Skip to main content
Glama
holdgate-proxy

holdgate-proxy

by im-amir

Related Servers

Alternatives to holdgate-proxy

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      B
      maintenance
      Experimental Python MCP server exposing traceguard_shield_exec to evaluate proposed tool calls through an authorization hook. Returns approval or rejection messages over stdio; it does not execute the requested tools.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Sits in front of any MCP server to enforce allow/ask/block policies on tool calls, paths, shell commands, and network domains, with local approval prompts and an audit log.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Provides a human-approval tool for MCP-compatible agents, pausing execution until a human approves or edits the action, with every decision logged.
      2
      10 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides an MCP stdio interface for AI agents to propose tool calls that are validated against task policy, held for human approval when required, executed in a sandboxed Linux environment, and recorded in an audit log.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Stands between an agent and a stdio MCP server: checks each tool call against a permission a person signed with a passkey, refuses calls outside it, and writes a signed receipt countersigned with its own keys. Holds the server's credentials, so the agent never sees them; a free offline checker says whether the agent stayed within the permission.
      2
      184 npm
      Apache 2.0
    • A
      license
      B
      quality
      C
      maintenance
      Sits in front of any other MCP server and decides, outside the model, whether each tool call goes straight through, waits for a named person to approve it, or is refused. Adds one-time approval claims, step-derived idempotency keys, read-after-write verification and a hash-chained audit log so agents can propose writes safely.
      9
      MIT