📡 MCP Radar

valtors/relay

All-in-one MCP server. Agents get memory, tools, and coordination in one binary.

⭐ 3 stars
⑂ 0 forks
Go
momentum ▲ 5.0
created 2026-07-04
on radar since 2026-07-10
ai-agentsdeveloper-toolsgolangmcpmcp-servermulti-agentopen-sourceorchestration
View on GitHub ↗Homepage ↗

About relay

Local MCP server for files, images, PDFs, web, and workflows.

Runs locally. Your files stay on your machine.

- Runs one MCP server with 40 tools across 7 categories. - Reads and writes local files. - Resizes, crops, converts, rotates, grayscales, and flips images. - Extracts text from PDFs, counts pages, merges files, splits files, and extracts pages. - Fetches web pages and checks status codes. - Converts CSV, JSON, markdown, base64, and regex output. - Works with Claude Desktop, Cursor, VS Code, and other MCP clients. - Supports stdio by default and HTTP with --http. - Enables built-in workflow tools when ANTHROPICAPIKEY is present.

No pile of single-purpose servers. One binary.

Use status first if you want a one-shot command instead of starting the stdio server.

If your editor is listed, write the config:

If you installed Relay from source or a release, relay status prints the same shape:

Resize ./screenshots/hero.png to 1200px wide and save it as ./screenshots/hero-large.png.

Fetch https://github.com/pdfcpu/pdfcpu, summarize what it does, list 3 commands worth trying, and save the notes to ./notes/pdfcpu-summary.md.

- webfetch - filewrite - text formatting tools as needed

A local markdown summary your agent can reuse later.

Read every PDF in ./invoices, extract the text, pull out all dollar amounts, and save one JSON file at ./invoices/amounts.json.

- filelist - pdfextracttext - datajsonformat - filewrite

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/valtors--relay.html)

Related MCP servers

luckeyfaraday/frontier-orchestrator

Multi-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi

⭐ 6TypeScript
okf-memory/okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zer

⭐ 553Go
enowdev/succubus

Cross-agent coordination for AI coding agents. One daemon, one database — so multiple agents in one repo can see each other's plan, tasks, and file claims.

⭐ 15Go
magna-nz/tallybook

Prices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. CLI, Browser UI and MC

⭐ 5Go
Smitner-Studio/facet

Render agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.

⭐ 4Go
gburgyan/aat

Model your API as a graph once. Long-chain integration tests, layer × environment matrices, CI-ready runs, and an MCP server — all from the same YAML.

⭐ 3Go

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.