Aerostack
Aerostack
electrical_services

Anthropic MCP Server — Hosted for Any AI Agent

MCP Server language Hosted language Public

Call Claude models directly — run AI conversations, tool-use chains, batch jobs, and model comparisons from any agent.

aerostack @aerostack verified
• v0.1.0 • MIT • Updated Jun 28, 2026
add_circleAdd to Workspace
robot_2

Use with AI AssistantsMCP

Connect Claude, Cursor, or any MCP-compatible client — then call tools directly

① Add This MCP Server

Paste into your AI client config — then all its tools are available instantly.

.claude/mcp.json
{
  "mcpServers": {
    "anthropic": {
      "url": "https://mcp.aerostack.dev/s/aerostack/mcp-anthropic",
      "headers": {
        "Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
      }
    }
  }
}

Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.

② Call a Tool

Ask your AI assistant to call a specific tool, or send raw JSON-RPC:

+7 more

Natural Language Prompt

“Use the _ping tool to verify anthropic credentials by calling a lightweight read endpoint. used internally by aerostack to validate credentials”

Using a Workspace?

Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.

add_circleAdd to Workspace

description Overview

mcp-anthropic — Anthropic MCP Server

Give your AI agents direct access to Claude — send messages, run batches, manage models, and administer your Anthropic organization.

Anthropic's API powers some of the world's most capable AI models. This MCP server exposes the full Anthropic API surface to your agents: from sending individual messages and tool-calling conversations to processing thousands of requests in efficient batches and administering your organization's workspaces and API keys.

Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-anthropic

What You Can Do

  • Send messages to Claude models with custom system prompts, temperature control, and stop sequences
  • Build multi-turn tool-use conversations where Claude can invoke external functions
  • Process large workloads efficiently with the Message Batches API (async, lower cost)
  • Estimate token costs before sending requests to stay within budget
  • Administer your Anthropic organization — list workspaces, API keys, and monitor usage

Available Tools

Tool Description
create_message Send a message to a Claude model and get a response with full parameter control
create_message_with_tools Send a message with tool definitions so Claude can respond with tool use blocks
count_tokens Count input tokens for a request without sending it — use to estimate cost
create_message_batch Submit a batch of message requests for async processing — returns a batch ID
list_models List all available Claude models with IDs and creation dates
get_model Get details for a specific Claude model by ID
list_batches List message batch jobs with status, request counts, and timestamps
get_batch Get status and result URL for a specific message batch
cancel_batch Cancel an in-progress message batch
list_workspaces List all workspaces in your organization (Admin API key required)
get_usage Get API usage and billing data for your organization (Admin API key required)
list_api_keys List all API keys in your organization (Admin API key required)

Configuration

Variable Required Description How to Get
ANTHROPIC_API_KEY Yes Anthropic API key (standard or Admin) console.anthropic.com → API Keys

Quick Start

Add to Aerostack Workspace
  1. Go to aerostack.dev → Your Project → MCPs
  2. Search for "Anthropic" and click Add to Workspace
  3. Add your ANTHROPIC_API_KEY under Project → Secrets

Once added, every AI agent in your workspace can call Claude models automatically — no per-user setup needed.

Example Prompts
"Ask Claude to summarize this document using the claude-opus-4-5 model"
"Count how many tokens this conversation will use before sending it"
"Submit a batch of 500 classification requests and check the status"
Direct API Call
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-anthropic \
  -H 'Content-Type: application/json' \
  -H 'X-Mcp-Secret-ANTHROPIC-API-KEY: your-key' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"create_message","arguments":{"messages":[{"role":"user","content":"Hello!"}]}}}'

License

MIT

terminal Tools (13)

Available tools on this MCP server. Each tool can be called directly from any AI agent.

terminal
_ping #1

Verify Anthropic credentials by calling a lightweight read endpoint. Used internally by Aerostack to validate credentials.

terminal
create_message #2

Send a message to a Claude model and get a response. Core tool for AI conversations — supports system prompts, temperature control, and stop sequences. Stream is always false (CF Workers stateless).

terminal
create_message_with_tools #3

Send a message to Claude with tool/function definitions. Claude can respond with tool use blocks. Supports tool_choice to control which tools are called.

terminal
count_tokens #4

Count the number of input tokens for a given request without sending it. Use to estimate costs and check if request fits within context window before sending.

