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
dongitran icon

Jira-MCP-Server

by dongitran

Sec9

Provides an AI-callable interface (via Model Context Protocol) to manage Jira tasks, sprints, comments, and team workload using OAuth authentication.

Setup Requirements

  • ⚠️Requires obtaining OAuth 2.0 (3LO) credentials (client ID, client secret, access token, refresh token, cloud ID) from Atlassian, which can be a multi-step process or use a helper tool.
  • ⚠️Requires Node.js version 18 or higher.
  • ⚠️Needs specific JSON configuration within the user's IDE (e.g., Claude Desktop, Cursor, VS Code) to define the MCP server and pass credentials.
Verified SafeView Analysis
OAuth credentials (access_token, refresh_token, client_id, client_secret, cloud_id) are passed as command-line arguments and persisted to a user-specific cache file (`~/.jira-mcp/tokens.cache`) for convenience. This cache file is excluded from version control (`.gitignore`), but its security relies on the user's local system security. The server implements retry logic and a circuit breaker for robust network handling. No 'eval' or other obvious malicious patterns were found in the provided code.
Updated: 2025-12-15GitHub→
30
1
Low Cost
Panduza icon

serial-port

by Panduza

Sec7

Controls and monitors serial port-connected power supplies via MQTT or Model Context Protocol (MCP) interfaces, with an optional Terminal User Interface.

Setup Requirements

  • ⚠️Requires Rust toolchain and Cargo for building and running.
  • ⚠️Requires appropriate system permissions for serial port access.
  • ⚠️The `pza-toolkit` dependency is pulled from a GitHub 'main' branch, which may indicate instability or breaking changes.
  • ⚠️Configuration file `pza-serial-port.json5` must be manually adjusted for specific serial port parameters (e.g., baud rate, USB VID/PID).
Verified SafeView Analysis
The server primarily acts as a bridge to serial hardware, allowing raw byte/text transmission and reception via MQTT and MCP. This functionality inherently allows for direct manipulation of connected devices, which requires careful use by the client. The MCP server binds to a configurable host and port. By default, it's local (127.0.0.1:5002), which is secure. However, if configured to bind to a public IP (e.g., 0.0.0.0) with the permissive CORS layer enabled (as indicated by `CorsLayer::permissive()`), it could expose the serial port control to unauthorized network access. Input parsing (e.g., hex decoding, UTF-8 conversion) includes error handling, preventing crashes from malformed data. No hardcoded secrets or 'eval' are present.
Updated: 2025-12-02GitHub→
30
1
Medium Cost
trevSmart icon
Sec8

This server provides a Model Context Protocol (MCP) interface to Salesforce organizations, enabling AI agents to interact with Salesforce data and metadata through a suite of specialized tools for development, administration, and data management tasks.

Setup Requirements

  • ⚠️Requires Salesforce CLI to be installed and logged into a target org.
  • ⚠️Requires Playwright Chromium browser to be installed for `get_setup_audit_trail` tool (can be installed automatically on first use, adding initial download/setup time).
  • ⚠️Relies on specific environment variables (e.g., GITHUB_TOKEN, PASSWORD) for certain features and server security.
Verified SafeView Analysis
The server extensively uses Zod for input validation and `shellQuote.quote` for sanitizing commands sent to the Salesforce CLI, mitigating injection risks. Sensitive information like tokens and passwords are expected from environment variables and are redacted in logs. User confirmation (`elicitation`) is implemented for destructive operations. The project's active secret scanning is a positive indicator. Potential risks include the inherent power of direct Salesforce CLI command execution if not strictly controlled within tool handlers, and the use of Playwright for audit trail download which introduces browser-related attack surface.
Updated: 2025-12-12GitHub→
30
1
Low Cost
hyperpolymath icon

poly-iac-mcp

by hyperpolymath

Sec6

A unified Model Context Protocol (MCP) server for Infrastructure as Code (IaC) management, allowing AI assistants to plan, apply, and manage infrastructure using Terraform/OpenTofu and Pulumi.

Setup Requirements

  • ⚠️Requires Deno runtime installed.
  • ⚠️Requires OpenTofu or Terraform CLI installed and accessible in the system's PATH for Terraform tools.
  • ⚠️Requires Pulumi CLI installed and accessible in the system's PATH for Pulumi tools.
Verified SafeView Analysis
The server's core function involves executing external Infrastructure as Code (IaC) CLI tools (Terraform/OpenTofu, Pulumi) using `Deno.Command.run`. This operation is inherently high-privilege and requires `allow-run`, `allow-read`, `allow-write`, and `allow-env` permissions. While `Deno.Command` passes arguments as an array (mitigating direct shell injection within arguments), the server processes arguments directly from client input. Users must ensure robust authentication and authorization at the MCP client layer and rigorously validate inputs to prevent malicious IaC operations. The README provides important security considerations for users, emphasizing careful handling of credentials and plan reviews. No `eval` or intentional obfuscation was found.
Updated: 2026-01-18GitHub→
30
1
Medium Cost
lucasmangelo2 icon

mcp-poc

by lucasmangelo2

Sec8

A self-contained .NET Model Context Protocol (MCP) server for local development and NuGet publication, offering tools for calculations, CEP lookups, random number generation, and history tracking, integrated with AI assistants like Copilot.

