Apify documents an official Model Context Protocol server hosted at https://mcp.apify.com that speaks Streamable HTTP in line with the current MCP specification; Apify warns that SSE transport was deprecated for removal April 1, 2026. Hosted clients authenticate through browser OAuth or by supplying Bearer tokens sourced from Console → Settings → Integrations (`APIFY_TOKEN`), can pin tool bundles via URL query (`?tools=actors,docs,apify/rag-web-browser` style examples reproduce Apify wording), optionally append `telemetry-enabled=false`, and benefit from inferred structured-output schemas surfaced for Actor tooling on hosted endpoints unlike the default stdio server. When MCP clients refuse remote transports, docs recommend `npx -y @apify/actors-mcp-server` with `APIFY_TOKEN` for stdio, Node.js ≥18, and adherence to documented per-user throughput (Apify cites up to thirty requests per second across Actor runs plus storage/documentation calls). Specialized payment modes (open x402 on Base plus Skyfire) appear as optional adjunct pages inside the broader integration handbook.
Use cases
- Discover and inspect Apify Store Actors (`search-actors`, `fetch-actor-details`) before approving spend
- Let coding agents summarize Apify tutorials using `search-apify-docs` / `fetch-apify-docs`
- Operationalize repeatable crawl jobs referencing datasets, KV stores, logs through storage tools lists
- Prototype agentic scraping without writing bespoke REST glue for every storefront template
- Gate production rollouts behind explicit URL tool allow-lists mandated by enterprise security reviewers
Key features
- Cursor
- VS Code
- Claude Desktop
- Claude remote connectors
- Codex
Frequently Asked Questions
- Do I always need manual API tokens?
- No—hosted clients can complete OAuth flows on first launch, but Bearer headers remain supported for scripted clients per Apify MCP documentation.
- What happens if telemetry should be disabled?
- Append `telemetry-enabled=false` to the HTTPS URL when using remote mode; CLI users can pass `--telemetry-enabled=false` or set `TELEMETRY_ENABLED=false` for local stdio.
- How aggressive are rate ceilings?
- Apify states the hosted MCP tier enforces roughly 30 HTTPS operations per second per user; bursts above that return HTTP 429 and require exponential backoff logic.
Related
Related
3 Indexed items
n8n MCP Server Trigger
The MCP Server Trigger is a first-party n8n core node that turns an n8n workflow into a Model Context Protocol server endpoint. Instead of chaining conventional trigger nodes, it connects only to tool nodes so remote MCP clients can list tools and invoke them over long-lived Server-Sent Events or streamable HTTP transports (stdio is explicitly unsupported). Each node exposes separate test and production MCP URLs, optional bearer or header authentication, and documentation explains how to proxy Claude Desktop through `npx mcp-remote` plus queue-mode caveats for multi-replica webhook deployments.
Webflow MCP Server
Connect any LLM to your Webflow sites via the Model Context Protocol. Manage pages, collections, CMS items, e-commerce products, forms, and users through natural language — enabling AI-driven site management and content workflows.
Neon MCP Server
Official Neon MCP integration exposes Neon Postgres projects to MCP-capable assistants via Streamable HTTP (`https://mcp.neon.tech/mcp`), legacy SSE (`https://mcp.neon.tech/sse`), or a locally launched `@neondatabase/mcp-server-neon` package. Documentation lists tools for project and branch lifecycle, SQL execution, migration rehearsal branches, slow-query diagnostics, Neon Auth provisioning, Data API setup, and embedded Neon docs retrieval—each mapped to Neon API operations.