MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server that suggests repository-specific AI agent skills.
go Apache-2.0 -
AI agent for rich text editors: let Ollama, OpenAI-compatible models, Claude or any MCP client (Claude Desktop, Claude Code, Cursor) read and edit a document, with every edit shown as a suggestion to accept or reject.
npm MIT -
Socratic AI Writing & Code Review Coach + 0-Token Google Docs Editor (Go CLI, Zero-GEMINI_API_KEY Host-AI MCP Server & 7-Client Skill Installer with WSL2<->Windows Bridge). Applies UTF-16 inline suggestions (WriteMode.SUGGEST), Socratic hints, multimodal checks, RAG rules, and AI+Human review learning summaries.
★ 3 -
Intelligent code suggestion MCP service that provides AI-powered component and utility method recommendations for AI IDEs.
npm MIT ★ 1 -
Spots CSS that looks AI-made and suggests fixes.
npm MIT -
MCP server for broken link detection, monitoring, and AI-powered fix suggestions. Built with FastMCP 3.x.
pypi MIT -
MCP-coding-assistantgithub.com/AviOfLagos/MCP-coding-assistantupdated this year
Detect hallucinations, repetitive bug fix (AKA. bottomless pit) and help AI coder's with access to documentations and suggest fixes.
MIT ★ 14 -
An AI-powered job recommender system that analyzes resumes, identifies skill gaps, suggests career roadmaps, and fetches live job postings ...
-
This MCP server enables an AI assistant to check the latest documentation of the libraries we are using before suggesting code.
★ 1 -
Collaborative AI-human document editor — real-time annotations, suggestions, and review powered by Claude Code via MCP
npm NOASSERTION ★ 28 -
marble-mcp-servergithub.com/withmarble/marble-mcp-serverupdated this year
MCP server for generating AI-powered learning project suggestions and Marble platform links
npm MIT -
Edit video by editing the transcript. Local, free, MIT. AI edits arrive as suggestions you approve.
pypi MIT -
A knowledge base you own, that AI agents work in — and can only suggest changes to. MCP + Cloudflare Workers.
MIT ★ 1 -
oracle-models-mcpgithub.com/vanppsa/oracle-modelsupdated this year
MCP Server — classifies dev tasks and suggests cost-efficient AI models with client-aware filtering
npm MIT -
Model Context Protocol server for Podio item and task management with AI-powered project/epic suggestions
npm MIT -
MCP server for posting AI code review comments on Bitbucket Cloud pull requests. 17 tools for PR discovery, inline comments, code suggestions, tasks & batch operations.
MIT ★ 1 -
A lightweight TypeScript-based MCP server that provides uniform, deterministic naming suggestions for code entities during AI-assisted development
npm MIT -
aparser-mcpgithub.com/izzipizzy/aparser-mcpupdated this year
MCP server for the A-Parser HTTP API — drive parsing tasks (SERP, positions, suggests) from an AI agent.
npm MIT -
contractwise-mcpgithub.com/marilynceo/contractwise-mcpupdated this year
AI-powered legal contract clause extraction, version comparison, redlining suggestions, and risk detection. All processing on local infrastructure u2014 contracts never leave your network.
-
Local MCP server for Dutch and US English spelling checks, dictionary lookups, and US English style suggestions for AI agents.
MIT -
MCP server providing OpenStreetMap tagging schema tools for AI assistants - validate tags, query values, search presets, and suggest improvements
GPL-3.0 ★ 9 -
ckeditor-agent-demogithub.com/krystiangw/ckeditor-agent-demoupdated this year
ClaimDesk — governed AI editing demo: an agent drafts insurance letters in CKEditor 5, every edit lands as a Track Changes suggestion (built on ckeditor-mcp + ckeditor-integration-mcp)
MIT -
Indonesian editorial travel guide: Astro SSR, React editor, FastAPI, PostgreSQL, Cloudinary, Gemini metadata suggestions, and an MCP server that lets AI agents draft but never publish.
NOASSERTION -
@lucianfialho/build-in-public-mcpupdated this year
MCP server for Build in Public - automatically share your dev progress on Twitter with AI-powered suggestions
npm MIT -
prompt-assessment-mcpgithub.com/jorgeiglopez/prompt-assessment-mcpupdated this year
A tool that helps users become better prompters over time. After every user prompt, the AI agent assesses its quality and — only when there's a concrete improvement to suggest.
-
A CLI and MCP server for analyzing iOS code quality using AI suggestions and test results.
npm -
openrouter-mcpgithub.com/alvinctk/openrouter-mcpupdated this year
MCP server in Python for OpenRouter: offers chat completion and model recommendation tools. AI assistants can query any OpenRouter model (free/paid) and receive task‑optimized model suggestions. Uses MCP Python SDK
MIT ★ 1 -
@iflow-mcp/lucianfialho-build-in-public-mcpupdated this year
MCP server for Build in Public - automatically share your dev progress on Twitter with AI-powered suggestions
npm MIT -
@iflow-mcp/tosin2013-build-in-public-mcpupdated this year
MCP server for Build in Public - automatically share your dev progress on Twitter with AI-powered suggestions
npm MIT -
brain-devgithub.com/mcp-tool-shop-org/brain-devupdated this year
MCP server for AI-powered code analysis — test generation, security audits, coverage analysis, and refactoring suggestions
pypi MIT -
markdocsgithub.com/thakurkharel/markdocsupdated this year
Self-hosted collaborative markdown editor with real-time editing, threaded comments, suggestions, MCP server for AI agents, and a CLI.
MIT ★ 3 -
Persistent AI context + memory — .faf and .fafm, IANA-registered. AI suggests your goal and six W's; you confirm. Anthropic-merged.
npm MIT -
CineMCP is an AI-assisted movie recommendation app that tailors suggestions based on your taste, mood, and real-time movie data using a custom context protocol.
MIT -
MCP server connecting Claude Desktop to the Finance AI Ecosystem — 19 tools across ingest, suggestions, approve/reject, tax analysis, FP&A, audit, treasury, and market data
-
CLI and MCP server for the LibreDesk helpdesk: manage help center articles, AI snippets and FAQ suggestions from the terminal or Claude
npm MIT -
Shared interactive terminal for AI agents: you drive a real shell (cmd/powershell/ssh/…) while an agent joins the same live session over MCP (read-only / suggest / auto). Windows-only (ConPTY).
nuget MIT -
MCP server + CLI for AI-native SEO audits: broken links, internal link suggestions, crawl diffs, optional local embeddings.
npm MIT ★ 2 -
anyapi-mcp-servergithub.com/quiloos39/anyapi-mcp-serverupdated this year
A universal MCP server that connects any REST API to AI assistants (Claude, Cursor, etc.) via OpenAPI or Postman specs. Features GraphQL-style field selection, automatic schema inference, mutation support, and smart query suggestions.
npm NOASSERTION ★ 6 -
mcp-server-getalifeupdated this year
MCP server for GetALife — Zero-Based Budgeting tools that help AI assistants answer budgeting questions with actionable plans, category suggestions, and budget analysis.
npm MIT -
AI-powered Jenkins pipeline intelligence platform with natural language interface. Provides comprehensive pipeline analysis, failure prediction, optimization suggestions, and automated Jenkinsfile reconstruction using Model Context Protocol (MCP) integration.
MIT ★ 3 -
Telegram integration for AI assistants with interactive approval workflows. Your AI asks permission via Telegram before risky actions - approve, deny, or suggest alternatives with custom instructions.
MIT ★ 2 -
@sandcheck/mcpgithub.com/sandcheck/sandcheckupdated this year
Model Context Protocol server that lets AI coding assistants (Claude Code, Cursor, Windsurf) check npm packages against the Sandcheck dataset before suggesting installs.
npm Apache-2.0 -
gcp-searchstale
Claude Code MCP server for intelligent Google Cloud Platform gcloud CLI assistance - enhanced discovery, search commands, explore flags, and get AI-powered suggestions for any GCP task
npm MIT -
@capitalthought/relationship-radar-mcpgithub.com/capitalthought/relationship-radar-mcpupdated this year
MCP server for Relationship Radar (relradar.ai) — query a person, suggest identity disambiguations, run a deep PI investigation, check source health.
npm MIT -
postforged-optimize-mcpgithub.com/crawde/postforged-optimize-mcpupdated this year
MCP server for LinkedIn post optimization — AI-powered engagement scoring, post generation, style refinement, and hashtag suggestions for viral LinkedIn content
npm MIT -
one-shot-uigithub.com/TN0123/one-shot-uiupdated this year
Deterministic screenshot diffing for AI coding agents. Extract design tokens, diff implementations vs reference, get CSS fix suggestions.
npm MIT ★ 6 -
MCP server for on-demand .NET memory profiling with AI-actionable code fix suggestions, collecting heap data in-process over EventPipe
nuget MIT ★ 11 -
Official Model Context Protocol server for Reactive CSS: API reference, examples, validation, feature analysis, bundle suggestions and 0.8 → 0.9 migration for AI coding agents. Offline, read-only, stdio.
npm MIT -
MCP server providing code quality checks (pylint and pytest) with smart LLM-friendly prompts for analysis and fixes. Enables Claude and other AI assistants to analyze your code and suggest improvements.
pypi MIT ★ 21 -
Mullwise: your random thought organizer. Capture 'subject: detail'; AI connects the dots and suggests clearer subjects. Claude plugin + encrypted local MCP server.
