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.
-
mode-manager-mcpgithub.com/niclasolofsson/mode-manager-mcpupdated this year
Mode Manager MCP: Server for managing VS Code .instructions.md files (GitHub Copilot persistent memory)
pypi MIT -
mcp-servergithub.com/AgentBase1/mcp-serverupdated this year
AgentBase MCP server — search and retrieve agent instruction files via MCP tools
MIT ★ 1 -
agentbase-mcpgithub.com/agentbase1/mcp-serverupdated this year
MCP server for the AgentBase agent instruction registry — search and retrieve system prompts, skills, workflows, and more
npm MIT -
mode-manager-mcpgithub.com/NiclasOlofsson/mode-manager-mcpupdated this year
MCP Memory Agent Server - A VS Code chatmode and instruction manager with library integration
MIT ★ 10 -
Insitu keeps your AI instructions and skills in one vault, and every project subscribes to exactly the set it needs, so guidance stops drifting between projects.
MIT -
csoai-eu-ai-act-art-13-ifu-mcpgithub.com/Council-of-AI-CSOAI-org/csoai-eu-ai-act-art-13-ifu-mcpactive
🔌 Exposes EU AI Act Article 13 Instructions for Use generator - provider-side IFU + FRIA crosswalk. MIT. By MEOK AI Labs.
NOASSERTION -
osmpgithub.com/octid-io/cloudless-skyupdated this year
OSMP -- Octid Semantic Mesh Protocol. Deterministic agentic instruction encoding.
pypi Apache Software License -
One-command installer for the Token Optimizer MCP server, skills, plugins, gateway config, and default-on instructions.
npm Apache-2.0 -
An MCP server for agent memory and instructions.
-
AI Agent, Instructions, Prompts, and MCP Servers, in a Go Post Quantum Cryptography project
AGPL-3.0 -
context42-iogithub.com/context42-io/context42updated this year
MCP server for semantic search over personal coding instructions and documentation
pypi MIT -
Hugeicons MCP Serverno update data
Integrate Hugeicons seamlessly into your applications. Discover icons, access platform-specific usage instructions, and enhance your projects with comprehensive documentation and examples.
smithery -
prompt-capsulegithub.com/FeilixX/prompt-capsuleupdated this year
Short-lived text/plain URLs for long prompts and agent instructions
MIT -
Assertline's hosted MCP server: find your recorded web tests, run them and read step-by-step results. Instructions only.
MIT -
Pack bug screenshots into AI coding instructions with MCP Server integration
npm MIT -
UIAnalyzerMCPgithub.com/0x-Professor/UIAnalyzerMCPupdated this year
UI Analyzer MCP Server. It analyzes website UIs and provides precise fix instructions for AI coding assistants.
MIT ★ 4 -
DeepWiki MCP proxy that preserves public wiki instructions and filters unavailable tools.
npm -
cortiviumgithub.com/Cortivium/cortiviumupdated this year
Create persistent AI tools through conversation. Ghost Skills turn plain-language instructions into real MCP tool registrations that trigger reliably — every time.
Apache-2.0 ★ 6 -
Bootstrap projects with pre-configured instructions, tests, and linters that guide AI coding agents to produce reliable code
npm BSD-2-Clause-Patent ★ 13 -
vitricgithub.com/opengeek/vitricupdated this year
A generic MCP server for Obsidian vaults. Connect any vault (or multiple vaults) to AI agents without imposing folder structure, frontmatter schema, or governance policies. Each vault defines its own agent instructions.
-
Local RAG MCP Server for opencode - with automatic MCP instructions for project/common indexing
npm MIT -
Read-only MCP server that extracts and displays image data URIs embedded in Solana SPL Memo instructions.
Apache-2.0 ★ 4 -
A project demonstrating how to expose a simple FastAPI CRUD API as a set of tools using FastMCP, with Docker containerization. Includes connection instructions for Gemini CLI and Copilot Chat.
★ 1 -
Gadriel AI Security Harness for GitHub Copilot — local MCP server, prompts, and instructions for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
Apache-2.0 ★ 2 -
Shared long-term memory and core instructions across every AI client, as a small MCP server.
MIT -
Memory server for MCP clients (TypeScript, SQLite/FTS5): quarantines injected instructions and records provenance; on npm.
MIT -
⚡ High-performance linter, cache-layout optimizer, and garbage collector for AI agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules) in Rust.
