TokenTerminal MCP for AI. Query TVL, revenue, and market trends in crypto.
Works with every AI agent you already use
…and any MCP-compatible client








How this MCP server connects to your AI agent
TokenTerminal (Crypto Financial Data) gives your AI agent access to institutional-grade crypto data. It lets you query specific project metrics—like Total Value Locked (TVL), revenue, and active users—and analyze aggregated market trends across DeFi protocols.
Use it to track fundamental performance for deep analysis.
What AI agents can do with TokenTerminal (Crypto Financial Data) Automation
Get market metrics
Retrieves aggregated, high-level metrics for the total crypto market sector.
Get project metrics
Returns historical time-series data, including revenue, TVL, and active users, for one specific project.
Get project
Fetches basic details and metadata (like category or description) for a single crypto project.
Retrieve a complete list of blockchains and dApps that TokenTerminal monitors.
Fetch detailed information (categories, descriptions) for a specific crypto protocol or dApp.
Generate time-series data points—like revenue, TVL, and active users—for a chosen project over time.
Get current aggregated metrics covering the total crypto market sector's performance and trends.
Ask an AI about this
Waiting for input…
What AI agents can do with TokenTerminal: 4 Tools for Crypto Finance Data
Use these four tools to list projects, get metadata, calculate historical financial metrics, or view aggregated market health data.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using TokenTerminal (Crypto Financial Data) on VinkiusGet Market Metrics
Retrieves aggregated, high-level metrics for the total crypto market sector.
Get Project Metrics
Returns historical time-series data, including revenue, TVL, and active users, for...
Get Project
Fetches basic details and metadata (like category or description) for a single...
List Projects
Outputs a list of all blockchain and dApp projects currently tracked by the server.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with TokenTerminal (Crypto Financial Data), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Token Terminal. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 4 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Sifting through crypto dashboards is slow and messy., Solved with Vinkius AI Gateway
Today, if you want to track how Ethereum's Total Value Locked (TVL) has changed over the last quarter, you open Dashboard A. You copy a date range. Then you jump to Spreadsheet B to find the revenue chart. You might have to click through three tabs and manually reconcile different data points just to build one comparison.
With TokenTerminal, that whole process vanishes. You tell your agent: 'Show me Ethereum's TVL and revenue for Q3.' The server runs `get_project_metrics`, pulls the time-series data, and hands you a clean, structured answer. You get the numbers, period.
TokenTerminal (Crypto Financial Data) MCP Server: Get Project Metrics
You don't have to manually cross-reference multiple sources for a single project’s performance. You use `get_project_metrics` to pull historical data for revenue, TVL, or active users in one go. No more jumping between Bloomberg terminal views and Dune Analytics reports.
It gives you the raw inputs needed for your own models—the precise metrics and date ranges. It's not just a chart; it’s structured data ready to be used by any agent, every time.
What your AI can actually do with this
Listen up. When you hook your agent into TokenTerminal, you're giving it access to institutional-grade crypto data—the kind professional investors actually use when they wanna deep-dive on an asset or a whole sector. You don't need fluff; you need facts.
get_market_metrics lets your agent pull together aggregated metrics for the total crypto market sector. This means you can get a real read on current performance and overall trends across the entire digital finance space, not just one corner of it. It gives you the big picture view, so you know which way the whole ship is sailing.
To figure out what's actually running in this space, use list_projects. This tool spits out a comprehensive list of every single blockchain and dApp that TokenTerminal keeps track of. You can see the sheer breadth of projects monitored, which helps map out where the action is happening right now.
Once you know which project you're looking at, get_project lets your agent pull basic metadata for a specific protocol or dApp. This isn't about money; it’s about identity. You get details like its official category, descriptive text, and general info needed to classify the asset. It’s quick reference material when you need context on something new.
For deep fundamental analysis, get_project_metrics is your go-to tool. This function generates time-series data points for one specific project over an extended period. You're talking about generating historical data for things like revenue figures, Total Value Locked (TVL), and active user counts. Running this through the agent lets you track how a protocol’s fundamental health has changed month by month or quarter by quarter.
You can use these tools together. First, your agent runs list_projects to see all the names in the game. Then, if you're interested in one like Uniswap, it uses get_project to grab its basic details. After that, for the real money talk, it hits get_project_metrics to pull years of revenue and TVL data on that specific protocol.
When you want to step back from a single project and understand market dynamics—say, comparing DeFi protocols against gaming tokens—you kick off with get_market_metrics. It provides the aggregated view needed to compare sectors side-by-side.
This setup means your agent can build out complex research reports. You're not limited to just checking current prices; you've got historical context, sector comparison data, and project identity metadata all wired up for deep work.
019e5d61-4cda-729d-97ff-7fa137009741 Here's how it actually works
The bottom line is: you stop searching for data and start asking questions that get answered with financial metrics.
Subscribe to this server and provide your Token Terminal API Key.
Tell your AI agent what data you need (e.g., 'What was Ethereum's TVL last quarter?').
The agent runs the necessary tool calls, retrieves the structured data, and presents the final analysis.
Who is this actually for?
Crypto analysts who hate manually compiling quarterly reports. Quantitative researchers needing reliable, time-series data without leaving their coding environment. Web3 developers building tools that require real-time on-chain finance metrics.
They use get_project_metrics to run comparative analyses of multiple protocols, calculating growth rates and identifying market leaders based on TVL or revenue.
They start with list_projects to map the entire sector, then use get_project to write a summary report for an investment thesis.
They integrate get_market_metrics into their application logic. This lets them build data-driven web interfaces that reflect the current state of the entire market.
What Changes When You Connect
Analyze deep financials without leaving your agent. You can calculate historical metrics for a protocol—TVL, revenue, active users—using get_project_metrics directly within your chat interface.
Understand the entire sector's health immediately. Use get_market_metrics to see aggregated data and spot which sectors are leading right now, without needing individual reports.
Map out the market landscape quickly. Running list_projects gives you a complete roster of tracked protocols, allowing your agent to narrow down potential research targets instantly.
Get instant project context. If you find an unknown ticker, use get_project to pull its official description and category metadata before wasting time researching it elsewhere.
Build verifiable arguments. By chaining tools—like listing projects and then running metrics on one—you create a clear data trail for your analysis.
See it in action
A new protocol needs due diligence.
You hear about Protocol X. You ask your agent to first use list_projects to confirm it's tracked, then get_project for its description and category. Finally, you run get_project_metrics to see if it has a solid history of revenue or TVL over the last year.
Comparing two competing DeFi platforms.
You want to compare Platform A vs. Platform B's performance over Q3. You instruct your agent to run get_project_metrics twice—once for each platform, specifying the date range and metrics (TVL/Revenue). This lets you build a direct comparison chart.
Checking overall market sentiment.
You need an immediate snapshot of the crypto sector. You use get_market_metrics first to check if L1s or DeFi are trending up. If they are, you then run list_projects to see which specific protocols might be driving that upward movement.
Building a market index tracker.
You're coding an internal tool and need financial data endpoints. You use get_project to validate the metadata format, then feed those project IDs into your workflow to calculate metrics using get_project_metrics in a structured manner.
The honest tradeoffs
Assuming basic data retrieval is enough
Just asking 'What's happening with Ethereum?' — this gives vague articles and no hard numbers. It wastes time.
You need to specify the exact metric and scope: 'Using get_project_metrics for Ethereum, show me historical revenue and TVL over the last 90 days.' Be precise about the inputs.
Overloading the agent with too many tools
Telling your agent to 'use everything' — it gets confused and returns a massive, unusable list of data points.
Break the task down. First, run list_projects to narrow focus. Then, use that resulting project ID in a targeted call like get_project_metrics. Keep calls sequential.
Missing required parameters
Asking 'Get metrics for Uniswap' without specifying the date range or metric type. The agent fails because it doesn't know what to pull.
Always define boundaries: 'Using get_project_metrics, show me TVL and active users for Uniswap between Jan 1, 2023, and Dec 31, 2023.' Specific dates matter.
When It Fits, When It Doesn't
Use this server if your analysis requires hard, time-series financial data about DeFi protocols (TVL, revenue) or aggregated market health. You need to know how much money is moving and where. Don't use it if you just want general news coverage or basic Wikipedia definitions—for that, a standard search engine works fine. If your goal is merely to find the official website for a project, get_project handles that metadata lookup easily. But if you need proof of performance over time, you gotta run through get_project_metrics. Don't try to use it as a general knowledge base; it’s purely for financial data.
Questions you might have
How do I list all crypto projects using the TokenTerminal (Crypto Financial Data) MCP Server? +
You run list_projects. This function returns a comprehensive list of all tracked blockchains and dApps, helping you quickly identify which protocols are available for deeper analysis.
What should I use if I want to compare revenue across different projects? +
You need get_project_metrics. You must call this tool multiple times—once for each project ID and specifying the 'revenue' metric in each call—to generate a consolidated comparison.
Can I find out basic info about a protocol using TokenTerminal (Crypto Financial Data) MCP Server? +
Yes, use get_project. This tool pulls core metadata like the project's official description and its category tags. It’s useful for initial due diligence.
Does get_market_metrics give me specific protocol data? +
No. get_market_metrics provides aggregated market data—the big picture of the entire crypto sector. If you need metrics for one specific protocol, use get_project_metrics.
What happens if I forget my API Key when calling list_projects? +
You must provide a valid Token Terminal API key in your client configuration. The server will return an authentication error and refuse to execute the list_projects call until the key is correctly supplied.
Can I set a specific date range when using the get_project_metrics tool? +
Yes, you can define a start and end date for your data retrieval. This allows you to scope historical time-series metrics (like TVL or revenue) down to precise periods, rather than pulling all available records.
Can I filter aggregated data when calling get_market_metrics by blockchain or sector? +
The get_market_metrics tool accepts parameters that let you narrow the focus. You can request metrics for a specific L1 chain, DeFi category, or other defined market segments.
If I run many calls, like get_project followed by multiple get_project_metrics, is there a usage limit? +
Yes, the API enforces rate limits to manage server load. If you exceed the allowed number of requests in a time window, your client will receive a 429 error, and you'll need to wait before retrying.
Can I get historical revenue for a specific protocol like Uniswap? +
Yes! Use the get_project_metrics tool with 'uniswap' as the project ID and specify 'revenue' in the metrics parameter to see historical financial performance.
How do I see which blockchains are currently tracked by the platform? +
Simply use the list_projects tool. It returns a comprehensive list of all blockchains and decentralized applications currently monitored by Token Terminal.
Is it possible to get a project's social links and category description? +
Yes, the get_project tool provides detailed metadata including the project's description, category, and official social media links.
We've already built the connector for TokenTerminal. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 4 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.