terminal
create_message_batch #5

Create a batch of message requests to be processed asynchronously. More efficient for large volumes. Returns a batch ID — use get_batch to poll status and retrieve results.

terminal
list_models #6

List all available Claude models. Returns model IDs, display names, and creation dates. Use to discover available models before calling create_message.

terminal
get_model #7

Get details about a specific Claude model by ID — display name, type, creation date.

terminal
list_batches #8

List message batch jobs. Returns batch IDs, status (in_progress, ended, canceling, canceled), request counts, and timestamps.

terminal
get_batch #9

Get the status and details of a specific message batch. Returns processing status, request counts (processing/succeeded/errored/canceled/expired), and result URL when complete.

terminal
cancel_batch #10

Cancel an in-progress message batch. Already-completed requests in the batch are not affected. Returns updated batch status.

terminal
list_workspaces #11

List all workspaces in the organization (Admin API). Requires an Admin API key with organization:read permission. Returns workspace IDs, names, and billing info.

terminal
get_usage #12

Get API usage and billing data (Admin API). Requires an Admin API key with billing:read permission. Returns token usage and cost breakdowns.

terminal
list_api_keys #13

List all API keys in the organization (Admin API). Requires an Admin API key with organization:read permission. Returns key IDs, names, status, and creation dates.

Details

upgrade Version 0.1.0
gavel License MIT
wifi Transport streamable-http
lock Access Public
category Category AI
terminal Tools 13

language Live Endpoint

https://mcp.aerostack.dev/s/aerostack/mcp-anthropic

Sub-50ms globally · Zero cold start

Publisher

aerostack
@aerostack verified

Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.

Tags

ai llm claude anthropic completions
Browse more servers

More in AI

Browse AI MCPs →
hub

Canva Design Platform

by @aerostack

Design creation, AI generation, editing, export, assets, brand kits, folders via Canva's official MCP

ai
star 0
hub

Intercom Messaging

by @aerostack

Conversations, contacts, tickets, articles via Intercom's official MCP

ai
star 0
hub

Vercel Deployments

by @aerostack

Deployments, projects, domains, env vars, logs via Vercel's official MCP

ai
star 0
hub

Gmail

by @aerostack

Read, send, and search Gmail messages — manage labels, drafts, and attachments with full inbox control.

ai
star 0
hub

Mailchimp

by @aerostack

Manage audiences, campaigns, and subscriber tags in Mailchimp — automate your email marketing with AI.

ai
star 0
hub

Openai

by @aerostack

Run chat completions, generate embeddings, create images, and moderate content via the OpenAI API.

ai
star 0

Frequently asked questions

What is the Anthropic MCP server and what can it do? +

The Anthropic MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `create_message`, `create_message_with_tools`, `count_tokens`, `create_message_batch`. You get one hosted URL — no self-hosting — that works from Claude, Cursor, ChatGPT, Gemini, VS Code, or any MCP-compatible client, and you can share it with your team or combine it with other MCP servers in a workspace.

Is the Anthropic MCP server hosted, or do I have to run it myself? +

It's hosted on Aerostack's edge infrastructure — you don't deploy or maintain anything. Add it to a workspace and you get one authenticated URL, with secrets encrypted, that any AI agent or editor can connect to. Use it solo or share the same URL across your whole team.

Which AI agents and editors can use the Anthropic MCP server? +

Any MCP client: Claude and Claude Code, Cursor, ChatGPT, Gemini, Windsurf, Cline, VS Code, and custom agents. Because it's one hosted URL, the same Anthropic MCP server works everywhere — and you can compose it with other MCP servers, skills, and functions behind a single workspace URL.

How do I install the Anthropic MCP server in Claude Desktop? +

Add the following to your Claude Desktop config (`claude_desktop_config.json`): ```json { "mcpServers": { "@aerostack/mcp-anthropic": { "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-anthropic"] } } } ``` Then restart Claude Desktop and the tools will appear automatically.

How do I use the Anthropic MCP server in Cursor? +

In Cursor, open **Settings → MCP** and add: ```json { "name": "@aerostack/mcp-anthropic", "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-anthropic"] } ``` Save and reload Cursor. The MCP tools will be available in Agent mode.

Does Anthropic MCP require authentication? +

Yes. Anthropic requires authentication. Check the MCP's documentation for the required credentials.