'s resolve functions. The 'readOnlyHint' annotation is a good practice for informational tools.
Updated: 2025-11-27GitHub→
PreviousPage 218 of 760Next