MIT -
resume-fit-scannergithub.com/mzterwalexzyy/resume-fit-scannerupdated this year
Pay-per-call OKX.AI ASP: compares resume text vs a job description, returns a fit score, missing keywords, ATS formatting issues, and rewrite suggestions. Stateless, MCP tool.
MIT -
@mintmcqueen/gcommandstale
Claude Code MCP server for gcloud command discovery - search 5,900+ Google Cloud commands, explore flags, and get AI-powered suggestions. Use 'gcommand' to find any GCP CLI command.
npm MIT -
@iflow-mcp/bradthebeeble-coderabbitai-mcpgithub.com/bradthebeeble/coderabbitai-mcpupdated this year
MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests. Enables LLMs to analyze, implement, and resolve CodeRabbit suggestions programmatically.
npm MIT -
correctover-runtime-guardgithub.com/correctover/runtime-guardupdated this year
Real-time RCE/SSRF/credential leak interception for AI agents — 22µs P50, 99.7% detection rate. MCP Server mode with diagnose_error, fault patterns, repair suggestions.
pypi Apache-2.0 -
Advanced Environment Architect & Diagnostic Tool for Model Context Protocol (MCP). Heimdall helps AI agents understand, verify, and fix their execution environment. It provides detailed insights into system architecture, runtime versions, dependencies, and environment variables, along with actionable correction suggestions.
npm -
Zero-config domain availability MCP server for Claude & ChatGPT. Live pricing via Porkbun, premium/auction detection via GoDaddy, AI suggestions, RDAP/WHOIS fallback. Stdio + HTTP.
npm MIT ★ 28 -
YouTube Autocomplete — FlashDatano update data
# YouTube Autocomplete — FlashData Get YouTube search suggestions for a query prefix, language and region. Build keyword idea sheets from actual autocomplete phrases. Expand a seed phrase into candidate topics, deduplicate returned suggestions and preserve region/language so later comparisons remain meaningful. [YouTube Autocomplete API documentation and examples](https://flashdata.dev/docs/sources/youtube_suggestions?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_suggestions-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Autocomplete listing](https://smithery.ai/servers/flashdata/youtube-autocomplete) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_suggestions`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_suggestions` without submitting a data query. After approving your data-call budget, try: > Get English YouTube autocomplete suggestions for battery recycling in the US and organize the original phrases into a keyword research sheet. This server exposes `youtube_suggestions`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call query is required. language defaults to en and region to US; region is a two-letter code. Results are phrases, not search-volume figures or video records. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_suggestions", "arguments": { "query": "battery recycling", "language": "en", "region": "US" } } ``` ## Work with the output Read the suggestion strings in results[0]. Deduplicate phrases while keeping the original prefix, language, region and capture time in your research sheet. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_suggestions", "status": "done", "results": [ [ "battery recycling at home", "battery recycling safely" ] ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Autocomplete returns phrases, not video results or search-volume estimates. A suggestion is not evidence of demand size. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
ShellGuardgithub.com/Shyamyemuka/ShellGuardupdated this year
An AI-powered web-based terminal that intercepts dangerous shell commands before execution, analyzes their risk using LLM-powered intelligence, explains consequences in plain English, and suggests safer alternatives. Built with Archestra MCP agent orchestration, FastAPI, xterm.js, and Next.js.
MIT ★ 2 -
coding-assistantgithub.com/Bessouat40/coding-assistantupdated this year
AI Coding Assistant powered by MCP server : it reads your code locally to provide truly context-aware help, explanations, and suggestions directly related to your files. Code smarter, locally or using external API..
MIT ★ 7 -
bastiongithub.com/BintangDiLangit/bastionupdated this year
Local-first security scanner for developers and AI coding agents — deterministic SAST with stable finding fingerprints, baseline deltas, suggested fixes, and an MCP server.
go MIT