Compatible with every major AI agent and IDE
What is the Glassnode (On-chain Data) MCP Server?
Connect your Glassnode account to any AI agent to analyze crypto markets with precision. Fetch real-time and historical on-chain metrics, exchange flows, and network health data through natural conversation.
What you can do
- Asset Discovery — List all supported assets and blockchains using
list_assetsto identify available data points. - Metric Exploration — Query thousands of metric paths with
list_metricsand get detailed documentation on parameters viaget_metric_details. - Time-Series Analysis — Retrieve historical data for active addresses, exchange balances, and price metrics using
get_metric. - Bulk Data — Fetch metrics for multiple assets simultaneously with
get_bulk_metricto compare market trends. - Point-in-Time Data — Access immutable historical snapshots via
get_pit_metricto eliminate look-ahead bias in backtesting.
How it works
- Subscribe to this server
- Enter your Glassnode API Key
- Start querying on-chain intelligence from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Crypto Traders — monitor exchange inflows and whale movements without leaving the chat
- Data Scientists — pull clean time-series data directly into your analysis environment
- Financial Analysts — generate reports on network growth and valuation metrics instantly
Built-in capabilities (6)
Use a="*" for all assets. Get bulk metric data for multiple assets
Path should be the metric name like "addresses/active_count" or "market/price_usd_close". Get time-series data for a specific metric
Get details, allowed parameters, and description for a specific metric
Get Point-in-Time (PIT) metric data
List all supported assets on Glassnode
Can be filtered by asset, interval, etc. List all available metric paths on Glassnode
Why Pydantic AI?
Pydantic AI validates every Glassnode (On-chain Data) tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Glassnode (On-chain Data) integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Glassnode (On-chain Data) connection logic from agent behavior for testable, maintainable code
Glassnode (On-chain Data) in Pydantic AI
Glassnode (On-chain Data) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Glassnode (On-chain Data) to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Glassnode (On-chain Data) in Pydantic AI
The Glassnode (On-chain Data) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Glassnode (On-chain Data) for Pydantic AI
Every tool call from Pydantic AI to the Glassnode (On-chain Data) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I find the exact path for a specific metric like 'Active Addresses'?
Use the list_metrics tool with the asset symbol (e.g., 'BTC') to see all available paths, or use get_metric_details with a known path to see its full documentation and allowed parameters.
Can I fetch data for multiple coins at once?
Yes, use the get_bulk_metric tool. You can specify a specific asset or use a wildcard * to get data for all supported assets for a specific metric path in a single response.
What is the difference between standard metrics and Point-in-Time (PIT) metrics?
Standard get_metric returns the most accurate current data (which may include revisions). get_pit_metric provides an immutable view of data as it was known at a specific moment, which is essential for backtesting to avoid look-ahead bias.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Glassnode (On-chain Data) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Teamwork Projects
17 toolsManage projects, tasks, milestones, time entries, and messages via Teamwork API.

Omni BI Intelligence
10 toolsInteract with Omni BI dashboards, models, and data exports — run queries and track metrics directly from your AI agent.

Determ
10 toolsEquip your AI agent to monitor media mentions, track keywords, and analyze sentiment via the Determ (formerly Mediatoolkit) API.

Platform.ly
12 toolsGrow your business with marketing automation, CRM, and analytics connected in one platform that shows what drives revenue.
