Skip to content
botshub
Visit MELRA

Open-source local MCP execution runtime for agents: policy-gated tool calls, scoped approvals, verified outcomes, durable receipts, and recovery after interruptions.

About MELRA

MELRA, short for Modular Execution Layer for Reliable Autonomy, is an open-source local runtime that sits between an AI agent and the tools it calls. The details here come from the project's README. It is published by XAGI Labs, and the README calls it alpha software whose APIs may change before 1.0.

The README says each call is checked against a policy, risky actions need approval, declared evidence of success is verified, and a redacted receipt is kept. Mutating calls are dispatched at most once, and uncertain outcomes are parked rather than retried. It exposes twelve MCP tools for single tasks and workflows, with adapters for files, terminal commands, browser automation, computer control and HTTP. It needs Node.js 22.13 or newer, with a Python SDK for Python 3.11 and up, and can be installed through npm, Docker or a release download. The README says the kernel and CLI are AGPL-3.0-only, with a commercial option, while the SDKs are Apache-2.0.

Key features

  • policy-gated tool calls
  • approval for risky actions
  • receipts and evidence checks
  • single-task and workflow tools
  • works with many MCP clients

More other MCP servers

  • Mcp Proxy

    sparfenyuk

    Other

    A bridge between Streamable HTTP and stdio MCP transports

    2.8K GitHub starsPythonMIT
  • Mcp Remote

    punkpeye

    Other

    Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server.

    1.7K GitHub starsTypeScriptMIT
  • Kanzo

    emanuele-em

    Other

    Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply, starts in 2 ms, zero setup.

    1.2K GitHub starsRustAGPL-3.0
  • Other

    į”Ÿæˆå’ŒįūŽåŒ–åŊįž–čū‘åŽŸį”Ÿ PPT įš„ Agent Skill

    484 GitHub starsPythonMIT
  • mcptoon

    activeing123

    Other

    MCP tool discovery burns 71,929 tokens. mcptoon drops it to 581 (−99.2%, measured). Zero dependencies.

    431 GitHub starsPythonApache-2.0
  • automcp

    NapthaAI

    Other

    Easily convert tool, agents and orchestrators from existing agent frameworks to MCP servers

    303 GitHub starsPythonApache-2.0
Suggest an improvement
Report this listing
Is this your project? Claim this listing