Skip to main content
Glama
70,277 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

"A GitHub repository for agent guardrails" matching MCP servers:

  • mcp-guardrails-kit

    tcharod
    A
    license
    -
    quality
    C
    maintenance
    A prompt-injection-aware MCP server demonstrating guardrails for agentic tool use, including permission tiers, untrusted-content quarantine, and heuristic injection detection, with a fictional ticket-triage assistant.
    MIT

  • Javelin Guardrails MCP Server

    abhijitjavelin
    F
    license
    -
    quality
    D
    maintenance
    Provides AI security guardrails through Javelin's platform to detect harmful content, prompt injection attempts, and language policies. Enables comprehensive content safety analysis with trust & safety detection, prompt injection protection, and language identification.

  • io.github.DiaaAj/a-mem-mcp

    DiaaAj
    A
    license
    -
    quality
    D
    maintenance
    A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.
    34
    MIT

  • CHOFF-A-MCP (Anamnesis)

    dd-dent
    A
    license
    -
    quality
    D
    maintenance
    Enables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, and access semantic anchors for decisions, breakthroughs, and questions.
    1
    MIT

  • MCP for Vivado

    lzw12123
    F
    license
    C
    quality
    C
    maintenance
    An AI-centric MCP server that enables automated Xilinx Vivado workflows, including project management, synthesis, implementation, and timing analysis. It allows AI agents to drive hardware design processes while integrating directly with the official Vivado GUI for visual context.
    15
    4

  • agent-coord

    ThatHunky
    A
    license
    -
    quality
    C
    maintenance
    A zero-dependency MCP server that allows multiple coding agents to coordinate work on the same repository using file locks, task claims, and status messages.
    1
    MIT

  • agent-guardrail

    rudimentall1
    A
    license
    -
    quality
    A
    maintenance
    MCP server for AI agent guardrails — validates and signs agent decisions (OAA tokens) so third parties can verify them without server access
    1
    MIT

  • agent-delegate

    HezLUO
    A
    license
    -
    quality
    B
    maintenance
    agent-delegate is an MCP-first delegation advisor for coding agents. It helps a main agent decide when to delegate read-only investigation, generate bounded subagent briefs, and summarize subagent results back into compact main-agent context.
    MIT

  • claude-for-hermes

    7D-codes
    A
    license
    -
    quality
    B
    maintenance
    A local MCP server that lets Hermes supervise Claude Code, delegating focused coding, research, or review tasks to the Claude Code CLI and managing worker sessions, background jobs, cancellations, and read-only reviews.
    2
    MIT

  • call-a-human-mcp

    nishantmodak
    A
    license
    -
    quality
    D
    maintenance
    An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.
    14
    Apache 2.0

  • Agent MCP

    rinadelph
    A
    license
    -
    quality
    D
    maintenance
    A Multi-Agent Collaboration Protocol server that enables coordinated AI collaboration through task management, context sharing, and agent interaction visualization.
    1,271
    MIT

  • Guardrails MCP Server

    solmon2011
    F
    license
    -
    quality
    -
    maintenance
    Enables AI agents to integrate with Guardrails to check user values, make aligned decisions, and respect faith-based preferences. It provides tools for profile management, rule-based compatibility checks, and faith-aware scheduling.

  • agent-guard

    ipezygj
    A
    license
    A
    quality
    A
    maintenance
    Safety checks an agent runs before it acts — flags malicious packages, destructive shell commands, secret leaks, and web-backend holes before execution.
    8
    MIT