Discover Awesome MCP Servers

PocketMCP

A lightweight, local-first MCP server that automatically watches folders, chunks and embeds files using Transformers.js, and exposes semantic search capabilities to VS Code and Cursor. Runs completely offline with SQLite vector storage, designed for resource-constrained environments.

Calendly MCP Server

Enables interaction with Calendly's scheduling platform via MCP, allowing users to manage events, invitees, and schedule meetings directly using the Calendly API.

beacon-mcp

MCP server for the beacon log analytics platform, exposing beacon's REST API as MCP tools and resources for AI agents to query and analyse AI-assistant usage data.

Jina AI Remote MCP Server

Provides access to Jina AI's web reading, search, embeddings, and reranking capabilities. Enables URL content extraction, web/arXiv/image search, document deduplication, and relevance ranking through natural language.

Android MCP Server

Enables AI agents to directly control Android devices via Termux, providing 120+ tools for screen manipulation, file management, app control, and system operations with layered loading and security gating.

TRAECNclaw MCP

Control TraeCN desktop automation through explicit, profile-scoped MCP tools. Supports task delegation, model control, dialog handling, code review, and unattended workflows.

Cloudflare Remote PostgreSQL MCP Server

Enables natural language interaction with PostgreSQL databases through MCP tools, with GitHub OAuth authentication and role-based access control.

Tribunal TRF1: Processo

MCP server to query legal process information from Brazil's Tribunal Regional Federal da 1ª Região (TRF1), providing a read-only consultation tool using official sources.

interclaude

Enables peer-to-peer communication between Claude Code sessions, allowing them to send messages, hand off tasks, and coordinate across worktrees without manual intervention.

