
Chainstack
Deploy and manage blockchain nodes across 70+ protocols, search docs, request testnet funds.
What it can do
What data it sees
Do you need an account
An API key from the service settings is required
Deploy and manage blockchain nodes across 70+ protocols, search docs, request testnet funds.
How to connect
How to connect Chainstack to Claude
The server address to paste into Claude settings:
https://mcp.chainstack.com/mcp
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Chainstack to ChatGPT
The server address to paste into ChatGPT settings:
https://mcp.chainstack.com/mcp
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Chainstack to Cursor
The server address to paste into Cursor settings:
https://mcp.chainstack.com/mcp
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (18)
Raw names from tools/list. Only developers need these.
| get_organization | Get organization name and ID. |
| get_deployment_options | List blockchain/cloud/network combinations for node deployment. Call before create_node to get valid blockchain and cloud IDs. |
| list_projects | List all projects. Projects are containers for nodes. |
| create_project | Create a new project. Args: name: Project name. description: Optional description. |
| list_nodes | List nodes with status and connection endpoints. Args: project_id: Optional project ID to filter by (e.g., PR-123-456-789). If omitted, returns all nodes in the organization. |
| get_node | Get a node's full details including endpoints and cloud info. Args: node_id: Node ID (e.g., ND-123-456-789). |
| create_node | Deploy a new blockchain node. Call get_deployment_options first for valid IDs. Trader nodes are region-bound (e.g., London, Ashburn, Singapore). Always confirm the region with the user before deploying — region cannot be changed after deployment. Args: name: Node name. project: Project ID from list_projects (e.g., PR-123-456-789). blockchain: Blockchain ID from get_deployment_options (e.g., BC-000-000-008). cloud: Cloud ID from get_deployment_options (e.g., CC-0016 for Global, CC-0020 for London). |
| get_project | Get project details. Args: project_id: Project ID (e.g., PR-123-456-789). |
| update_project | Update a project's name or description. Args: project_id: Project ID (e.g., PR-123-456-789). name: New name. description: New description. |
| delete_project | Delete a project (irreversible). Args: project_id: Project ID (e.g., PR-123-456-789). |
| update_node | Rename a node. Args: node_id: Node ID (e.g., ND-123-456-789). name: New name. |
| delete_node | Delete a node (irreversible). Args: node_id: Node ID (e.g., ND-123-456-789). |
| search_docs | Search Chainstack docs — blockchain RPC methods, node infrastructure, Web3 APIs, deployment guides, and code examples. Args: query: Search query (e.g., "deploy ethereum node", "eth_call"). |
| get_doc_page | Get the full content of a Chainstack documentation page. Use after search_docs to fetch the complete page when a snippet isn't enough. Args: page: Page path from search results — pass the `page` field from a search_docs result (e.g., "docs/ethereum-trader-nodes"). The leading slash, the `.mdx` extension, and the docs.chainstack.com URL prefix are all optional and stripped if present. |
| get_platform_status | Check platform status, active incidents, and maintenances. Args: network: Optional filter (e.g., "ethereum"). Without it, returns overall status and incidents only. |
| contact_chainstack | Submit a message to Chainstack's sales and support team. Use when the user wants to ask about pricing, get a custom quote, request a plan upgrade, request node customizations (Enterprise), report a problem, or reach Chainstack for any reason. Posts to the same contact form as chainstack.com/contact/. ## Before calling this tool CRITICAL — follow these steps EVERY time: 1. Draft the message based on your conversation context. 2. Show the user the EXACT message, email, and name you will send. 3. If the user has a Chainstack API key configured, tell them: "I'll also include your Chainstack account info (org name and ID) so the team can pull up your account immediately — this means significantly faster handling and a more tailored response." 4. Ask: "Shall I send this to Chainstack? Please confirm there's no sensitive information you'd like removed." 