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.
-
Enterprise-grade Model Context Protocol (MCP) server for Microsoft Active Directory DS with 100 essential tools, Windows DPAPI Credential Vault, and strict security guardrails.
MIT -
tooldirectory-mcpgithub.com/AI-Directory-Partners/tooldirectory-mcpupdated this year
MCP server for the AI Tool Directory — search 2,000+ AI tools, compare them, and check whether a tool is still active, defunct, or acquired.
MIT ★ 1 -
agent101github.com/rachelsu-blip/agent101-mcpupdated this year
MCP server for Agent101 - a directory of 300+ AI tools across 15 categories. Search, browse, and get recommendations for AI agents, MCP servers, and developer tools.
npm MIT -
NeuralReapergithub.com/the-artist111/NeuralReaperupdated this year
AI-powered penetration testing framework with 55+ MCP tools, CVE intelligence, Active Directory, and autonomous security workflows.
MIT ★ 1 -
mcp-file-toolsgithub.com/rog0x/mcp-file-toolsupdated this year
MCP server for file operations: directory tree, file stats, duplicate finder, lines of code counter, file search by name/content/size/date Install: npx @rog0x/mcp-file-tools
npm MIT -
MCP server for the PixDig directory: 100+ vetted AI tools and 40+ LLMs inside Claude Code, Codex, Cursor and Gemini CLI. Read-only.
MIT ★ 1 -
MCP server for Altimateguide — an AI agent can list a software tool in the directory for editorial review. Works with Claude, Cursor, and any MCP client.
npm MIT -
Website Technology Detector, CMS & Theme Checker (WordPress, Shopify, Laravel, Next.js), 110M+ Reverse Domain Lookup Index & 190+ AI Tools Directory by GrowthNiq.
NOASSERTION ★ 1 -
Public remote MCP server for the AgentScout directory: 2,065+ AI agent tools and 276 MCP servers. Docs + registry manifest.
MIT -
MCP servers exposing libvirt, Active Directory, WinRM, SQL and shell tooling for infrastructure automation
MIT -
MoCoPo CLI — the MCP server directory in your terminal. Search, install, publish, claim, and review MCP servers. Execute 75+ gateway tools. Works as an MCP server itself (stdio or remote).
npm SEE LICENSE IN LICENSE -
MCP server for the Rise of Machine AI tools directory.
npm MIT -
My-Network-MCPgithub.com/danielrosehill/My-Network-MCPupdated this year
MCP for providing a manually managed LAN directory to AI tools
npm ★ 1 -
MCP server for reading, writing and editing files inside chosen directories, with an optional shell tool.
npm MIT -
dirgrepgithub.com/AstraBert/dirgrepupdated this year
CLI tool and MCP server to grep an entire directory in one go
npm MIT ★ 5 -
Local RAG over a directory. Incremental. Served as MCP tool + CLI.
MIT -
Steward MCP — 25 tools for x402 agent commerce: trust verification, spend controls, merchant directory
npm MIT -
go-mcp-textgithub.com/benjaminmwilson/go-mcp-textupdated this year
An MCP (Model Context Protocol) server written in Go that exposes a directory of text files as tools and resources
MIT -
Altimateguideno update data
Submit a software tool to the Altimateguide directory for editorial review. Exposes one tool, submit_tool, so an AI agent can list a tool — the submission is queued for human review and never published automatically.
smithery -
A tool for copying gitignored files from a source git repository to a new worktree directory. Works as both a CLI tool and MCP server.
nuget -
deletegithub.com/hegner123/deleteupdated this year
MCP tool that moves files and directories to macOS Trash instead of permanently deleting them
MIT -
File explorer — browse, search, create, move, and manage files and directories — 17 MCP tools.
MIT -
importsgithub.com/hegner123/importsupdated this year
Dependency/import mapper MCP tool. Scans directories for import statements across 11 languages and outputs structured JSON for blast radius analysis before refactoring.
MIT -
The open-source community directory for discovering 520+ developer tools, free APIs, AI agents, and open-source projects. Includes terminal CLI and MCP server.
npm MIT -
vaulthash-mcpgithub.com/AlexeySamosadov/vaulthash-mcpupdated this year
MCP server giving AI agents local file-integrity tools — hash, verify, compare (free), plus directory manifest & duplicate-finder (Pro). Files never leave the machine.
NOASSERTION -
MCP server for Indian bank IFSC data — lookup, offline validation, branch search, bank directory — plus a routing eval harness that scores its own tool descriptions.
MIT -
Detect It Easy MCP server for Claude and Codex: binary triage, ten tools, graphical setup, and bounded directory scans.
NOASSERTION -
A free, independent privacy resource: a sourced privacy tools directory, practical guides, and a read-only MCP server for AI assistants.
AGPL-3.0 -
MCP server for Omnissa Horizon VDI management — exposes the Horizon REST API as tools for inventory, monitoring, configuration, entitlements, Active Directory, and help desk.
★ 1 -
codeguard-mcpgithub.com/Miles0sage/codeguard-mcpupdated this year
AI-powered code review + OWASP security scanner MCP server. 8 tools: smart review, security scan, MCP server audit, directory scan. Catches what linters miss.
-
Microsoft Graph MCP server — 85 tools across mail, calendar, meetings, Teams chat, files, search, people, directory, tasks and OneNote, over stdio or Streamable HTTP.
pypi MIT -
🚀 Powerful flexible project scaffolding tool - supports Git repositories and local directory templates, one-click generation of React/Vue/Node.js project structures, integrated AI assistant calling capabilities, and bilingual internationalization support
npm MIT -
memory-bank-loader-mcpgithub.com/abeyuya/memory-bank-loader-mcpupdated this year
This is an MCP server for retrieving all files in the memory-bank directory at once. Its purpose is to reduce AI tool invocation frequency when loading memory-bank, saving both time and money.
npm MIT ★ 4 -
ha-template-mcpgithub.com/morganwm/ha-template-mcpupdated this year
An MCP server for Home Assistant that exposes Jinja2 templates as tools. The server reads YAML template files from a directory and makes them available for querying Home Assistant state information.
★ 1 -
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
pypi MIT ★ 49 -
huozigithub.com/Dachein/huoziupdated this year
活字 huozi — an Agent-native cloud drive. Speaks the Claude Code tool dialect bit-for-bit, so any MCP-capable Agent can mount it as a working directory.
MIT -
scraper-api-mcpgithub.com/bitterdev/scraper-api-mcpupdated this year
MCP server for scraper-api.com — one tool per endpoint. Pull public web data (social platforms, business directories, real estate) as JSON from your agent.
MIT -
Unofficial MCP server exposing skills.sh - the agent skills directory - as MCP tools: search, leaderboards, skill details, security audits and official skills
npm MIT -
Gutenberg Extractor is a powerful tool designed to process .gutemberg files by extracting large embedded assets like SVGs, PNGs, and JPEGs. It reorganizes the content into a clean, web-friendly index.html file and a structured assets/ directory.
-
mcp-obsidian-toolsgithub.com/dp-veritas/mcp-obsidian-toolsupdated this year
A Model Context Protocol (MCP) server that allows MCP clients (Cursor, VSCode, Claude Desktop, etc.) to read and search any directory containing Markdown notes, such as an Obsidian vault. This server exposes a rich, read-only toolkit of obsidian_-prefixed MCP tools for working with vault metadata (tags, links, frontmatter), filenames, and more
AGPL-3.0 ★ 4 -
Model Context Protocol (MCP) server for Smarter.Poker: 26 poker equity, GTO preflop range, Malmuth-Harville ICM, PLO pot-limit bet, live cardroom directory, and TDA floor ruling tools
MIT -
A confined generation tool: runs an LLM over a local directory read-only and emits the output as a product that is always labeled untrusted. CLI + stdio MCP server on the myelin substrate, optional in-process creatine engine. Part of the Nootropics stack.
GPL-2.0 -
FileSensegithub.com/hemant-kothari/FileSenseupdated this year
A file organization tool that auto generates simple descriptions for every file and folder, updating them in real time as things change. Supports all file types, manual edits, and now exposes descriptions to AI assistants via an MCP server, so you and your AI tools can navigate messy directories without opening everything.
