Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
StackOne
Connectors
Pricing
Login
Book Demo Start Free
Connect

Connect to everything your agents need, without writing the infrastructure to get there.

Secure

Enterprise-grade controls to ensure your agent always meets security & compliance standards.

Optimize

Maximise agent efficiency – faster responses, increased accuracy, fewer tokens used.

Explore More Use-Cases
Next up: Connecting AI Agents Securely in Healthcare
StackOne
Connectors
Connect

Connect to everything your agents need, without writing the infrastructure to get there.

Secure

Enterprise-grade controls to ensure your agent always meets security & compliance standards.

Optimize

Maximise agent efficiency – faster responses, increased accuracy, fewer tokens used.

Use-Cases
Pricing
Book Demo Start Free
Live 37 Actions

LunarCrush MCP Server
for AI Agents

Connect your AI agent to StackOne's LunarCrush MCP server and give it 37 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
LunarCrush logo
LunarCrush MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

37 Agent Actions

Create, read, update, and delete across LunarCrush — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your LunarCrush MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every LunarCrush tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every LunarCrush call.

Tools Discovery →

What is the LunarCrush MCP Server?

A LunarCrush MCP server lets AI agents read and write LunarCrush data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's LunarCrush MCP server ships with 37 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All LunarCrush MCP Tools

Every action from LunarCrush's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Coins

  • List Coins

    Get a general snapshot of LunarCrush metrics on the entire list of tracked coins

  • Get Coin

    Get market data on a coin or token

Creators

  • List Creators

    Get a list of trending social creators over all of social based on interactions

  • Get Creator

    Get detail information on a specific creator

NFTs

  • List NFTs

    Get a general snapshot of LunarCrush metrics on the entire list of tracked NFTs

  • Get NFT

    Get market data on an nft collection

Posts

  • Get Post

    Get details of a post

  • Search Posts

    Get recently popular social posts matching a single search term or phrase

Stocks

  • List Stocks

    Get a general snapshot of LunarCrush metrics on the entire list of tracked stocks

  • Get Stock

    Get market data on a stock

Topics

  • List Topics

    Get a list of trending social topics

  • Get Topic

    Get summary information for a social topic

Other (25)

  • Create Search

    Create a custom search aggregation of topics and search terms

  • List Category Topics

    Get the top topics for a social category

  • List Category Posts

    Get the top posts for a category

  • List Category News

    Get the top news posts for a category

  • List Category Creators

    Get the top creators for a social category

  • List Categories

    Get a list of trending social categories

  • Get Category

    Get summary information for a social category

  • Get Category Time Series

    Get historical time series data for a social category

  • Get Coin Time Series

    Get market time series data on a coin or token

  • Get Coin Meta

    Get meta information for a cryptocurrency project

  • List Creator Posts

    Get the top posts for a specific creator

  • Get Creator Time Series

    Get time series data on a creator

  • Get NFT Time Series

    Get market time series data on a nft

  • Get Post Time Series

    Get interactions over time for a post

  • List Searches

    List all custom search aggregations

  • Get Search

    Retrieve the summary output of a custom search aggregation (deprecated by LunarCrush)

  • Get Stock Time Series

    Get market time series data on a stock

  • List System Changes

    List revisions to historical time series data

  • List Topic Posts

    Get the top posts for a social topic

  • List Topic News

    Get the top news posts for a social topic

  • List Topic Creators

    Get the top creators for a social topic

  • Get Topic AI Summary

    Generate an AI summary of the hottest news and social posts for a specific topic

  • Get Topic Time Series

    Get historical time series data for a social topic

  • Update Search

    Update a custom search aggregation name or priority

  • Delete Search

    Delete a custom search aggregation

Set Up Your LunarCrush MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to LunarCrush in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What Hundreds of Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.

14 min read

LunarCrush MCP Server FAQ

Does StackOne have a LunarCrush MCP server?
Yes. StackOne offers a hosted LunarCrush MCP server with 37 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
LunarCrush MCP server vs direct API integration — what's the difference?
A LunarCrush MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling LunarCrush. A LunarCrush MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling LunarCrush at runtime. StackOne provides both.
How does LunarCrush authentication work for AI agents?
LunarCrush authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own LunarCrush account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are LunarCrush MCP tools vulnerable to prompt injection?
Yes — LunarCrush MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a LunarCrush agent and how do I avoid it?
Context bloat happens when LunarCrush tool schemas and API responses eat your LunarCrush agent's memory, preventing it from reasoning effectively. A single LunarCrush query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my LunarCrush agent can access?
Yes — you can limit which actions your LunarCrush agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my LunarCrush MCP server?
Yes — you can create custom agent actions for your LunarCrush MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research LunarCrush's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a LunarCrush MCP server?
Skip a LunarCrush MCP server if your integration is purely software-to-software — direct LunarCrush API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call LunarCrush actions at runtime.
What AI frameworks and AI clients does the StackOne LunarCrush MCP server support?
The StackOne LunarCrush MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo