Odel

Cloud & IT operations

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

5,106 servers3,891 publishers11 tags

All of Cloud & IT operations

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
OSINT MCP
@rjn32s · External

26 free OSINT tools as MCP tools for AI agents. Auto-installs everything on first run.

22% 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.
Claude Army
@robbhimself-1337 · External

Orchestrate multiple Claude Code agents in parallel from chat

8% 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.
mcp-lint
@robert19001-cmyk · External

Lint MCP tool schemas for cross-client compatibility and agent preflight safety.

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 npm.Free to use.
MCP server: One MCP server.
Grantd
@rafavecchi · External

Grantd MCP server: let your AI agent act on a user's behalf across third-party APIs via OAuth.

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.
Dev Workflow MCP ServerRun by its publisher: served from their own domain, namespace checked by the registry.
@programinglive · External

MCP server to enforce development workflow discipline

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.
Ableton for AI
@peterkolbe · External

Bridge between Ableton Live and AI. Inspect, analyze audio, and control mixing via MCP.

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.
AgentPay VN
@phuocdu · External

Let AI agents collect VietQR payments — generate a QR and auto-confirm settlement.

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.
Ark
@pedroknigge · External

Architecture co-pilot for AI TypeScript (write gate, CI, plan/loop)

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from npm.Deprecated by the publisher: Superseded by io.github.pedroknigge/arkgate (npm: arkgate)Free to use.
MCP server: One MCP server.
Calendar.app
@p-l-ta · External

List, search, and manage calendar events via macOS Calendar.app across all configured accounts.

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 npm.Free to use.
MCP server: One MCP server.
Mail.app
@p-l-ta · External

Search, read, send, and manage email via macOS Mail.app across all configured accounts.

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.
Launcher
@oneprofile-dev · External

Single MCP hub: discover, add, audit, and govern MCP servers across every AI client.

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.
Ratary Memory MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@ontorata · External

Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context.

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 npm.Free to use.
MCP server: One MCP server.
WarpwebRun by its publisher: served from their own domain, namespace checked by the registry.
@northbeamsoftware · External

Research, build, and deploy AI-generated websites via the Warpweb API.

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.
PQC-Khepra MCP — CMMC Autopilot & AI Security Recorder
@nouchix · External

Post-quantum CMMC compliance scanner & AI agent attestation. FIPS 140-3, ML-DSA-65, 36K+ mappings.

8% 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.
Aiglare
@nugehs · External

Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.

5% 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.
bouncerRun by its publisher: served from their own domain, namespace checked by the registry.
@nugehs · External

Static compliance-controls checker for UK Online Safety Act & ICO Children's Code. CLI + MCP.

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 npm.Free to use.
MCP server: One MCP server.
Opengate
@nickjlamb · External

Check whether an AI answer is grounded in its context — deterministic, no LLM judge.

5% 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.
AgentWatch
@nicofains1 · External

Multi-agent observability: cascade failure detection, heartbeats, and forensic replay

5% 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.
DiskCleanKit
@namtran · External

MCP server for DiskCleanKit - One Touch Scan and Clean for Mac

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.
Recon Kit
@nan786521 · External

Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.

12% 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.
x402 ToolsRun by its publisher: served from their own domain, namespace checked by the registry.
@mizukaizen · External

melis x402 Tools — 22 pay-per-call APIs for AI agents. No accounts, no API keys. USDC on Base.

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.
DNS MCP Server
@mclose · External

Real-time DNS security analysis — DNSSEC, email auth, and RDAP. Built for SOC investigations.

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 Docker.Free to use.
MCP server: One MCP server.
ResearchTwin
@martinfrasch · External

Federated research discovery with S-Index metrics across a network of digital twins.

5% 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.
Rundeck
@mariomorenodev · External

50 tools to manage Rundeck jobs, executions, projects, nodes, and system via MCP

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.

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