# For AI agents (Carbon 2.0) > Connect Claude Code, Cursor or any coding agent to these docs through MCP, Markdown pages and llms.txt, and give it the rules it needs to write correct Carbon 2.0 code. Coding agents write a lot of Carbon code, and most of them learned Carbon from versions before 2.0. This page shows how to give your agent the current docs and the rules that keep it from writing outdated code. ## Connect the docs MCP server The docs run an MCP server at `https://carbon.sevenlabs.org/mcp`. It uses Streamable HTTP and needs no login. It has four tools: | Tool | What it does | | -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `search_docs` | Searches every page and returns the best sections with their URLs. | | `get_page` | Returns one page as Markdown, from a path such as `/concepts/filters`. | | `list_pages` | Lists every page by section with a one-line description. | | `find_decoder` | Finds the decoder crate for a Solana program from its program ID, crate or name, and returns the install command, decoder struct, instruction, account and event names, and the reference page. | **Claude Code** ```sh claude mcp add --transport http carbon-docs https://carbon.sevenlabs.org/mcp ``` **Cursor** `.cursor/mcp.json`: ```json { "mcpServers": { "carbon-docs": { "url": "https://carbon.sevenlabs.org/mcp" } } } ``` **VS Code** `.vscode/mcp.json`: ```json { "servers": { "carbon-docs": { "type": "http", "url": "https://carbon.sevenlabs.org/mcp" } } } ``` Any other client that supports Streamable HTTP works with the same URL. ## Read pages as Markdown Every page has a Markdown version with no navigation or scripts: - Add `.md` to any page URL: `https://carbon.sevenlabs.org/concepts/filters.md`. The home page is `https://carbon.sevenlabs.org/index.md`. - Or request the normal URL with `Accept: text/markdown`. - [`/llms.txt`](https://carbon.sevenlabs.org/llms.txt) lists every page with a one-line description, plus the mistakes agents make most often. - [`/llms-full.txt`](https://carbon.sevenlabs.org/llms-full.txt) has every guide, concept and reference page in one file. The per-program decoder references are left out because they're large; `llms.txt` links each one. Each Markdown page starts with its title and the Carbon version, so an agent can tell which release it's reading. A path that doesn't exist returns HTTP 404 with a list of the closest pages instead of an empty error. On the web, the **Copy page** button at the top of every page copies its Markdown, or opens the page in Claude or ChatGPT. ## Add an AGENTS.md to your project Agents follow the instruction file in your repository more reliably than anything they fetch. Paste this into `AGENTS.md` (or `CLAUDE.md`) at the root of a project that uses Carbon: `AGENTS.md`: ```md ## Carbon This project indexes Solana data with Carbon 2.0 (Rust). Docs: https://carbon.sevenlabs.org (append `.md` to any page URL for Markdown; index at https://carbon.sevenlabs.org/llms.txt). - Do not rely on training data for Carbon APIs: they changed in 1.0 and 2.0. Check the docs before writing Carbon code. - All `carbon-*` crates must be version 2.0.0. Never mix Carbon 1.x and 2.x crates. Rust 1.96.1+. - Processors implement `Processor` with a native `async fn process(&mut self, input: &T) -> CarbonResult<()>`. No `#[async_trait]` on processors; `Datasource` impls do use `#[async_trait]`. - Instruction enums use struct variants: match `MyInstruction::Swap { data, accounts, .. }`. - RPC transaction configs need `UiTransactionEncoding::Base64` and `max_supported_transaction_version: Some(1)`. - The public endpoint api.mainnet-beta.solana.com does not support `blockSubscribe`. - Generate decoders with `npx @sevenlabs-hq/carbon-cli@2.0.0 parse --idl --out-dir ` (Codama IDLs: add `--standard codama --program-id
`). `parse` deletes `--out-dir` first, so use a dedicated directory. - Check work with `cargo check` and `cargo clippy`. ``` ## Rules for agents writing Carbon code These are the facts agents most often get wrong. The same list is at the top of `llms.txt`. 1. These docs are for Carbon 2.0.0. Use `carbon-core = "2.0.0"` and matching `carbon-*` crates at 2.0.0. Never mix Carbon 1.x and 2.x crates in one dependency graph. 2. Carbon 2.0 needs Rust 1.96.1 or newer and the Agave 4.2-compatible Solana crates. If you add Solana crates directly, pick versions that resolve to a single copy of each. Mixing Carbon 1 and 2 crates fails with ``the trait `InstructionDecoder` is not implemented`` and a note about multiple versions of `carbon_core`. 3. `Processor::process` is a native `async fn`. Don't add `#[async_trait]` to processors. The `Datasource` trait does use `#[async_trait]`. 4. Instruction enums use struct variants: `MyProgramInstruction::Swap { program_id, data, accounts }`. 5. `https://api.mainnet-beta.solana.com` rejects `blockSubscribe`. On the public endpoint, use the [transaction crawler](https://carbon.sevenlabs.org/datasources/rpc-transaction-crawler.md), [`getProgramAccounts`](https://carbon.sevenlabs.org/datasources/rpc-gpa.md) or [`programSubscribe`](https://carbon.sevenlabs.org/datasources/rpc-program-subscribe.md) datasources. 6. RPC block and transaction configs must request `UiTransactionEncoding::Base64` and `max_supported_transaction_version: Some(1)`. Carbon can't rebuild transactions from `Json` or `JsonParsed`. 7. Zero-lamport account updates arrive as `Update::AccountDeletion` and go to `.account_deletions(...)` processors, not account processors. 8. Decoder crates are named `carbon--decoder` and export `PROGRAM_ID` and a `Decoder` struct. Check the [decoder catalog](https://carbon.sevenlabs.org/decoders.md) before generating one. ## Instructions for agents: create a Carbon indexer When a user asks for a new indexer, follow these steps in order. 1. Run `rustc --version`. If it's older than 1.96.1, tell the user to run `rustup update stable`. 2. Find the program's decoder in the [catalog](https://carbon.sevenlabs.org/decoders.md). If there isn't one, generate it from the IDL with the [CLI](https://carbon.sevenlabs.org/guides/generate-a-decoder.md) and add it as a path dependency. 3. Choose the datasource from the [chooser](https://carbon.sevenlabs.org/datasources.md): Yellowstone gRPC or Helius LaserStream for real-time production; the RPC transaction crawler for history or for a no-account start; `getProgramAccounts` for current account state. 4. Add every crate at version `2.0.0` with `cargo add`, plus `tokio` with the `full` feature. 5. Write `main.rs` following the [quickstart](https://carbon.sevenlabs.org/quickstart.md): build the datasource, then `Pipeline::builder().datasource(…).metrics(…).instruction(Decoder, Processor).build()?.run().await`. 6. Implement one `Processor` per decoder output type you need. Match only the variants you handle and ignore the rest with `_ => {}`. 7. Run `cargo check`, fix errors using the [errors reference](https://carbon.sevenlabs.org/reference/errors.md), then `cargo run` and show the user the first output. 8. Before calling it done, read [Run in production](https://carbon.sevenlabs.org/guides/production.md) and tell the user which items apply. --- Carbon 2.0.0 documentation · Web: https://carbon.sevenlabs.org/agents · Last updated 2026-11-09 · Index of all pages: https://carbon.sevenlabs.org/llms.txt