Setup Requirements

  • ⚠️Requires an IDE (VS Code or Visual Studio) with Model Context Protocol (MCP) server support, which is currently in an early preview stage.
  • ⚠️If using the NuGet package, the specific package ID and version must be manually configured in the `.mcp.json` file.
Verified SafeView Analysis
The server uses standard practices like Dependency Injection for HttpClient and async/await for I/O operations. History tracking uses thread-safe ConcurrentBag. No 'eval', obfuscation, or hardcoded secrets are evident in the provided source code snippets. Communication is via stdio, a local channel. External API calls (ViaCEP) are handled through a configured HttpClient, with general risks associated with external APIs (e.g., rate limiting, data validation, although validation for CEP format is mentioned).
Updated: 2026-01-19GitHub→
30
1
High Cost
directive-reticule640 icon

codex-mcp-server

by directive-reticule640

Sec9

Integrates OpenAI's Codex CLI with Model Context Protocol (MCP) clients to enable AI-powered code analysis, generation, and brainstorming directly within development environments.

Setup Requirements

  • ⚠️Requires Codex CLI (from OpenAI) installed and authenticated on your system.
  • ⚠️Requires a paid OpenAI API key or ChatGPT subscription for Codex CLI functionality.
  • ⚠️Requires Node.js v18.0.0 or higher.
Verified SafeView Analysis
The server implements robust input validation using Zod and utilizes 'cross-spawn' for external command execution, which is generally safer than raw shell execution for arguments. It transparently exposes the underlying Codex CLI's sandbox modes ('read-only', 'workspace-write', 'danger-full-access') and approval policies, explicitly flagging the 'yolo' (bypass all safety) option as dangerous. No hardcoded secrets were found; API key management is delegated to the Codex CLI (via 'codex login' or 'OPENAI_API_KEY' environment variable). Overall safety heavily relies on the user's careful configuration and understanding of the Codex CLI's sandbox and approval settings, as the server delegates powerful operations to the AI agent.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
TeamSparkAI icon

mcp-registry

by TeamSparkAI

Sec8

A comprehensive Model Context Protocol (MCP) server catalog, discovery platform, and validation tool, enabling developers and AI practitioners to find, evaluate, and integrate MCP servers with schema validation and linting.

Setup Requirements

  • ⚠️Requires Node.js 18+ and pnpm 10+
  • ⚠️For local development, manual `.env.local` configuration is needed for `NEXT_PUBLIC_REGISTRY_URL` to test against local API server instead of the default external registry.
  • ⚠️Relies on `public/server-registry.json` which is generated by a daily GitHub Action or can be downloaded manually via `pnpm registry:download`.
Verified SafeView Analysis
The system explicitly warns about potential command injection risks within the `Argument` schema definition, indicating awareness of this common vulnerability. API endpoints use `Access-Control-Allow-Origin: *` for CORS, which is standard for public APIs but means any domain can make requests, a common consideration for public data. No hardcoded secrets or direct malicious patterns like 'eval' were found in the provided source.
Updated: 2026-01-19GitHub→
30
1
High Cost
Manoj00069 icon

Natural-Language-OS

by Manoj00069

Sec10

Natural-Language OS (NLOS) that defines and executes cognitive structures, value systems, and reasoning patterns entirely in natural language, using an LLM as its kernel.

Setup Requirements

  • ⚠️Requires access to a powerful Large Language Model (LLM) (e.g., GPT-4/5, Claude, Grok, Gemini), which may incur significant costs.
  • ⚠️The system operates by pasting lengthy natural language prompts into an LLM's chat interface or API, rather than running a traditional software application.
Verified SafeView Analysis
The provided source code consists solely of Markdown documentation, whitepapers, and natural language prompts intended for an LLM. There is no executable code (e.g., Python, JavaScript) to audit for typical security vulnerabilities such as `eval`, obfuscation, hardcoded secrets, or network risks. The project explicitly states that it does not access hidden memory, jailbreak models, or modify system behavior. Risks, if any, would stem from the LLM's own capabilities and interpretation, rather than from this project's 'code'.
Updated: 2026-01-19GitHub→
30
1
Low Cost
LucasBiason icon
Sec3

Automate Notion workflows by encapsulating specific business rules for different database types (Work, Studies, Personal, Youtuber) and exposing them as Model Context Protocol (MCP) tools for AI agents.