-
Automate the extraction of your codebase context for Large Language Models. This tool scans your project directory, respects .gitignore rules, and formats the output for seamless integration with MCP-compatible clients. Save time and enhance your LLM's context with structured codebase information.
smithery -
This is an MCP server for retrieving all files in the memory-bank directory at once. Its purpose is to reduce AI tool invocation frequency when loading memory-bank, saving both time and money.
npm MIT -
150-tool MCP server for codebase analysis — dependency graphs, architecture layers, security scanning, refactor plans, git history, and more. Works with GitHub and GitLab repos (cloud + self-hosted) and local directories.
npm Elastic-2.0 -
Zero-dependency .NET implementation of the Open Knowledge Format (OKF) v0.2: knowledge bundles as directories of markdown files with YAML frontmatter. Library, CLI validator, static site renderer, Agent Framework tools and MCP server.
nuget LGPL-3.0 ★ 4 -
Mana is an MCP server that saves 50-70% on AI coding API costs. It intercepts bloated tool responses — file reads, bash outputs, directory searches, MCP calls — and routes them through lightweight models benchmarked for accuracy. Your prompts and your AI's responses stay untouched. Same workflow, fraction of the spend.
NOASSERTION ★ 3 -
A Python-based server implementation of the Model Context Protocol (MCP) designed for Retrieval-Augmented Generation (RAG) workflows. It manages the flow of context, tool invocation and model output in one unified service. Supports modular “Models” and “Modules” directories for extensible integrations, environment configuration, and easy deployment
MIT ★ 4 -
A Java-based server leveraging Apache Tika to extract content and metadata from files (PDF, DOCX, TXT, etc.) in a local files-to-extract directory. Supports HTML (with CSS styling) and text extraction, file listing, and metadata retrieval via MCP-compliant tools and REST APIs. Built with Spring Boot, Jetty, and MCP SDK.
-
Kompressrno update data
Upload local files or public file URLs, wait for processing, list uploads, generate expiring private links and permanently delete explicit assets. Requires a Kompressr account with paid API upload access and your own project or scoped API key. The server runs on the MCP client's machine and can read files allowed by that process's operating-system permissions; it does not enforce a directory allowlist. URL uploads download to temporary local storage before uploading to Kompressr. Supply a project UUID to enable upload listing. Account setup tools cannot replace an already configured runtime.
smithery -
MWS S3 MCP AI CLIgithub.com/stufently/mws-s3-mcp-ai-clino update data
An MCP server and command-line client for MWS S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 14 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (32 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
Beget S3 MCP AI CLIgithub.com/stufently/beget-s3-mcp-ai-clino update data
An MCP server and command-line client for Beget S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 10 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (18 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
An MCP server and command-line client for Timeweb Cloud S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 14 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (31 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
An MCP server and command-line client for Cloud.ru S3 object storage in one Go binary. It connects Claude, Cursor or Codex to an existing bucket for browsing, previewing and restoring files. By default the server is read-only and offers 14 tools: buckets, objects, metadata, prefix usage, largest objects and unfinished multipart uploads. Write, delete and bucket-admin tools (32 tools in total) appear only when the matching allow_write, allow_delete or allow_admin switch is on, and a destructive call asks a person first under the default confirm policy. Optional bucket and prefix allowlists narrow access further; local upload and download are confined to a chosen directory. Needs an S3 access key ID and secret. The bundle published here is the linux-amd64 build; binaries for linux-arm64, macOS and Windows and a container image are on the GitHub Releases page.
smithery -
What's Allowedno update data
What your coding agent can do without asking you. Reads every settings file that contributes permission rules — managed policy, project, local, user — and reports the merged picture: which file each rule came from, which defaultMode wins, what proceeds unattended, and which rules the client accepts and then ignores (path rules on Write/Glob, unanchored allow globs, /path rules in user settings that anchor at the config directory, allow rules a deny rule reaches first). Four read-only tools: whats_allowed (full summary), permission_sources, rule_findings, unattended_surface. Read-only by construction — no child processes, no network, no writes; values of env entries are never read, only their names. MIT licensed. Free and MIT, with no telemetry and nothing held back. Built by Shift The Culture, who also publish paid kits for the failure modes this server surfaces: https://shifttheculture.media/agent-tools
smithery -
**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.
smithery -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
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 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