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. 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.
-
内容合规审核 MCP Server:零依赖本地违禁词检测,8平台独立词库(小红书/抖音/视频号/快手/B站/公众号/闲鱼/通用),P0/P1 分级 + 修改建议,无网络请求无 API Key
-
kevlar-4ugithub.com/churzexo/kevlar-4uupdated this year
Local-first MCP content review server — simulates reader reactions before publishing. 100% offline, no telemetry, AGPL-3.0 open source.
npm AGPL-3.0-or-later -
Self-hosted studio to review, approve and publish social content with your team and your AI agents: frame-accurate comments, approvals bound to the exact file, a calendar that publishes to nine networks, and an MCP server for Claude.
NOASSERTION ★ 5 -
@iflow-mcp/github-review-mcpupdated this year
MCP server for GitHub API interactions - PR analysis, file content, and review posting
npm MIT -
contentrx-mcpgithub.com/thenewforktimes/contentrxupdated this year
ContentRX MCP server — content-design review for Claude Code, Cursor, and any MCP client.
pypi MIT -
@rip-lang/aigithub.com/shreeve/rip-langupdated this year
Persistent multi-model AI consultation MCP — discuss, panel, fresh-review, content-hashed attachments, live model catalog
npm MIT -
TripAdvisor Content API MCP server — location search, details, photos, and reviews for Claude
npm MIT -
Self-hosted CMS that works human or headless: full admin UI plus REST and MCP APIs, built-in semantic search and site chat, and content forking, versioning, diff/merge review, templates, approvals, and static page generation.
MIT ★ 35 -
The model proposes, deterministic code disposes, a human signs. Content-addressed envelopes, hash-chained audit, signed approval — for ledgers, Lean proofs, manuscript claims, reproductions, benchmarks, peer review. Conformance-tested; byte-compatible with @kernel.chat/kbot-finance.
MIT -
🎯 MCP server with 18+ reusable prompt templates for code review, debugging, content writing, and data analysis. Works with VS Code, Claude Desktop, and Cursor. Easy setup, fully customizable.
★ 3 -
A Model Context Protocol (MCP) server for Tripadvisor Content API. This provides access to Tripadvisor location data, reviews, and photos through standardized MCP interfaces, allowing AI assistants to search for travel destinations and experiences.
MIT ★ 64 -
Multi-agent AI system built with LangGraph, LangChain, Groq, and MCP for automated research, analysis, content generation, and iterative quality review.
-
AI-native web production platform — sitemap, content drafts and visual review unified around pages. MCP-first, Cloudflare-native (Workers+D1+R2). AGPL-3.0
AGPL-3.0 -
MCP server for Overleaf projects. Syncs LaTeX files via Git, parses sections, equations, and citations, and exposes them to AI clients for assisted paper review, LaTeX fixes, and content generation.
pypi MIT ★ 66 -
outlook-agentgithub.com/johnkil/outlook-agentupdated this year
Local safety-gated MCP bridge for AI agents and Outlook mail & calendar: metadata-first reads, explicit content, reviewed sends, guarded cleanup.
Apache-2.0 ★ 3 -
speakerweavegithub.com/Brandonmchu/speakerweaveupdated this year
Open-source conference speaker management: CFP and conditional forms, review workflows, speaker CRM, content pipeline, drag-and-drop agenda, public program pages, REST API, hosted MCP server, and one AI agent in-app and in Slack.
MIT ★ 2 -
Cross-vendor multi-model review committee that gates AI/agent-generated content before it ships — consensus-based hallucination defense. Zero dependencies, local-first CLI, MCP server, CI gate exit codes.
GPL-3.0 ★ 1 -
ArXivgithub.com/jasonleinart/arxiv-mcp-serverno update data
The ArXiv MCP Server provides a comprehensive bridge between AI assistants and arXiv's research repository through the Model Context Protocol (MCP). Features: • Search arXiv papers with advanced filtering • Download and store papers locally as markdown • Read and analyze paper content • Deep research analysis prompts • Local paper management and storage • Enhanced tool descriptions optimized for local AI models • Docker MCP Gateway compatible with detailed context Perfect for researchers, academics, and AI assistants conducting literature reviews and research analysis. **Recent Update**: Enhanced tool descriptions specifically designed to resolve local AI model confusion and improve Docker MCP Gateway compatibility.
oci -
YouTube Trainability and License Labels — FlashDatano update data
# YouTube Trainability and License Labels — FlashData Inspect a YouTube video’s Creative Commons license classification. Record the returned license-label signal for a separate rights review. Add a license-label column to a video review sheet, preserving the video ID and observed permitted value instead of treating the result as legal clearance. [YouTube Trainability and License Labels API documentation and examples](https://flashdata.dev/docs/sources/youtube_trainability?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_trainability-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Trainability and License Labels listing](https://smithery.ai/servers/flashdata/youtube-trainability) 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_trainability`. 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_trainability` without submitting a data query. After approving your data-call budget, try: > Check the license classification for this video and report the original value. Explain what it says without granting training or reuse permission. This server exposes `youtube_trainability`, `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 Provide video_id only, plus optional realtime/async mode. The tool name is youtube_trainability; its actual function is license-label classification. It does not read the creator’s third-party training setting. 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_trainability", "arguments": { "video_id": "dQw4w9WgXcQ" } } ``` ## Work with the output Read results[0].permitted together with videoId and collection time. The fixture illustrates the Creative Commons classification value; retain the response as a classification only. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_trainability", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "permitted": [ "all" ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The tool name is youtube_trainability, but it checks a license label. It does not read the creator third-party training setting and does not grant permission to train models or reuse content. 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 -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) 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_search_extended`. 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_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `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 max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. 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_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. 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 -
Human review for AI output: reviewers check model output against policy, with decisions on a hash chain. HTTP, MCP and webhooks. Apache 2.0, free to self-host.
Apache-2.0 ★ 6 -
kevlar-mcpupdated this year
Kevlar: A Local-first, MCP-compliant Multi-Agent armor to stress-test your content before the internet does.
npm ISC -
Swipe through AI-generated batches to keep, toss, or send back with a note - local board + MCP server (MIT)
MIT -
Portable editorial standards and checks for AI-assisted writing: plain language, house style, source comparisons, Agent Skill, CLI and MCP.
npm CC0-1.0 -
Klype AI MCP server over stdio: plan, draft, capture, check, calendar and distribute posts against a company's saved facts and a real person's voice.
npm MIT -
orbixio-studiogithub.com/AhmedAliQadir/orbixio-studioupdated this year
MCP-native video script generation platform — generate structured YouTube scripts via Claude Desktop, review and approve before publishing. TypeScript monorepo.
-
@iflow-mcp/repomixgithub.com/yamadashy/repomixupdated this year
A tool to pack repository contents to single file for AI consumption
npm MIT -
Connect CapCut to ChatGPT, Claude and any AI agent. Export drafts, add captions and share review links from your CapCut account.
NOASSERTION -
mcp-approvalgithub.com/zavora-ai/mcp-approvalupdated this year
Approval MCP Server — multi-stage approval workflows for legal and media-content agents: configurable workflow templates, stage rules (all-of/any-of/quorum), decisions, delegation, escalation, SLA clocks, and an immutable audit trail
cargo Apache-2.0 -
MCP server that clones the style of a reference reel onto your footage — analyze, scaffold, render, and self-review with Remotion
npm MIT ★ 32 -
Official VixAI MCP connector for creating, reviewing, publishing and scheduling Instagram images, 2-10 image carousels and Reels from ChatGPT, Claude and Grok.
MIT -
Semantic Similarity Score (S3): content-based science mapping of research fields from titles and abstracts. Python library, R package and MCP server, plus an open hub for proposing new analyses
pypi MIT ★ 1 -
Write and publish with your agent. A Markdown editor where your agent drafts and you review every change, then publish to your site, newsletter, X and LinkedIn.
npm MIT ★ 36 -
Official Instagram Graph API MCP — multi-account read, publish, comments, analytics + review-gated DMs for Instagram Business/Creator accounts. ToS-safe, no private API.
pypi MIT ★ 17 -
Plan social media campaigns, review posts, schedule approved publishing and read saved Insights through the Influence MCP connector.
MIT-0 -
Management software for a video and marketing production agency: production timeline, frame-accurate video review, crew orders, finance and reports. Django + React, English and Russian, Telegram and Claude (MCP) integrations.
NOASSERTION -
Deprecated: replaced by hitl (Human In The Loop, npx hitl), which does everything questionme does. Questions from an LLM agent, answered on your phone: hundreds at a time, with rich content (files, code, diffs, diagrams, mockups), branching follow-ups, an
npm MIT -
Kabo: your creator partner inside Claude, ChatGPT, Grok Bot and Muse. Remake a viral video with you on camera, right from your phone, plus daily picks, account reviews and scripts for YouTube, Instagram and TikTok.
npm MIT ★ 2 -
Claude plugin (also for OpenAI Codex and ChatGPT) that turns any blog post, product page or recipe into a finished Pinterest pin with InsightPins. Also reviews and improves pins and checks Pinterest bulk upload CSV files.
MIT -
Social media scheduler MCP server for Claude, Claude Code and Cursor: draft, schedule, edit and retry LinkedIn posts (Facebook Pages and Instagram after Meta review). Dry run first, posts only after your yes.
MIT