MELRA MCP server
io.github.XAGI-Lab/melra·v0.3.0-alpha.14·10 starsLocal MCP runtime for policy-governed, verified agent actions with durable receipts.
10 stars9 downloads/wk
Reviews
Write oneNobody has reviewed MELRA yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
MELRA tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- Code scan27 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How MELRA compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 88% of 4,460 AI and agents servers
- GitHub stars
- 10
- more than 84% of 2,711 AI and agents servers
- Downloads a week
- 9
- more than 2% of 1,538 AI and agents servers with a package
Install MELRA in Claude Code, Cursor or VS Code
Runs npx -y @melra/cli on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add melra -- npx -y @melra/cli
What the publisher says
From the MELRA repository's README, as published. We do not edit it. Read it on GitHub
MELRA
Modular Execution Layer for Reliable Autonomy
Your AI agent decides what to do. MELRA governs how tool calls are authorized, verified, and recovered.
An open-source autonomy kernel: the layer every agent action passes through on its way to your files, terminal, browser, desktop and APIs. It checks each action against policy, requests approval when needed, verifies declared evidence, and keeps a redacted receipt. For each task, MELRA dispatches mutations at most once; uncertain outcomes are parked for reconciliation instead of replay. Exactly-once external effects still depend on the provider.
<!-- Build & quality (live) -->
<!-- Release & project -->
<!-- Platforms & stack -->
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
MELRA: common questions
- Is MELRA MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the MELRA safety report
- How do I install MELRA?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does MELRA need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is MELRA maintained?
- The last commit was 19 days ago (2026-10-16). The latest release is v0.3.0-alpha.14.
- What can I use instead of MELRA?
- Servers from other publishers that do the same job: Agent-Native Chat MCP server, Emilia Protocol MCP server and Agoragentic Agent OS MCP server. Compare all MELRA alternatives.
- How does MELRA compare with other AI and agents MCP servers?
- safety score 91/100 (higher than 88% of 4,460 AI and agents servers); github stars 10 (more than 84% of 2,711 AI and agents servers); downloads a week 9 (more than 2% of 1,538 AI and agents servers with a package). Full comparison.
Alternatives to MELRA
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts.not reviewedEstablishedB
Agoragentic Agent OS MCPTriptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.not reviewedEstablishedB- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB
