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.
-
figma-mcpgithub.com/alucardeht/figma-mcpupdated this year
MCP server for Figma API with intelligent context management, pagination, and token optimization
★ 1 -
Navigate and query OpenAPI specs with fuzzy search, pagination, and API testing
pypi -
@devheerim/notion-mcp-servergithub.com/henry-hong/notion-mcpupdated this year
Notion API MCP server with powerful database query support including filters, sorts, and pagination
npm MIT -
webhook-cogithub.com/webhook-co/webhookupdated this year
The official Python SDK for the webhook.co API — a typed client with retries, cursor pagination, idempotency, and secret redaction.
pypi Apache-2.0 -
Model Context Protocol server for MySQL access via HTTP/REST API with strict JSON output, default pagination with bypass, and configurable granular permissions
npm MIT -
The Oura v2 API as an MCP server. Paginates, fixes the date range, warns when data is missing.
pypi MIT -
Token-lean MCP server for the Pixabay image & video API — slim results, 24h cache, free pagination, download-to-server with attribution. Stdlib-only core.
MIT ★ 1 -
Google Search Console MCP server that paginates past the 25,000-row API cap and reports data coverage with every pull.
MIT ★ 1 -
monarchmoney-nodegithub.com/hakimelek/monarchmoney-nodeupdated this year
Node.js/TypeScript API client for Monarch Money with built-in MCP server for AI agents. 30 tools, retry, rate limiting, auto-pagination.
npm MIT ★ 2 -
StatusPro API client ecosystem — Python + TypeScript + MCP server with transport-layer resilience, rate-limit awareness, and auto-pagination.
pypi MIT -
MCP server for the Google Custom Search JSON API: web and image search via Programmable Search Engine with pagination, language and country filters and SafeSearch
npm MIT -
Connect AI assistants to JustSERPAPI via MCP: discover endpoints, inspect schemas, call APIs, paginate results, and check usage or credits.
MIT ★ 1 -
Instagram & Facebook MCP server for Meta Marketing API v26 with secure token redaction, cursor pagination, and OSS tooling for campaigns, ad sets, ads, creatives, insights, and reports.
AGPL-3.0 ★ 79 -
The definitive Spotify MCP server — full non-deprecated Web API coverage, paginated everything, podcast-first, tested end to end
npm MIT ★ 1 -
Complete MCP server for Cisco Meraki Dashboard API. 79 tools across 9 categories: organizations, networks, devices, switch, wireless, appliance, camera, monitoring & alerts. Production-ready with rate limiting, auto-retry, caching & pagination.
★ 1 -
FastMCP server for the Cisco ThousandEyes API, generated dynamically from the official OpenAPI spec. Bearer-token auth, adaptive tool splitter, cursor + offset pagination.
pypi Apache-2.0 -
MCP server for Wave accounting: live transactions, every public API entity, payments and reports, with context-safe pagination. Also a pi package.
npm MIT -
Modern TypeScript and Python Katana Manufacturing MRP API clients with automatic retries, rate limiting, and smart pagination. Now with an alpha MCP implementation!
go MIT ★ 3 -
student-export-mcpactive
MCP server that logs into a web app with a headless browser and exports its student list API to Excel (auto-detects login, auth and pagination)
npm MIT -
MCP server for VirusTotal API — analyze URLs, files, IPs, and domains with comprehensive security reports, relationship analysis, and pagination support.
npm MIT ★ 155 -
formbot-mcpgithub.com/marilynceo/formbot-mcpupdated this year
Online form creation and management for AI agents u2014 build Typeform-style surveys, collect responses with pagination, update forms with logic jumps, track completion analytics, and generate shareable links. Self-contained SQLite storage, zero external API dependencies.
-
espacenet-mcpgithub.com/navisbio/espacenet-mcpupdated this year
MCP server for searching and retrieving patents from Espacenet via the EPO Open Patent Services API. Supports CQL search, bibliographic data, paginated full-text reading, keyword search within patents, patent family lookup, legal status, and citations.
npm MIT -
MCP server for searching and retrieving patents via the EPO Open Patent Services API. Supports CQL search, bibliographic data, paginated full-text reading, keyword search within patents, patent family lookup, legal status, and citations.
npm MIT -
yourimageshareno update data
yourimageshare-mcp connects Claude, ChatGPT, and other MCP-compatible agents to YourImageShare's free image and video hosting API. Ask an agent to upload a screenshot and it gets back a shareable link — no manual copy-paste-upload loop. Tools: upload_image (from a local path or inline base64 — images up to 200MB in JPG, PNG, GIF, WEBP, AVIF, BMP, TIFF, or HEIC, or MP4/WEBM/AVI video — with optional auto-expiry from 60 seconds to 30 days), list_uploads (paginated, newest first), and delete_upload. Requires a free YourImageShare API key from yourimageshare.com/my-account (API tab). No account is needed to use the hosting service itself, but the MCP server needs a key to act on your behalf.
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 -
Enhanced MCP server for Trello with advanced pagination support for large boards
npm MIT -
Local MCP tools for document search, reusable document profiles, spreadsheet SQL, JSON snapshot changes, resumable API batches and retry-loop checks. Built by AVRG3.
mcpb MIT -
@amplify-studio/open-mcpgithub.com/amplify-studio/open-mcpupdated this year
Open MCP server for web search and URL reading via Gateway API
npm MIT -
@lm902/mail-imap-mcp-rsgithub.com/lm902/mail-imap-mcp-rsupdated this year
Secure IMAP MCP server over stdio with cursor-based pagination, multi-account support, and TLS-only connections
npm MIT -
@iflow-mcp/instantly-mcpupdated this year
Multi-transport MCP server for Instantly.ai with stdio, SSE, and DXT support. Features bulletproof pagination, one-click installation, and comprehensive email automation tools.
npm MIT -
Secure, minimalist, read-only MCP access to your complete Steam library and wishlist—with full local pagination and zero credential storage.
MIT ★ 1 -
MCP-compatible WooCommerce connector that lets AI agents securely read merchant orders with list, get, search, pagination, validation, retries, and rate-limit handling.
NOASSERTION -
hubspot-mcp-servergithub.com/amin-ale/hubspot-mcp-serverupdated this year
HubSpot MCP server for contacts, deals and pipelines: idempotent writes, a full PII-redacted audit trail, scope-aware errors instead of raw 403s, rate-limit retries, local read cache, cursor pagination. Private-app token or OAuth. Works with Claude Desktop or any MCP client.
MIT