Odel

Software development

Code, repositories, reviews, tests, debugging, databases and developer docs.

5,433 servers4,326 publishers15 tags

All of Software development

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

Versioned agent memory in your own Postgres: portable context, permissioned, audit trail.

7% 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; it needs your API key.Free to use.
MCP server: One MCP server.
ShipCheck
@wtaylorwilson · External

Independent preview-URL QA for coding agents. Playwright heuristics, pass/fail pack.

26% 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; no sign-in.Free to use.
MCP server: One MCP server.
WhiteIntel — Ownership IntelligenceRun by its publisher: served from their own domain, namespace checked by the registry.
@whiteintel · External

UBO, sanctions & ownership graph. 23 tools, 130.7M entities, 31 registries.

11% 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; no sign-in.The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
GPT-4o API — JoJ APIRun by its publisher: served from their own domain, namespace checked by the registry.
@jojapi · External

GPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.

10% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
GPT-5 API — JoJ APIRun by its publisher: served from their own domain, namespace checked by the registry.
@jojapi · External

GPT-5: GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time.

20% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
SimplePagesRun by its publisher: served from their own domain, namespace checked by the registry.
@simplepages · External

Build and edit landing pages and websites from your AI assistant, and pull how they are performing.

7% 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.
Python Code Reviewer
@duckdns · External

Security + bug + perf + refactor audit for Python. Returns 0-10 score + MD report.

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; no sign-in.Free to use.
MCP server: One MCP server.
HepCloud MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@hepcloud · External

Manage HepCloud (Turkish cloud) servers and managed PostgreSQL from your AI assistant. OAuth 2.1.

9% 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.
ZeroCMSRun by its publisher: served from their own domain, namespace checked by the registry.
@zerocms · External

AI-native Git-based CMS for Astro. Create and publish content in the browser, without learning git.

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.
Release Branch Planner
@wxt-ai · External

Select a branch for a release

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.A remote server; no sign-in.Gone from the registry since 9 Oct.Free to use.
MCP server: One MCP server.
OutilsIA — Conseiller IA localeRun by its publisher: served from their own domain, namespace checked by the registry.
@outilsia · External

Read-only local AI advice, shared reports and website audits. No PC scan or local actions.

7% 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; no sign-in.Free to use.
MCP server: One MCP server.
Earth LinCRun by its publisher: served from their own domain, namespace checked by the registry.
@earthlinc · External

Compose a finished, hosted web page from a brief, then read it back and refine it.

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; no sign-in.Free to use.
MCP server: One MCP server.
NiceVoisRun by its publisher: served from their own domain, namespace checked by the registry.
@nicevois · External

Free stem, lead/backing vocal, noise and reverb splitting, no account. Train and use RVC voices.

17% 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.
Orq.aiRun by its publisher: served from their own domain, namespace checked by the registry.
@orq · External

Build and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.

7% 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.
Drupal Code Query
@tresbien · External

Drupal core API changes, contrib usage, upgrade readiness, patch verdicts, code search, SQL.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Execute anomaly-detection-sentinel-mcp
@evozim · External

Premium agentic endpoint for anomaly-detection-sentinel-mcp.

19% 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; it needs your API key.Free to use.
MCP server: One MCP server.
Agent Hub - AI-operated public sandbox: demo data, simulated payments, no real bookingsRun by its publisher: served from their own domain, namespace checked by the registry.
@videtion · External

Agent-to-business commerce sandbox: intents, offers, bookings. Demo data, ed25519-signed calls.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
TapcartRun by its publisher: served from their own domain, namespace checked by the registry.
@tapcart · External

Tapcart analytics, App Studio blocks and components, and push campaigns for your mobile app.

7% 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.
OpenWakeWord / microWakeWord — custom wake-word trainingRun by its publisher: served from their own domain, namespace checked by the registry.
@openwakeword · External

Train custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
PenholderRun by its publisher: served from their own domain, namespace checked by the registry.
@penholder · External

Preventive human-approval write-gate for AI agents: writes commit only after a human approves.

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.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
ROKI ConnectRun by its publisher: served from their own domain, namespace checked by the registry.
@roki · External

Verified ROKI Connect payments contract for coding agents: operations, schemas, validator.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Qwen38 Free Gateway
@khs0927 · External

Free Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
MemorySync DocumentationRun by its publisher: served from their own domain, namespace checked by the registry.
@memorysync · External

Search and read the current MemorySync documentation while writing integration code.

2% 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; no sign-in.Free to use.
MCP server: One MCP server.
ishRun by its publisher: served from their own domain, namespace checked by the registry.
@ishlabs · External

Simulated people experience what you are making and report what they noticed and felt.

7% 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.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacyAI & agentsCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport