Odel

Cloud & IT operations

Cloud infrastructure, deployments, monitoring, networking, automation and your own servers.

4,979 servers3,780 publishers11 tags

All of Cloud & IT operations

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
FirekeepRun by its publisher: served from their own domain, namespace checked by the registry.
@kapella-hub · External

Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.

6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
MCP Sandbox Computer VM for AIRun by its publisher: served from their own domain, namespace checked by the registry.
@flujo-app · External

Named Docker and Fly Machine sandbox computers with an interactive MCP App dashboard.

7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
ReachpadRun by its publisher: served from their own domain, namespace checked by the registry.
@reachpad · External

Coding agents build full-stack apps in persistent workspaces and share them by link.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Finance MCP
@blahaj-gif · External

Market data, SEC filings and risk tools for Webull, Saxo and IBKR. Only you can send an order.

7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
German Newsfeed MCP Server
@jakolo121 · External

MCP server for the public news API of tagesschau.de, including regional news from ARD broadcasters

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
PostgreSQL (hardened, read-only)
@eszetael · External

Read-only PostgreSQL over MCP. Writes refused at the parsed SQL, plus a READ ONLY transaction.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
OpenProject
@kar-thik · External

91 tools for the OpenProject API v3, with read-only, admin-gate, profile and per-group switches.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Lambdacad
@psalmustrack · External

AI drafting, design review and a drawing memory in BricsCAD on Linux: 128 tools, pure AutoLISP

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
oveccRun by its publisher: served from their own domain, namespace checked by the registry.
@ovecc-labs · External

Architecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate

2% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Weasley DeepMind
@potatohoney-p · External

Secure, fragment-based long-term memory for MCP-compatible AI agents.

6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
gha-doctor
@linnea-bakshi · External

Diagnose GitHub Actions CI: lint, flaky tests, wasted minutes, health score. Read-only MCP tools.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
Seatbelt
@kryptosai · External

MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Skedra Whiteboard
@moonriddim · External

Create, read and live-edit visual boards, Kanban plans, Gantt timelines and diagrams with AI agents.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Testa
@valewnrt · External

Drive the iOS Simulator from an agent: read the screen, tap/type/swipe, replay flows in CI.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
UnlocalhostRun by its publisher: served from their own domain, namespace checked by the registry.
@info-arnav · External

Deploy localhost to a private, authenticated link from your AI coding agent.

7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
misMEMRun by its publisher: served from their own domain, namespace checked by the registry.
@lucasmella-stack · External

Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Lotor
@githubscum · External

A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
OpenAdapt Agent (openadapt-flow bridge)Run by its publisher: served from their own domain, namespace checked by the registry.
@openadaptai · External

Local Beta bridge for governed openadapt-flow workflows and attended actions.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Data ProfilerRun by its publisher: served from their own domain, namespace checked by the registry.
@haiiibin · External

Profiles CSV/Parquet/Excel/JSON files: schema, stats, quality flags and dtype tips for LLM agents.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Vibes-Coded Agent Security and Commerce Tools
@doteyeso-ops · External

Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools.

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Kafka Sentinel
@sanjay-amu · External

Read-only Kafka observability MCP server: cluster health, consumer lag, and replay-readiness.

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Qt4 Doc
@jztan · External

Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Google Antigravity
@turkeryakup · External

MCP server exposing Google Antigravity (agy CLI / Gemini): jobs, codebase analysis, file tools.

18% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Klaket
@huseyinstif · External

Let AI agents watch videos: local transcripts, speakers, scenes, chapters and moment search

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacySoftware developmentAI & agentsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport