Raymon — Ray-style log store & MCP server

Trust Score 84/100

Lightweight searchable Ray-compatible log server (Raymon) exposing an MCP interface for agents to search, list, and fetch full log entries for debugging and tri

triggers:raymon.searchraymon.get_entriessearch logsfetch uuidray-styleadd mcp serverraymon --demo

GitHub SKILL.md

What it does

Raymon provides a Ray-style log collection and TUI with an MCP-compatible HTTP interface. Agents can search stored log entries with filters and pagination, then fetch full payloads by UUID for debugging. Integrations exist for multiple languages so applications can send Ray-style dumps to Raymon.

When to use it

Use Raymon to centralize and query structured debug logs from apps (local or remote), inspect payloads during incident response, or integrate with an agent harness that needs a searchable log store. Prefer authenticated remote setups to avoid exposing logs.

What's included

Scripts: no extra scripts detected in the skill directory, but the repo provides a runnable binary and demo mode.
References: no separate references folder detected.
Instructions: quickstart to run raymon locally, examples to add it as an MCP server to agent harnesses (Codex CLI example), workflows for search → pick UUID → fetch details, and guardrails for remote auth.

Compatible agents

{}

Audit Summary

Raymon is an MCP server for searching and inspecting Ray-style log entries. The SKILL.md is well-written with clear workflows for local and remote setup, search/fetch patterns, and proper security guidance (auth token enforcement, warnings against insecure remote mode). No bundled scripts to test. The skill targets a specific niche (Ray ecosystem users) but provides genuine debugging value.

Watch Out

Requires the raymon binary installed and running before the MCP server can be used
RAYMON_AUTH_TOKEN='change-me' is a placeholder — users must set their own token for remote setups
No scripts included — purely instructional SKILL.md

Notes

Clean skill with good security posture. Explicitly warns against RAYMON_ALLOW_INSECURE_REMOTE=1. Auth is promoted as default for remote setups. Architecture is flat (no scripts/references dirs). Useful for Ray ecosystem developers but niche audience.

Information

Repository: raymon
Stars: 17
Installs: 0

Trust Score

Overall84

Security98

Code Quality72

Architecture68

Usefulness60

Related Skills

Retriever (Membrane CLI)

Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Caveman Compress

Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.

ClawPod / Massive Unblocker

Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)

Retriever (Membrane) Integration

Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.

Ip2Location IO Automation (Composio)

Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.

Canary — Post-Deploy Visual Monitor

Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail

Monitoring Stack Deployer

Deploy and configure production-ready monitoring stacks (Prometheus, Grafana, Datadog) with collectors, dashboards, and alerting rules for Kubernetes, Docker, o

Back to Skills