Skip to main content
Glama
59,744 servers. Last updated

Matching MCP tools:

Matching MCP Connectors:

"Shell" matching MCP servers:

  • Memory Shell Detector MCP

    RuoJi6
    A
    license
    A
    quality
    C
    maintenance
    A tool for detecting and cleaning Java memory shells via local or SSH remote execution. It enables AI agents to scan Java processes, analyze suspicious class code, and safely remove memory shells after user confirmation.
    Last updated
    9
    25
    MIT

  • bash-vet-mcp

    temurkhan13
    A
    license
    A
    quality
    B
    maintenance
    MCP server that vets LLM-emitted shell commands BEFORE execution — detects rm -rf nested deep in chains, package-manager glob removal (apt remove 'nvidia'), dd/mkfs filesystem destruction, chmod 777 / chown -R privilege blast, network-exfil via curl | bash, chained shutdown/reboot, git destructive ops. 30 detection rules across 8 families. Sub-second, local, free, MCP-native.
    Last updated
    3
    MIT

  • shellward

    jnMetaCode
    A
    license
    A
    quality
    B
    maintenance
    MCP security server with 7 tools: command safety check, prompt injection detection (32+ rules, zh+en), PII/sensitive data scanning, file path protection, tool policy enforcement, response auditing, and security status. 8-layer defense, zero dependencies.
    Last updated
    8
    237
    122
    Apache 2.0

  • Fida

    ajipurn
    A
    license
    A
    quality
    A
    maintenance
    A local-first redacting MCP gateway that strips secrets from file reads and shell output before they reach an AI coding agent's context, the command still runs with the real credential, but the model never sees it.
    Last updated
    2
    16
    MIT

  • mcp-guardian

    rudraneel93
    A
    license
    A
    quality
    A
    maintenance
    Security, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.
    Last updated
    4
    202
    3
    MIT

  • mcp-opnsense

    itunified-io
    A
    license
    A
    quality
    B
    maintenance
    Slim OPNsense MCP Server — 62 tools for managing firewall infrastructure via the OPNsense REST API. Covers DNS/Unbound, Firewall rules, Diagnostics, Interfaces, DHCP (ISC + Kea), System/Backups, ACME/Let's Encrypt, and Firmware. No SSH, no shell, API-only with 3 runtime dependencies. AGPL-3.0 + Commercial dual-licensed.
    Last updated
    100
    90
    2
    AGPL 3.0

  • mcp-tailscale

    itunified-io
    A
    license
    A
    quality
    D
    maintenance
    Production-ready MCP server for Tailscale management with 48 tools across 9 domains: Devices, DNS/Split DNS, ACL policies, Auth Keys, Users, Webhooks, Posture Integrations, Tailnet Settings, and Diagnostics. Supports stdio and SSE transport with Bearer token authentication. Built with TypeScript strict mode, Zod validation, and zero shell execution. AGPL-3.0 + Commercial dual-licensed.
    Last updated
    49
    104
    AGPL 3.0

  • kali-mcp

    Hannes221
    A
    license
    A
    quality
    D
    maintenance
    Provides an MCP interface to a full Kali Linux environment running in Docker, enabling AI assistants to execute security tools like nmap, sqlmap, and metasploit. It allows users to start/stop the container, run shell commands, and transfer files for security testing and educational purposes.
    Last updated
    7
    3
    3
    MIT

  • ai-runtime-guard

    runtimeguard
    A
    license
    B
    quality
    A
    maintenance
    ai-runtime-guard is an MCP server that sits between your AI agent and your system, enforcing a policy layer before any file or shell action takes effect. No retraining, no prompt engineering, no changes to your agent or workflow, just install, configure once, and your agent operates within the boundaries you set.
    Last updated
    8
    15

  • mcp-wsl-exec

    spences10
    A
    license
    B
    quality
    B
    maintenance
    A secure MCP server for Windows Subsystem for Linux environments, facilitating safe command execution with extensive validation and protection against vulnerabilities like shell injection and dangerous commands.
    Last updated
    7
    86
    20
    MIT

  • mcp-cloudflare

    itunified-io
    A
    license
    B
    quality
    D
    maintenance
    Slim Cloudflare MCP Server — 42 tools for managing DNS, zones, tunnels, WAF, Zero Trust, and security via Cloudflare API v4. Multi-zone support. No SSH, no shell, API-only with 3 runtime dependencies. AGPL-3.0 + Commercial dual-licensed.
    Last updated
    96
    74
    AGPL 3.0

  • MCP Shield

    rob925
    A
    license
    C
    quality
    D
    maintenance
    Security scanner and MCP server that catches dangerous patterns in MCP servers and AI agent projects, such as leaked secrets, shell execution, and prompt-injection text. Runs as both a CLI and MCP server with CI-friendly severity gates.
    Last updated
    2
    1
    MIT
  • APERION Shield MCP Server by AperionAI

    APERION Shield MCP Serverofficial

    AperionAI
    A
    license
    -
    quality
    C
    maintenance
    Governance engine for MCP tool calls, providing deterministic rule enforcement to block destructive actions like SQL drops, shell commands, and file system modifications before execution.
    Last updated
    1
    Apache 2.0
  • AgentWall by agentwall

    AgentWallofficial

    agentwall
    A
    license
    -
    quality
    B
    maintenance
    Policy-enforcing MCP proxy that blocks dangerous tool calls before they execute. Protects credentials, filesystem, shell, and databases across Claude Desktop, Cursor, Windsurf, and OpenClaw.
    Last updated
    6
    35
    Apache 2.0

  • Shellgate

    matthiastjong
    A
    license
    -
    quality
    A
    maintenance
    A secure gateway that lets AI agents interact with APIs and SSH servers via scoped tokens, with credential injection, human-in-the-loop for dangerous commands, and MCP integration for tool access.
    Last updated
    8
    15
    MIT

  • check-mcp

    golproductions
    A
    license
    -
    quality
    A
    maintenance
    Validate any shell command before execution. AI agents call Check to know if a command will work before running it: returns runnable or invalid. $0.04 AUD per check.
    Last updated
    1,530
    Sleepycat

  • safe-key-mcp

    Yormede
    A
    license
    -
    quality
    C
    maintenance
    MCP server enabling AI agents to use secrets (API keys, tokens) via encrypted vault, executing HTTP/shell/SSH actions server-side while never exposing secret values to the AI.
    Last updated
    MIT