Find your next MCP server
Find remote and local MCP servers by task, transport, capability, access, and publisher, with clear verification labels.
14,270 MCP servers
Vendor-operated and community listings, with live-check and source-verification states shown independently.
| Server | Type | Category | Access | Setup |
|---|---|---|---|---|
agent-godmode MCPA sandboxed workspace MCP server providing file operations (read, write, edit, list) and command execution. | CommunityPackage | Developer tools | Source reviewed | |
AgentGo MCPAgentGo is a real Chromium browser for Windows designed for AI agents. | CommunityPackage | Developer tools | Source reviewed | |
agent-guard-mcpA community Model Context Protocol server that provides safety checks for AI coding agents. | CommunityPackage | Developer tools | Source reviewed | |
agent-guard-mcpA Git-aware safe file operations MCP server for AI agents that allows deletion of files and directories while preventing the removal of git-tracked source code. | CommunityPackage | Developer tools | Source reviewed | |
agent-guard-mcpAn MCP server designed to enhance AI agent reliability by detecting and preventing infinite loops. | CommunityPackage | Developer tools | Source reviewed | |
AgentGuard MCPA read-only MCP server for accessing coding-agent traces, alerts, costs, usage, and budget health. | CommunityPackage | Developer tools | Source reviewed | |
AgentGuard MCPAgentGuard is a free, open-source, single-binary MCP server that provides security checks for AI agents. | CommunityPackage | Developer tools | Source reviewed | |
AgentGuard MCPAgentGuard MCP provides signed spend decisions for MCP hosts, enabling local spend caps, kill-switch blocking, and Ed25519-signed receipts for AI agent tool calls. | CommunityPackage | Developer tools | Source reviewed | |
agentguard-mcpAn MCP server that provides a declarative network-egress firewall for agent tools. | CommunityPackage | Developer tools | Source reviewed | |
agent-guardrail MCPA deterministic policy firewall for AI agent tool calls that uses YAML rules to check requests against policies before execution. | CommunityPackage | AI and machine learning | Source reviewed | |
Agent Guardrail MCP ServerAgent Guardrail provides action-level governance for AI agents, allowing developers to control what agents do rather than just filtering their output. | CommunityPackage | Developer tools | Source reviewed | |
agent-guards MCPA local MCP server providing deterministic detection of known attack patterns against AI agents, including package installation, untrusted text reading, link following, and money… | CommunityPackage | AI and machine learning | Source reviewed |
Browse by category
Let your agent find its tools
Add Koskamo to your agent to find official MCP servers for a task, inspect access requirements, and get setup links. Public discovery needs no key.
How listings and verification work
Remote listings are live-checked and re-checked weekly. Local packages are validated from their attributed registry or catalog source and are never executed by Koskamo. Community and vendor evidence are labelled separately.
Access labels describe remote connection and discovery. Individual tools may require accounts, credentials, permissions, or payment. Registry membership and endpoint checks are not security audits.
List your own server