Odel

Software development

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

5,630 servers4,498 publishers15 tags

All of Software development

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

When the agent writes a bad import, the write doesn’t land. The same check fails the pull request.

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.
klaws — Korean compliance risk scanner
@rostradamus · External

Scan code for Korean compliance risks — PIPA/개인정보보호법, Network Act, Credit Info. Not legal advice.

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

Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.

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.
ATAG
@mmasey · External

ATAG 2.0 (Authoring Tool Accessibility Guidelines) guidance for authoring tool developers

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Letmediff MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@letmediff · External

The official Letmediff MCP server helping you review your code with an agent first workflow

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.
Mcpskills MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@mcpskills · External

Trust scoring for MCP servers, AI skills & npm packages — 15 signals + safety scanning.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Knowledge graph
@zcsabbagh · External

Knowledge graph MCP for student learning with spaced repetition and mastery tracking

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.
TeamMemory
@ysydhc · External

Team experience database - let AI accumulate, retrieve and apply team knowledge across chats.

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.
Repo Memory
@yubinkim444 · External

Shared, git-tracked working memory for AI agents on the same codebase.

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.
Drone CI/CD MCP Server
@yusiwen · External

MCP server for Drone CI/CD: 45 tools for builds, repos, secrets, users and templates

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 Docker.Free to use.
MCP server: One MCP server.
Gmem
@yksanjo · External

Persistent, Solana-aware project memory for AI coding agents. Typed entities + git-aware diffs.

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.
Kimi MCP Server
@x51xxx · External

MCP server bridging AI assistants to Moonshot AI Kimi Code CLI for code analysis and review

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
MindCore Memory MCP
@woshilaohei · External

AI long-term memory MCP server with importance scoring and confidence calibration

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.
multichain-mcp
@wkalidev · External

MCP server for AI agents — Stacks, Celo, and Base in one npm package.

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.
Agent Receipts
@webaesbyamin · External

Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.

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.
Playwright Network Chaos
@vola-trebla · External

MCP server that gives AI agents dynamic network chaos control over Playwright browser sessions

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Playwright Trace Decoder
@vola-trebla · External

MCP server for unpacking and analyzing Playwright trace.zip archives

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.
Code Impact
@vk0dev · External

Dependency graph and blast-radius analysis for local TypeScript/JavaScript repos.

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

Behavioral verification intelligence for AI coding agents. 17 MCP tools. Local-first. MIT.

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.Deprecated by the publisher: Security: <3.0.0 executed plugins from the analyzed repo by default, and fabricated a baseline when git was unavailable. Upgrade to 3.x — https://github.com/vighriday/Veris/blob/main/UPGRADING.mdFree to use.
MCP server: One MCP server.
MLflow
@us-all · External

MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)

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.
Linear Bootstrap
@toolwright-adk · External

Bootstrap Linear projects from natural language — milestones, epics, issues, and dependencies.

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.
Cozo MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@tobs-code · External

Local-first memory system for AI agents with hybrid search and graph reasoning

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

Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.

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.
Kaiten
@theyahia · External

MCP server for Kaiten API — cards, boards. 3 tools.

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.

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