MIT ★ 4 -
MCP server answering x86 questions agents hallucinate - instruction forms, flags read/written, CPL, CPUID extension, exceptions, CR/MSR bits - built from Intel XED (Apache-2.0) data.
MIT -
MCP server for time-travel kernel debugging: record a QEMU run, replay it, step backwards, and ask 'which instruction last wrote this address?' - with file:line.
MIT -
An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development tools.
MIT ★ 21 -
MSFS-SimConnect-MCPgithub.com/TheDigitalNinja/MSFS-SimConnect-MCPupdated this year
Model Context Protocol (MCP) server for Microsoft Flight Simulator 2024. Exposes real-time SimConnect flight data - position, altitude, airspeed, autopilot, engine status - to AI agents like Claude. Read-only tools for AI-powered flight instruction.
Unlicense ★ 3 -
mcp-ai-agent-guidelinesgithub.com/anselmoo/mcp-ai-agent-guidelinesupdated this year
MCP server exposing public instruction workflows as tools, backed by hidden AI agent skills for requirements, orchestration, quality, research, evaluation, governance, resilience, and physics-inspired analysis
npm MIT -
Local-first unified index for code, data, Agent instructions, Skills, and cross-Agent project memory across 16 coding-agent harnesses.
NOASSERTION -
MCP server that generates PRD, SRS, ERD, SDD, a design spec, a traceability matrix, and agent instructions as Markdown. Missing input is marked [NOT SUPPLIED], not invented.
MIT -
What a checkout you did not write tells your agent to do — instruction files, hook commands, declared MCP servers, and repo-shipped skills. Read-only MCP server.
MIT ★ 1 -
Manifests and install instructions for the Syfert legal-research MCP server - verify every citation, check whether a case is still good law, audit a whole brief. 10.7M U.S. opinions + statutes for all 50 states.
NOASSERTION ★ 3 -
DevOps-MCP-Servergithub.com/IranUdesha/DevOps-MCP-Serverupdated this year
A production-ready MCP (Model Context Protocol) server that serves an internal DevOps knowledge base — skills, instructions, prompts, and policies for Python, Ansible, Terraform, Docker, Kubernetes, and CI/CD — to AI assistants over Streamable HTTP.
★ 1 -
@oleksandr.rudnychenko/sync_loopupdated this year
Self-correcting 7-stage agent reasoning loop (SENSE→GKP→DECIDE+ACT→CHALLENGE-TEST→UPDATE→LEARN→REPORT). MCP server + CLI that scaffolds instruction files for GitHub Copilot, Cursor, and Claude Code.
npm MIT -
Prompt injection scanner for documents, web pages and RAG content: instruction overrides, spoofed chat roles, hidden text and data-exfiltration attempts, as a CLI and an MCP server
npm MIT -
Catch the instructions hidden in a document before your agent follows them. Finds text a model reads but a person cannot see in PDF, DOCX and HTML. CLI, library and MCP server.
Apache-2.0 -
Shared, persistent memory for any AI agent. Agents recall what your workspace established — instructions, decisions, facts, preferences, active working threads, and grounded PDF/DOCX/CSV/web documents — before they act, then report outcomes so confidence
npm Apache-2.0 -
minecraft-mcp-servergithub.com/yuniko-software/minecraft-mcp-serverupdated this year
A Minecraft MCP Server powered by Mineflayer API. It allows to control a Minecraft character in real-time, allowing AI assistants to build structures, explore the world, and interact with the game environment through natural language instruction
Apache-2.0 ★ 817 -
im-connectoractive
MCP server that lets agents drive DingTalk (dws) and WeCom (wecom-cli) CLIs: send messages, write reports, create todos, query calendars and approvals. Ships MCP resources, server instructions, structured tool output, and an inline QR login row for the DS
npm MIT -
whats-inherited-mcpgithub.com/stcmain/whats-inherited-mcpupdated this year
MCP server that shows what a checkout you did not write tells your agent to do — instruction files, hook commands wired to agent events, MCP servers it declares, and the skills and subagents it ships.
npm MIT -
Prompt-injection scanner for AI agents: deterministic, documented rules (instruction override, jailbreaks, exfiltration URLs, tool hijack/MCP tool poisoning, hidden Unicode, encoded payloads) returning a risk score, categories and spans. Library + x402 pa
npm MIT -
Give any agent self-improving memory you can trust in production. Every correction is kept, shown to your agent when it matters and enforced on Claude Code and Codex. Built-in memory security: notes cannot instruct the agent, and any edit to the record sh
npm MIT -
An enterprise-grade autonomous AI orchestration engine implementing Model Context Protocol (MCP) to manage GitHub repositories, branches, files, issues, and pull requests via Gemini AI natural language instructions, featuring built-in human-in-the-loop security guardrails, destructive action interception, and granular audit logging.
-
Give AI agents orchestration capabilities with an iTerm2 MCP server for macOS. Coordinate Claude Code, Codex CLI, and other coding agents across terminal sessions: delegate tasks, monitor progress, send follow-up instructions, and verify results.
pypi MIT ★ 1 -
Stop prompt injection in AI inbox and chat agents: scan emails, pages and messages for instructions aimed at the AI, fence untrusted content for the prompt, and gate the tool calls an agent makes after reading it. CLI, library, MCP server. Zero dependencies.
MIT -
quickbooks-mcpgithub.com/nichewizard/quickbooks-mcpupdated this year
A QuickBooks MCP server built for real books. Exposes QuickBooks Online as callable tools over the Model Context Protocol, with every create, update and delete gated behind human approval and a plain-English summary, and all QuickBooks text treated as untrusted input rather than instructions.
Apache-2.0 ★ 5 -
Stop prompt injection in AI inbox triage and chat agents. Scans emails, web pages and messages for instructions aimed at the AI (hidden HTML, invisible Unicode, base64, fake system markers), fences untrusted content for the prompt, and gates the tool call
npm MIT -
@assurly/mcp-servergithub.com/assurly/assurlyupdated this year
MCP server that gives Cursor, Claude Code, VS Code and Windsurf a pre-deploy ship gate. Five tools: scan a path or files, explain a rule, read a hosted verdict, and audit the agent stack itself (MCP config and instruction files).
npm MIT -
xstitchgithub.com/raghavvbiyani/xstitchupdated this year
Cross-tool memory for AI agents. Stitch context across Cursor, Claude Code, Codex, Gemini CLI, Windsurf, Copilot, and 9+ AI tools. Preserves decisions, failed experiments & warnings across sessions. Zero dependencies, MCP + instruction files, BM25 relevance search. Never re-explain your work.
MIT ★ 3 -
Read-only linter for CLAUDE.md, AGENTS.md, SKILL.md and agent rules files: vendor limits, tokens loaded per session, hidden instructions and invisible characters, and files Claude Code or Codex never read. Claude Code plugin, MCP server, CLI, GitHub Action and pre-commit hook. No network. MIT.
npm MIT -
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
Cardano MCPno update data
<p align="center"> <img src="https://cdn.simpleicons.org/cardano/0033AD" width="80" /> </p> <h1 align="center">Cardano MCP Server</h1> A **Model Context Protocol (MCP) server** for interacting with the Cardano blockchain from AI agents and automation systems. This server exposes wallet-aware tools for: - Submitting transactions - Fetching addresses - Reading UTxOs - Fetching balances - Resolving ADAHandles - Checking stake delegation ## Secrets 1. Copy the `.env.example` file to a new file `.env` 2. Specify your seed-phrase (`SEED_PHRASE`). Your seed-phrase is NEVER exposed to LLMs, and is only used for local wallet connection. 3. Configure the wallet connection details. Specify a Blockfrost Project ID (https://blockfrost.io/), or a Kupo & Ogmios URL. ## Docker Installation Build the container ```bash docker build -t cardano-mcp . ``` Run with your secrets ```bash docker run -p 8000:8000 \ -e PORT=8000 \ -e SEED_PHRASE="lizard,llama,frog..." \ -e BLOCKFROST_PROJECT_ID="your_blockfrost_key" \ cardano-mcp ``` ## Manual Installation Clone this repository ```bash git clone https://github.com/IndigoProtocol/cardano-mcp.git ``` Install dependencies ```bash cd cardano-mcp npm install ``` Build & Run ```bash npm run dev - or - npm run build npm run start ``` ## Connecting The URL for the Cardano MCP server will be hosted at http://localhost:8000/mcp ### Claude Desktop Configuration Add to `~/Library/Application Support/Claude/claude_desktop_config.json`: ```json { "mcpServers": { "cardano": { "command": "node", "args": ["/path/to/cardano-mcp/dist/index.js"], "env": { "SEED_PHRASE": "lizard,llama,frog..." "BLOCKFROST_PROJECT_ID": "mainnet123..." } } } } ``` ## Disclaimer By using this Cardano MCP Server and all related tools and technology (“MPC”), you acknowledge and agree that (i) your use of decentralized finance, including MPC and/or AI agents that you empower to manage your digital assets, involves various significant financial risks, including but not limited to, the risk of financial loss caused by MPC design or instructions, impermanent loss, and changes in digital asset prices; and (ii) that you are solely responsible for all MPC actions and transactions, and for securing your seed phrase, private keys, and environment configuration.
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 -
Mailcycleno update data
An email address for your AI agent. Mailcycle lets an agent read, wait for and reply to mail at its own addresses: sign-up codes, verification links, support threads, attachments. Mail is decrypted on the machine running the agent. Mailcycle stores it sealed and can't read it. Needs a [Mailcycle](https://mailcycle.email/agents/) account on Scale or above, and Node 20 or later. ## Before you install: pair the agent On the machine the agent runs on: ```sh npx -y mailcycle-mcp pair --name "Support agent" ``` It prints a line starting with `MC1:`. In the Mailcycle app, open **AI agents**, paste the line, and give the agent an email address. The line carries the key the agent's mail is sealed to, so keep it private. It goes from your terminal to the app and never through Mailcycle. The server needs no other settings. It reads the key that pairing saved. ## Tools | Tool | What it does | |---|---| | `list_addresses` | The agent's addresses, and what it may send. | | `list_messages` | The newest messages, with a preview of each. | | `read_message` | One message in full, with its attachments numbered. | | `read_attachment` | Opens an attachment: text as text, images as images, anything else saved to a folder. | | `wait_for_message` | Waits for new mail, optionally from a sender or with a subject. Good for sign-up codes and verification links. | | `reply` | Replies to the sender of a message, threaded. Can attach files. | | `send_message` | Sends a new message, if the agent may send to anyone. Can attach files. | ## Sending Each agent has a send mode, set in the app: - **Reply only** (the default): it can answer whoever wrote to it, and no one else. - **Send to anyone**: up to 20 messages an hour per agent. - **Read only**: it cannot send. Mail an agent reads can contain instructions written by whoever sent it. Reply only limits what those can make it do. ## What sees what - **Mailcycle** stores mail sealed to keys it doesn't have. - **Your machine** holds the agent's key in `~/.config/mailcycle/agent.json`, readable only by your user. Remove the agent in the app to cut it off. - **Your model provider** sees whatever the agent reads. Also on npm as [`mailcycle-mcp`](https://www.npmjs.com/package/mailcycle-mcp) and the [official MCP Registry](https://registry.modelcontextprotocol.io) as `email.mailcycle/mailcycle`. Proprietary, © 2026 Northlab Studios Ltd. [Terms](https://mailcycle.email/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 -
YouTube Transcript — FlashDatano update data
# YouTube Transcript — FlashData Retrieve available YouTube transcript text with start and end timestamps. Build cited summaries, searchable notes and transcript exports. Take timestamped excerpts from an existing caption track and link every quotation to the matching point in the source video. [YouTube Transcript API documentation and examples](https://flashdata.dev/docs/sources/youtube_transcript?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_transcript-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Transcript listing](https://smithery.ai/servers/flashdata/youtube-transcript) 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_transcript`. 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_transcript` without submitting a data query. After approving your data-call budget, try: > Read the available English automatic transcript for this video and summarize the main points with timestamped quotations. This server exposes `youtube_transcript`, `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 video_id is required; language defaults to en. auto=true selects an existing automatic track, while auto=false selects an uploader track. Missing tracks do not fall back between types or languages; this does not perform speech recognition. 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_transcript", "arguments": { "video_id": "dQw4w9WgXcQ", "language": "en", "auto": true } } ``` ## Work with the output Read results[0].segments. Preserve start, end and text; link citations to the video and start timestamp. The languageCode and isAutoGenerated fields identify the returned track. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_transcript", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "languageCode": "en", "isAutoGenerated": true, "segments": [ { "start": 0, "end": 3, "text": "Example transcript." } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling auto=true selects existing automatically generated captions; it does not run speech recognition. Missing tracks do not fall back to uploader captions or another language. 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