MCP For Claude Marketplace
Anthropic

Anthropic MCP Connector for Claude

A+

Access Claude models via Anthropic API — send messages, count tokens, manage batches and discover models from any AI agent.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Anthropic account to any AI agent and leverage Claude's capabilities through natural conversation.

What you can do

  • Model Discovery — List all available Claude models with their IDs and capabilities
  • Message API — Send conversations to Claude models and receive responses with configurable max tokens, system prompts and temperature
  • Token Counting — Count tokens in messages before sending to estimate costs and context window usage
  • Batch Processing — Submit batches of independent message requests for asynchronous, cost-effective processing

How it works

  1. Subscribe to this server
  2. Enter your Anthropic API Key
  3. Start using Claude from Claude, Cursor, or any MCP-compatible client

No more switching between API tools to interact with Claude. Your AI acts as an LLM orchestration layer.

Who is this for?

  • Developers — quickly send messages to Claude, count tokens and manage batch requests without writing HTTP code
  • ML Engineers — discover available models, compare capabilities and batch-process many prompts efficiently
  • Product Teams — review model outputs, track token usage and manage batch processing jobs via conversation
llmmodel-discoverytoken-countingnatural-language-processingprompt-engineeringapi-management

6 tools expose this connector's capabilities to your AI agent.

cancel_batch_message

Requests that have already been completed cannot be cancelled. Provide the batch ID. This is useful if you submitted a large batch by mistake and want to stop further processing to save costs. Cancel an in-progress batch message request

count_tokens

Requires the model ID and messages array. Returns the total input token count. Useful for estimating API costs and ensuring messages fit within context limits. Count tokens in a message before sending to Claude

create_batch_message

Each request in the batch has its own model, messages, max_tokens, etc. This is more cost-effective than individual requests when you have many independent prompts to process. Returns a batch ID for tracking. Use get_batch_message to check progress. Create a batch of message requests to Claude

get_batch_message

Returns the batch status (in_progress, succeeded, expired, canceling, canceled, failed), request counts (total, succeeded, errored) and individual results. Use the batch ID returned from create_batch_message. Get the status of a batch message request

list_models

Each model returns its ID (e.g. "claude-sonnet-4-20250514"), display name, creation date and capabilities. Use this to discover which models are available and their IDs for use with the send_message tool. List all available Anthropic Claude models

send_message

Requires the model ID (e.g. "claude-sonnet-4-20250514") and messages array in JSON format. Each message must have a "role" ("user" or "assistant") and "content" (text or array of content blocks). Optionally set max_tokens (default 1024), system prompt and temperature (0-1). Returns the assistant's response text. Send a message to Claude (Messages API)

See how to talk to your AI agent using Anthropic.

Send a message to Claude asking 'What is the capital of Brazil?'

Claude responded: 'The capital of Brazil is Brasília. It was purpose-built to replace Rio de Janeiro as the capital in 1960, and is located in the country's central-west region.' The response used 45 tokens.

List all available Claude models.

Available models: claude-sonnet-4-20250514 (latest Sonnet, 200K context), claude-opus-4-20250514 (most capable, 200K context), claude-haiku-20241022 (fastest, cost-effective, 200K context). Each model has different pricing and capabilities.

Count tokens for a message asking Claude to summarize a 500-word article.

The message would use approximately 547 input tokens (45 for the prompt + 502 for the article text). With a typical response of 150 tokens, the total would be ~697 tokens for this conversation turn.

Log in to the [**Anthropic Console**](https://console.anthropic.com), go to **Account Settings > API Keys** and click **Create Key**. Copy the key immediately — it starts with `sk-ant-` and won't be shown again. You can also create workspace-scoped keys to control spending by use case.

Related Connectors

CU

Customer.io MCP

18 tools Official

Automate customer engagement via Customer.io — track events, manage profiles, and trigger multi-channel campaigns directly from any AI agent.

A+ View details →
AU

Authing MCP

10 tools Official

Cloud-native identity and access management platform — manage users, roles, and security logs via AI.

A+ View details →
MO

Mod.io MCP

22 tools Official

Manage game mods, browse titles, and handle subscriptions via mod.io — discover, rate, and organize game content directly from any AI agent.

A+ View details →
42

42Crunch MCP

10 tools Official

Automate API security testing via 42Crunch — manage collections, trigger audits, run conformance scans, and retrieve security reports directly from any AI agent.

F View details →