5. Only call this tool after the user explicitly confirms. NEVER include in the message: - API keys, tokens, passwords, private keys, wallet seeds, mnemonics - RPC endpoint URLs (Chainstack or any other provider) - Wallet addresses, transaction hashes, or on-chain account details the user hasn't approved sharing - Any information the user hasn't explicitly approved sharing If the user shared sensitive data during the conversation, do NOT include it unless they specifically approve it in the review step. ## Writing an effective message A great message gets the user a faster, more tailored response. Include what you already know from the conversation: - What they're building and at what scale - Current plan and usage (e.g., "Pro plan, ~80M RU/month on Base") - What they need (upgrade, custom pricing, migration help, etc.) - What they've tried or what's not working - Specific numbers when available Bad: "I have a question about pricing." Good: "Pro plan user running 200M RU/month across Base and Ethereum, evaluating Business plan for archive access and higher RPS. Looking for annual pricin |
| request_testnet_funds | Top up a testnet address from Chainstack's faucet. The faucet does not send a fixed amount — it tops the address up to the per-network maximum (e.g. 0.5 ETH for sepolia). If the address already sits above the cap, the call fails with an insufficient-balance error. Describe the behavior to the user as "top up" not "give", and surface the returned `amountSent` so they see the actual delta. Supported networks and their native assets: - sepolia, hoodi — Ethereum testnets (ETH) - base — Base Sepolia (ETH) - amoy — Polygon Amoy (POL) - bnb-testnet — BNB Smart Chain testnet (BNB) - zksync-testnet — zkSync Sepolia (ETH) - robinhood — Robinhood Chain testnet (ETH) - hyperevm — HyperEVM testnet (HYPE) - plasma — Plasma testnet (XPL) - monad — Monad testnet (MON) - ton — TON testnet (TON) - solana — Solana devnet (SOL) Per-address cooldown applies after each successful drip. On cooldown the faucet returns a `nextFaucetAvailable` timestamp (ISO 8601) that this tool surfaces in the error message. Requires a Chainstack API key. The key is also the rate-limiting identity — the faucet tracks usage per organization. Get a key at https://console.chainstack.com/user/settings/api-keys and add it as `Authorization: Bearer <key>` in the MCP client config. Never ask the user to paste their API key in chat. Args: network: Canonical testnet id (the schema `enum` advertises the set). Case-insensitive; common aliases are normalized to the canonical id. address: Destination address. EVM hex address for EVM networks, a TON address for `ton`, or a base58 Solana public key for `solana`. Validated server-side — format errors surface as 400. Returns: On success: `{network, amountSent, transaction}`. `amountSent` is a string in the network's native unit (not wei/lamports). |
| get_chainstack_pricing | Fetch Chainstack's public pricing and return a normalized snapshot. Use this to answer pricing questions before quoting the user: plan fit, overage math, per-chain dedicated-node costs, and add-on pricing (Unlimited Node flat-fee tiers, Yellowstone gRPC streams, Warp transactions, dedicated-node base rates). This tool returns the menu, not the bill — the calling agent does the arithmetic. All prices are list prices in USD; disclaimers are surfaced in the `disclaimers` field. Design: we pass pricing.md through as raw markdown. Marketing owns that file and its structure changes freely; parsing it server-side would couple us to heading text and table column names we don't control. The LLM reads markdown natively, so handing the raw text to the agent keeps us correct regardless of how the page is restructured. pricing_current.json is parsed into `dedicated_catalog` because it has a stable engineering-owned schema, and the catalog benefits from filtering (to user-orderable SKUs only), unit conversion (cents → USD, milli-cores → cores), and region humanization (via `region_legend`). Per-method RU billing rules are NOT in these sources. Plan-level rates (Full Node = 1 RU, Archive Node = 2 RU) are in the markdown, but some EVM archive-state methods (eth_getBalance, eth_call, eth_getProof, eth_getStorageAt, eth_getCode, eth_getTransactionCount, eth_callMany, eth_createAccessList) and all debug_* / trace_* methods are billed at 2 RU on a full node when called against old blocks. For method-level detail, call `search_docs` with "request units" or `get_doc_page("docs/request-units")`. No API key required — sources are fully public. Each call fetches both sources fresh (no caching), so a stale result isn't possible. Returns: A dict with fields: - `pricing_markdown`: raw markdown from chainstack.com/pricing.md. Read this for plan tiers, feature matrix, add-on pricing, support levels, PAYG details, and provider comparisons. - `dedicated_catalog`: use |