Setup Requirements

  • ⚠️Requires a Notion API Token (integration token) with access to relevant databases.
  • ⚠️Requires Notion Database IDs for each specific domain (Work, Studies, Personal, Youtuber) to enable respective tools. Tools for unconfigured databases will raise runtime errors.
  • ⚠️Requires Python 3.10+ if running locally (not via Docker).
Review RequiredView Analysis
The server dynamically generates and executes Python code using `exec()` within the `_build_tool_callable` function during tool registration. While the inputs for code generation (tool names, schemas) are derived from internal, hardcoded definitions, relying on `exec()` for core functionality is a significant security risk. If an attacker could compromise the tool definition files (e.g., via a supply chain attack or direct file system access), they could inject arbitrary code, leading to remote code execution. This makes the server vulnerable if the integrity of its source or deployment environment is compromised.
Updated: 2026-01-09GitHub→
30
1
High Cost
ozanmutlu icon

Gitlab-Docs-MCP

by ozanmutlu

Sec8

Provides AI assistants instant access to GitLab's official documentation for intelligent search and content retrieval via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Node.js 22+ to be installed.
  • ⚠️Requires cloning the GitLab documentation repository locally (specifically to `data/gitlab-docs-repo`) as a prerequisite.
  • ⚠️Requires running `npm run build-index` to create the search index before the server can be used.
Verified SafeView Analysis
The server uses `zod` for input validation on tool arguments, which helps prevent injection attacks. File system operations are scoped to a pre-built search index directory, limiting arbitrary file access. No direct `eval` or arbitrary command execution is visible within the server's core logic. Communication is via standard I/O (stdio). The primary risk lies with the client's execution of the `npx` command and the potential for large content retrieval (`getDocPage`) to incur high token costs, which needs to be managed by the AI assistant/user.
Updated: 2026-01-19GitHub→
30
1
Low Cost
agustinvalencia icon

mdvault

by agustinvalencia

Sec9

A terminal-based markdown vault manager and MCP server, providing structured note-taking, automation, search, and AI-assisted knowledge management for knowledge workers.

Setup Requirements

  • ⚠️Requires Rust toolchain (Rustup) to be installed for building from source or using `cargo install`.
  • ⚠️Initial setup requires manual creation of `config.toml` file with specific directory paths (`vault_root`, `templates_dir`, `captures_dir`, `macros_dir`, `typedefs_dir`).
  • ⚠️The `mdv reindex` command must be run initially and after significant changes to the vault to enable full search and query functionality.
  • ⚠️For AI-assisted vault interaction via MCP, a separate Python project (`markdown-vault-mcp`) is required, as `mdvault` is primarily a CLI tool that the MCP server utilizes.
Verified SafeView Analysis
The project demonstrates a strong focus on security, particularly concerning user-defined scripts and shell execution. Lua scripts are run in a sandboxed environment, with dangerous globals (`io`, `os`, `require`, `load`, `debug`, `collectgarbage`) explicitly removed and memory/instruction limits applied. Shell command execution within macros requires both a configuration flag (`allow_shell = true`) and an explicit `--trust` CLI flag from the user. Network access (`allow_http`) is similarly gated. An audit trail is mentioned for trusted operations, indicating a defense-in-depth approach.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
cfdude icon

mcp-jira

by cfdude

Sec8

Provides enterprise-level integration with Jira's REST API, enabling AI assistants to perform advanced project management, analytics, and strategic planning tasks across multiple Jira instances.

Setup Requirements

  • ⚠️Requires Jira Premium with Advanced Roadmaps for 'Plans' features (create, update, get, archive, trash, duplicate, team management).
  • ⚠️Requires a `.jira-config.json` file for multi-instance configuration and project mappings. Configuration search paths include working directory and home directory.
  • ⚠️Critical for AI: Most tools explicitly require `instance` and `projectKey` parameters to be specified to avoid configuration errors and ensure correct target Jira instance/project.
  • ⚠️Requires `JIRA_EMAIL`, `JIRA_API_TOKEN`, and `JIRA_DOMAIN` environment variables if using a legacy single-instance configuration without a dedicated `.jira-config.json` file.
Verified SafeView Analysis
The server demonstrates good security practices including explicit configuration of API tokens and emails via `.jira-config.json` or environment variables, avoiding hardcoded secrets. It utilizes `zod` for input validation and includes comprehensive error handling for API responses (e.g., 400, 401, 403, 404), which mitigates common injection and access risks. Session management is robust, offering thread-safe multi-client support and state isolation. There is no evidence of `eval` or other dangerous code patterns, and network communication is implied to use HTTPS when connecting to Jira domains. Cross-server integration with Confluence is designed for local communication, reducing external exposure. Overall, it appears safe to run in a well-configured environment.
Updated: 2026-01-19GitHub→
PreviousPage 219 of 760Next