Topic · Agent Workflows
Best MCP servers skills, page 8
MCP servers skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 337 | Review many client Odoo databases at once through odoo-mcp's cross-instance tools — fleet-wide accounting health, per-client aging, partial-failure triage — for agencies and partners managing 5–50… | erpipe-org/ | 421 | — | ~699 | Automated safety check: Pass | MIT | 1 mo ago |
| 338 | 338.Roslynk How to use the Roslynk MCP tools (mcproslynk) effectively for .NET work. | mrpmorris/ | 132 | — | ~3.3k | Automated safety check: Pass | MIT | yesterday |
| 339 | A skill your agent uses when the cardputer MCP tools (notify, ask, confirm, show, progress) are available in the session, or the user mentions their Cardputer / handheld / "buzz me" / "page me". | dakshaymehta/ | 208 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 3 mo ago |
| 340 | 340.Vexa MCP Setup Set up or fix the Vexa MCP connection for this plugin — where the API key comes from, hosted vs self-hosted URL, and how to check the connection… | Vexa-ai/ | 2.9k | — | ~289 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 341 | 341.Kuaidi100 Where a parcel is, when it will arrive and what a shipment would cost, through the 快递100 MCP server: any Chinese courier (顺丰, 京东, 中通, 圆通, 韵达, 邮政 and more) from a tracking number. | nano-muse/ | 608 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | today |
| 342 | 342.Buddy Graph Generate and open an interactive visualization of Buddy guard-mode reasoning data using Buddy's local CLI command. | fiorastudio/ | 115 | — | ~290 | Automated safety check: Pass | MIT | yesterday |
| 343 | QA MCP tool changes with local CLI and real agent clients. An agent skill from getsentry/toolkit. | getsentry/ | 920 | — | ~1.3k | Automated safety check: Pass | Unknown | yesterday |
| 344 | 344.Openai Docs A skill your agent uses when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or… | Haohao-end/ | 791 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 345 | A skill your agent uses when working with ComfyUI workflows through FL-MCP or similar MCP tools: inspect, explain, create, edit, debug, compact, validate, queue, screenshot, or organize node graphs… | filliptm/ | 127 | — | ~3.6k | Automated safety check: Pass | MIT | 26 days ago |
| 346 | Searches a codebase with hybrid semantic and lexical retrieval plus neural reranking through MCP tools, for finding implementations and grounded answers. | Context-Engine-AI/ | 402 | — | ~14k | Automated safety check: Pass | MIT | 3 mo ago |
| 347 | Search context-mode's persistent FTS5 knowledge base for previously indexed local project content, documentation, or session memory. Trigger… | mksglu/ | 26k | — | ~250 | Automated safety check: Pass | Unknown | today |
| 348 | 348.PR Review Reviews pull requests for the Confluent MCP server. An agent skill from confluentinc/mcp-confluent. | confluentinc/ | 167 | — | ~4.6k | Automated safety check: Notes | MIT | today |
| 349 | Autonomous, spec-driven, multi-agent pipeline that takes an EDT-MCP task or issue end-to-end — research → critics → architect → parallel development → review loop → tests → live-stand check →… | DitriXNew/ | 296 | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | 3 days ago |
| 350 | Installs and connects the Forgetful CLI in local or remote mode, sets up token auth for CI, and proves the setup with a real round-trip call. | ScottRBK/ | 301 | — | ~898 | Automated safety check: Notes | MIT | yesterday |
| 351 | Automates Accelo tasks through Composio's Accelo toolkit and the Rube MCP server, with a search-first routine so tool schemas are always current. | ComposioHQ/ | 77k | 3 repos | ~727 | Automated safety check: Pass | No licence | 22 days ago |
| 352 | 352.Project Release Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work. | swimmwatch/ | 164 | — | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 353 | Build, install, and hot-reload Nimbalyst extensions using MCP tools. | nimbalyst/ | 1.9k | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 354 | 354.Sereinflow Connect to SereinFlow MCP, load its live routing guide, and operate only the requested capability. | fhhyyp/ | 187 | — | ~2.2k | Automated safety check: Pass | No licence | 14 days ago |
| 355 | 355.Triage Find worthwhile FastMCP issues to work on in a backlog or release window, verify promising candidates, and present concrete picks with existing PR links. | PrefectHQ/ | 28k | — | ~573 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 356 | 356.Nlm Skill Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM. | iusztinpaul/ | 179 | 1 repo | ~6.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 357 | Keeps an n8n MCP session pointed at the right n8n instance, with rules for discovering, switching and verifying the target before credential writes and for recovering from misroutes. | czlonkowski/ | 6.4k | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 358 | A skill your agent uses when benchmarking rubydex MCP against plain Grep/Glob for Ruby code tasks. | Shopify/ | 364 | — | ~1k | Automated safety check: Pass | Unknown | 2 days ago |
| 359 | 359.Deep Links Deep links in ToolHive Studio. An agent skill from stacklok/toolhive-studio. | stacklok/ | 171 | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 360 | 360.Lightpanda Lightpanda browser, drop-in replacement for Chrome-based browsing in any AI agent - faster and lighter for tasks without graphical rendering like data retrieval. | lightpanda-io/ | 101 | — | ~6k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 361 | Complete JetBrains MPS workflow guide for DSL projects — models, languages, generators, node JSON blueprints, type queries, validation, MPS MCP tool usage, and the index of companion skills. | JetBrains/ | 1.7k | — | ~6.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 362 | Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution… | kajisho5/ | 1.9k | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 363 | Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. | glittercowboy/ | 2k | — | ~1.5k | Automated safety check: Pass | MIT | 6 mo ago |
| 364 | Creates and validates dubbo-go-pixiu MCP gateway conf.yaml. An agent skill from apache/dubbo-go-pixiu. | apache/ | 567 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 365 | 365.Horosa Agent Use Horosa (星阙) local metaphysics MCP tools correctly — 110 techniques: Western astrology natal chart, solar return, progressions, primary directions, horary, electional 择日, birth-time… | Horace-Maxwell/ | 450 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0-only | 4 days ago |
| 366 | 366.Memorywhale Query and write durable debugging memory recorded by MemoryWhale. | wuisabel-gif/ | 154 | — | ~765 | Automated safety check: Pass | MIT | 3 days ago |
| 367 | Searches a locally cached, security-graded catalog of agent skills and MCP servers, and returns install commands after checking each one's grade. | zhuyansen/ | 413 | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 368 | 368.Bat Adhoc Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. | homeassistant-ai/ | 5k | — | ~1.4k | Automated safety check: Notes | MIT | yesterday |
| 369 | 369.Projectatlas Use ProjectAtlas before broad source reads, preferring the installed short atlas CLI for an exact checkout and MCP for registered worktree routing, compact session briefs, or federated graph evidence. | styler-ai/ | 443 | — | ~9.2k | Automated safety check: Pass | MIT | 4 days ago |
| 370 | 370.MCP Musescore Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin. | ghchen99/ | 110 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 371 | Triage a UI Verify build from your coding agent via the UI Verify MCP — bucket a build's changed stories into real regressions vs cosmetic reflow vs rendering noise, summarize the real regressions… | igrlk/ | 154 | 1 repo | ~2.9k | Automated safety check: Pass | MIT | 27 days ago |
| 372 | Covers the Tiger Brokers OpenAPI Python SDK for market data, stock, futures and options trading, push subscriptions, a CLI and an MCP server, defaulting to paper trading. | qusong0627/ | 1.7k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 373 | Analyze and resolve APIView review feedback on Azure SDK PRs. | Azure/ | 121 | — | ~549 | Automated safety check: Pass | MIT | 4 mo ago |
| 374 | 374.Gas Execution Guidelines for writing and executing Google Apps Script code using ggsrun and finding documentation via workspace-developer. | tanaikech/ | 173 | — | ~2.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 375 | 375.Joplin Orchestration guidance for Joplin note, notebook, and tag management tools | alondmnt/ | 173 | — | ~897 | Automated safety check: Pass | MIT | 28 days ago |
| 376 | Guides scene and world building in Unreal Engine through the Flopperam MCP: placing actors, sculpting landscapes, scattering foliage, editing materials and verifying the level. | flopperam/ | 1.1k | — | ~1.4k | Automated safety check: Pass | No licence | 3 mo ago |
| 377 | Monitored single-subtask execution workflow. An agent skill from RoboClaw-Robotics/RoboClaw. | RoboClaw-Robotics/ | 167 | — | ~1.2k | Automated safety check: Pass | No licence | 6 mo ago |
| 378 | 378.Test MCP Build and test MCP tools using direct API calls or MCP Inspector. | tomaspavlin/ | 121 | — | ~593 | Automated safety check: Notes | MIT | 6 mo ago |
| 379 | 379.Sciverse A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original… | opendatalab/ | 120 | — | ~3k | Automated safety check: Pass | Unknown | 21 days ago |
| 380 | 380.Trace MCP Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. | nikolai-vysotskyi/ | 189 | — | ~1.6k | Automated safety check: Notes | MIT | today |
| 381 | 381.Neurolink Guide Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink. | juspay/ | 145 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 382 | Capture reproducible real-use evidence for keep-mcp features and fixes through an MCP client and the Google Keep interface. | feuerdev/ | 105 | — | ~1.7k | Automated safety check: Pass | MIT | 4 days ago |
| 383 | 383.Open Knowledge Authoritative agent-runtime contract for working inside an OpenKnowledge project — a markdown-CRDT knowledge base exposed over MCP. | inkeep/ | 4.5k | — | ~4.7k | Automated safety check: Pass | GPL-3.0 | yesterday |
| 384 | Add or retrofit Tenuo authorization for AI-agent tools and effects. | tenuo-ai/ | 103 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
Explore related skills
Category
More topics in Agent Workflows
- Subagents1,016
- Agent instruction files743
- Multi-agent orchestration526
- Agent memory511
- Skill authoring501
- Planning497
- Brainstorming462
- Hooks and plugins353
- Autonomous loops323
- Context engineering299
- Session handoff262
- Requirements gathering233
- Task breakdown225
- Human-in-the-loop approvals202
- Skill management196
- Codebase knowledge for agents189
- Verification before completion172
- Agent evaluation and testing133