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.
MemPersist
@ravhirizaldi · External

Durable, revision-pinned memory storage and retrieval for AI conversations.

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.
CueMapRun by its publisher: served from their own domain, namespace checked by the registry.
@cuemap-dev · External

Local memory and context retrieval for AI agents through CueMap.

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.
cmssyRun by its publisher: served from their own domain, namespace checked by the registry.
@cmssy-io · External

Headless CMS whose page sections are defined by your own code: pages, records, media, commerce.

4% 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.
ZeroMind (OrigoZero game engine)Run by its publisher: served from their own domain, namespace checked by the registry.
@origozero · External

Build, run and publish 3D games in the Zero engine from Claude Code, Cursor or Codex, over MCP.

10% 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; you sign in with your account.Free to use.
MCP server: One MCP server.
isitdoneRun by its publisher: served from their own domain, namespace checked by the registry.
@raimondasl · External

Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.

4% 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.
Pursers
@swisspra · External

Coordinate AI-agent work on a local-first, owner-controlled MCP board

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 PyPI.Free to use.
MCP server: One MCP server.
apimodels
@stimqq · External

Image, video, chat and speech models with one account — local (npx) or hosted with OAuth sign-in.

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.
Ticket Demo
@markusvankempen · External

MCP server demo — tickets, schema discovery, auth, and PII gating. stdio + HTTP.

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.
Engram
@devinmlowe · External

Cognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams.

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.
Agentos
@officialtanishsharma · External

Local-first persistent memory MCP server for AI coding agents.

3% 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 a package registry.Free to use.
MCP server: One MCP server.
GitHub repo
@thedhruv-07 · External

MCP server for GitHub repo health, commit summaries, issue triage, and RAG Q&A.

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.
tmodloader-mcp
@musharna · External

Drive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state.

4% 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.
Cssprobe CliRun by its publisher: served from their own domain, namespace checked by the registry.
@mack-peng · External

Runtime CSS probe — inspect layout, overflow, scroll chains in a real browser. For AI agents.

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.
Kleap
@kleaphq · External

Build, edit, publish, and manage websites and web apps with Kleap hosting, domains, and analytics.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Engraphy
@devon-clarkk · External

Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.

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

Evidence-backed Android repository knowledge for humans and AI 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.
OpenAPI SyncRun by its publisher: served from their own domain, namespace checked by the registry.
@akintomiwa-fisayo · External

Type-safe MCP server for OpenAPI Sync to inspect, validate, and synchronize OpenAPI specs.

3% 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.
Wwise MCP Server
@williamwaudio · External

Wwise automation via WAAPI: 45 tools, batch super-interfaces, subscriptions, SoundBank, profiler.

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 MCPB.Free to use.
MCP server: One MCP server.
Zhijiangyun Cloud (智匠云)Run by its publisher: served from their own domain, namespace checked by the registry.
@artibot · External

Robot embodied-AI cloud for GPU training, inference, benchmarks, and robot data collection.

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.
JDBC MCP Server
@igorolv · External

Read-only SQL, plans, schema for AI agents: PostgreSQL, Oracle, SQL Server, Firebird, SQLite, JDBC

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.
AI Pensieve MCP
@as-xs · External

Search and cross-reference local AI chat history with read-only tools and source citations.

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.
minitokRun by its publisher: served from their own domain, namespace checked by the registry.
@minitok · External

Verified coding workflows with planning, verification, bounded retries, evidence, and evolution.

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.
Super LogRun by its publisher: served from their own domain, namespace checked by the registry.
@super-log · External

Query your local super-log bench from an AI agent - read-only log tools over the hub.

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.
Layerbridge
@muradyf · External

Read, edit and export the Figma file open in a local plugin. No REST API, no rate limits.

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.

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