MCP Kali Server

MCP (Management Control Protocol) configuration to connect an AI agent to a Linux machine depends heavily on the specific MCP implementation and the AI agent you are using. There isn't a single, universal configuration. However, I can provide a general outline and considerations, along with examples of common approaches. You'll need to adapt this to your specific tools and environment. **General Considerations:** * **MCP Implementation:** What MCP system are you using? Examples include: * **Custom MCP:** If you've built your own MCP, you'll need to refer to its documentation. * **Existing Management Frameworks:** Some frameworks like Ansible, Chef, Puppet, or SaltStack could be used as a foundation for your MCP. In this case, you'd configure the AI agent to interact with the framework's API. * **Cloud Provider Services:** If your Linux machine is in a cloud environment (AWS, Azure, GCP), you might leverage their management services (e.g., AWS Systems Manager, Azure Automation, Google Cloud Operations). * **AI Agent Capabilities:** What can your AI agent do? Can it: * Execute commands on the Linux machine? * Read files and system information? * Monitor system metrics? * Deploy software? * Authenticate securely? * **Security:** This is paramount. Consider: * **Authentication:** How will the AI agent authenticate with the Linux machine? SSH keys, passwords (discouraged), certificates, or API keys are possibilities. * **Authorization:** What permissions will the AI agent have? Use the principle of least privilege. Don't give it root access unless absolutely necessary. * **Encryption:** Use encryption (e.g., SSH, TLS) for all communication between the AI agent and the Linux machine. * **Auditing:** Log all actions performed by the AI agent. * **Network Connectivity:** Ensure the AI agent can reach the Linux machine over the network. Firewall rules may need to be adjusted. **Example Scenario: AI Agent using SSH and Python (Paramiko) for a Custom MCP** This is a common and relatively straightforward approach. Let's assume: * The AI agent is a Python script. * It uses the `paramiko` library to connect to the Linux machine via SSH. * It needs to execute commands and retrieve output. **1. Linux Machine Setup:** * **SSH Server:** Ensure the SSH server (`sshd`) is running and configured securely. Disable password authentication if possible and use SSH keys. * **User Account:** Create a dedicated user account for the AI agent with limited privileges. For example: ```bash sudo adduser aiagent sudo usermod -aG sudo aiagent # If the agent needs to run commands with sudo sudo passwd aiagent # Set a strong password (if you must use passwords) ``` * **SSH Key Authentication (Recommended):** * Generate an SSH key pair on the AI agent's machine. * Copy the public key (`id_rsa.pub`) to the `~/.ssh/authorized_keys` file of the `aiagent` user on the Linux machine. ```bash # On the AI agent's machine: ssh-keygen -t rsa -b 4096 # Copy the public key to the Linux machine (using ssh-copy-id or manually): ssh-copy-id aiagent@<linux_machine_ip_address> # Or manually: scp ~/.ssh/id_rsa.pub aiagent@<linux_machine_ip_address>:/tmp/aiagent_key.pub ssh aiagent@<linux_machine_ip_address> "mkdir -p ~/.ssh && cat /tmp/aiagent_key.pub >> ~/.ssh/authorized_keys && rm /tmp/aiagent_key.pub && chmod 700 ~/.ssh && chmod 600 ~/.ssh/authorized_keys" ``` **2. AI Agent (Python) Configuration:** ```python import paramiko def execute_command(hostname, username, private_key_path, command): """Executes a command on a remote Linux machine via SSH.""" try: ssh_client = paramiko.SSHClient() ssh_client.set_missing_host_key_policy(paramiko.AutoAddPolicy()) # WARNING: Insecure for production! Use known_hosts. private_key = paramiko.RSAKey.from_private_key_file(private_key_path) ssh_client.connect(hostname=hostname, username=username, pkey=private_key) stdin, stdout, stderr = ssh_client.exec_command(command) output = stdout.read().decode('utf-8') error = stderr.read().decode('utf-8') ssh_client.close() return output, error except Exception as e: return None, str(e) # Configuration hostname = "<linux_machine_ip_address>" username = "aiagent" private_key_path = "/path/to/your/id_rsa" # Path to the AI agent's private key command_to_execute = "ls -l /home/aiagent" # Execute the command output, error = execute_command(hostname, username, private_key_path, command_to_execute) if output: print("Output:\n", output) else: print("Error:\n", error) ``` **Explanation of the Python Code:** * **`paramiko.SSHClient()`:** Creates an SSH client object. * **`set_missing_host_key_policy(paramiko.AutoAddPolicy())`:** **CRITICAL SECURITY WARNING:** This automatically adds the host key to the `known_hosts` file. This is convenient for testing but **highly insecure** for production. In production, you should manually verify and add the host key to the `known_hosts` file. See `ssh-keyscan`. * **`paramiko.RSAKey.from_private_key_file()`:** Loads the SSH private key from the specified file. * **`ssh_client.connect()`:** Connects to the Linux machine using the provided credentials. * **`ssh_client.exec_command()`:** Executes the specified command on the remote machine. * **`stdout.read().decode('utf-8')`:** Reads the standard output from the command and decodes it as UTF-8. * **`stderr.read().decode('utf-8')`:** Reads the standard error from the command. * **`ssh_client.close()`:** Closes the SSH connection. **3. MCP Integration:** The `execute_command` function is the core of the MCP interaction. You would integrate this into your AI agent's logic. For example: * **Command Execution:** The AI agent might receive a command from a central server and use `execute_command` to run it on the Linux machine. * **Data Collection:** The AI agent might run commands to collect system information (e.g., CPU usage, memory usage, disk space) and send it back to a central server. * **Automated Tasks:** The AI agent might be scheduled to run certain commands periodically to perform maintenance tasks. **4. Security Hardening (Important):** * **`known_hosts`:** Replace `paramiko.AutoAddPolicy()` with proper `known_hosts` verification. Use `ssh-keyscan` to get the host key and add it to the `known_hosts` file. * **Firewall:** Restrict SSH access to only the AI agent's IP address. * **Least Privilege:** Grant the `aiagent` user only the necessary permissions. Use `sudo` with caution and configure it to allow only specific commands. * **Logging:** Implement comprehensive logging of all actions performed by the AI agent. * **Regular Security Audits:** Regularly review the configuration and logs to identify and address any security vulnerabilities. **Example in Japanese (Configuration Comments):** ```python import paramiko def execute_command(hostname, username, private_key_path, command): """リモートのLinuxマシンでSSH経由でコマンドを実行します。""" try: ssh_client = paramiko.SSHClient() ssh_client.set_missing_host_key_policy(paramiko.AutoAddPolicy()) # 警告: 本番環境では安全ではありません！ known_hostsを使用してください。 private_key = paramiko.RSAKey.from_private_key_file(private_key_path) ssh_client.connect(hostname=hostname, username=username, pkey=private_key) stdin, stdout, stderr = ssh_client.exec_command(command) output = stdout.read().decode('utf-8') error = stderr.read().decode('utf-8') ssh_client.close() return output, error except Exception as e: return None, str(e) # 設定 hostname = "<linux_machine_ip_address>" # LinuxマシンのIPアドレス username = "aiagent" # ユーザー名 private_key_path = "/path/to/your/id_rsa" # AIエージェントの秘密鍵へのパス command_to_execute = "ls -l /home/aiagent" # 実行するコマンド # コマンドを実行 output, error = execute_command(hostname, username, private_key_path, command_to_execute) if output: print("出力:\n", output) else: print("エラー:\n", error) ``` **Other Approaches:** * **Ansible/Chef/Puppet/SaltStack:** Use these configuration management tools to manage the Linux machine. The AI agent would interact with the tool's API to trigger configuration changes or execute commands. This provides a more structured and auditable approach. * **Cloud Provider Services:** If you're using a cloud provider, leverage their management services. For example, AWS Systems Manager allows you to run commands on EC2 instances without SSH. * **gRPC/REST API:** Create a custom gRPC or REST API on the Linux machine that the AI agent can call. This provides a more controlled and secure interface. **Key Takeaways:** * **Security is paramount.** Implement strong authentication, authorization, and encryption. * **Use the principle of least privilege.** Grant the AI agent only the necessary permissions. * **Choose the right MCP implementation for your needs.** Consider the complexity, scalability, and security requirements of your application. * **Thoroughly test and monitor your configuration.** Remember to replace the placeholder values (e.g., `<linux_machine_ip_address>`, `/path/to/your/id_rsa`) with your actual values. This is a starting point; you'll need to adapt it to your specific environment and requirements.

patents-mcp

MCP server for patent search and prior art discovery powered by Google Patents public dataset on BigQuery. Supports searching patents, fetching full patent details with CPC codes and citations, and retrieving legal claims text.

SEFAZ PR: CADIN

MCP server for querying the Paraná state tax agency's CADIN registry, read-only, hosted, with pay-per-use credits.

LangChain Documentation MCP Server

Provides real-time access to official LangChain documentation, API references, and GitHub code examples to assist in LangChain-based development. It enables LLMs to search for tutorials, version info, and detailed class specifications directly from live sources.

rybbit-mcp

Exposes Rybbit Analytics as MCP tools for querying site traffic, page views, visitor sessions, and live visitor counts through natural language.

tasks-mcp

An MCP server that exposes outputty's task tracker as typed tools backed by GitHub Issues, allowing coding agents to manage tasks with two-way sync.

dad-jokes-mcp

Enables fetching and managing dad jokes with tools for random jokes, multiple jokes, categories, and persistent storage.

CCCMemory MCP

Provides Claude with long-term memory by indexing conversation history, enabling semantic search, decision tracking, and cross-project search.

bhs-mcp

An MCP server for Blackhearts & Sparrows product data that enables searching products, retrieving details, listing stores, and managing carts via a sandboxed TypeScript execution environment.

Microsoft Copilot Studio ❤️ MCP

A lab demonstrating how to deploy a Model Context Protocol (MCP) server and integrate it with Microsoft Copilot Studio, allowing users to connect AI models to different data sources and tools through a standardized protocol.

MCP-Context-Provider

A static MCP server that helps AI models maintain tool context across chat sessions, preventing loss of important information and keeping conversations smooth and uninterrupted.

marm-mcp

MARM MCP provides persistent memory and structured session context beneath any AI tool, so your agents learn, remember, and collaborate across all your workflows.

jankins

Token-optimized Jenkins MCP server with smart log handling and failure triage for AI coding assistants.

Multimodal RAG MCP Server

Connects Claude to a personal knowledge base with hybrid search over code, documents, and images. Allows the AI assistant to retrieve and answer from your own files during conversations.

OpenAI Image Generation MCP Server

Enables image generation using OpenAI's DALL-E and GPT-Image models directly through the Model Context Protocol. It allows users to create and save images with fine-grained control over parameters like size, quality, and background transparency.

mcp-hashline-edit-server

Provides hashline-based file editing using line-addressed edits and content hashes for integrity verification. It enables LLMs to perform precise file modifications while ensuring edits are rejected if the file content has changed since the last read.

mcp-inaturalist

Enables querying citizen-science species observations from iNaturalist via the Pipeworx MCP gateway. Provides read-only access to species data without authentication.

cobos-apple-mail-mcp

Unifies fast on-disk read and search with complete AppleScript writes, behind a mandatory safety layer with read-only mode, batch caps, dry-run, and undo for reversible operations.

Vibe Blocks MCP

Connects Roblox Studio to AI coding editors via the Model Context Protocol, allowing AI agents to understand and interact with live Roblox Studio sessions through scene manipulation, scripting, and optional Roblox Open Cloud API integration.

mcp-infoblox

An MCP server that provides AI assistants with full access to Infoblox NIOS for managing DNS records, DHCP reservations, and IPAM through the WAPI REST API. It supports 35 tools for network discovery, record lifecycle management, and grid infrastructure status.

Intern MCP

Local stdio MCP server for working on Intern-hosted sites through guarded Git checkouts. It enables authentication, site preparation, testing, validation, and publishing via coding harnesses like Codex and Claude Code.