Compatible with every major AI agent and IDE
What is the The Graph (Web3 Indexing) MCP Server?
Connect to The Graph to index and retrieve real-time blockchain data across multiple ecosystems. This MCP server allows your AI agent to query decentralized data from Ethereum, Polygon, Solana, and more through standardized tools and custom GraphQL subgraphs.
What you can do
- EVM Data Access — Retrieve token transfers, top holders, and DEX swap events (Uniswap, Curve) for any EVM-compatible chain.
- Solana (SVM) Integration — Fetch SPL token transfers, holders, and AMM swaps (Jupiter, Raydium) directly from the Solana network.
- Historical Analysis — Access wallet balance changes in OHLCV format to track portfolio performance over time.
- Custom Subgraph Queries — Execute raw GraphQL queries against any specific subgraph ID for deep, specialized data extraction.
- Market Intelligence — Monitor liquidity pool activities and token distribution metrics without manual block explorer searching.
How it works
- Subscribe to this server
- Enter your The Graph API Token, API URL, and optional API Key
- Start querying on-chain data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Web3 Developers — debug smart contract events and verify on-chain state directly from your IDE
- Data Analysts — aggregate token holder distributions and DEX volume metrics for research
- DeFi Power Users — track wallet movements and liquidity pool swaps through natural language
Built-in capabilities (8)
Get EVM historical balances
Get EVM token holders
) for EVM chains. Get EVM DEX swaps
Get EVM token transfers
Get SVM (Solana) token holders
) for Solana. Get SVM (Solana) DEX swaps
Get SVM (Solana) token transfers
Requires THE_GRAPH_API_KEY. Query a subgraph using GraphQL
Why Cursor?
Cursor's Agent mode turns The Graph (Web3 Indexing) into an in-editor superpower. Ask Cursor to generate code using live data from The Graph (Web3 Indexing) and it fetches, processes, and writes. all in a single agentic loop. 8 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
The Graph (Web3 Indexing) in Cursor
The Graph (Web3 Indexing) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect The Graph (Web3 Indexing) to Cursor 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 The Graph (Web3 Indexing) in Cursor
The The Graph (Web3 Indexing) 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 8 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor 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
The Graph (Web3 Indexing) for Cursor
Every tool call from Cursor to the The Graph (Web3 Indexing) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I query any specific subgraph if I have its ID?
Yes! Use the query_subgraph tool by providing the subgraph_id and your GraphQL query string. This allows for deep, custom data extraction beyond the standard tools.
Does this server support Solana token data?
Absolutely. You can use get_svm_transfers, get_svm_holders, and get_svm_swaps to interact with SPL tokens and decentralized exchanges on the Solana network.
Can I track historical balance changes for a specific wallet?
Yes, the get_evm_historical_balances tool provides historical balance data in OHLCV format for EVM chains, making it easy to analyze portfolio trends.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
SMPTE Timecode Calculator
3 toolsStop LLMs from melting down over base-60 math. Add, subtract, and convert video SMPTE timecodes natively.

JSON Schema Validator
1 toolsPrevent malformed JSON hallucination. Validates large LLM-generated JSON objects strictly against JSON Schema standards before sending to the client.

Webflow
8 toolsDesign and build professional websites visually with a no-code platform that generates clean, production-ready HTML and CSS.

Wikidata
8 toolsAccess the world's largest open knowledge graph—query entities via SPARQL, perform vector searches, and manage structured data directly from your AI agent.
