Avalanche AVAX MCP

io.github.Airpote由 GitHub 账号 Airpote 发布v1.0.1更新于 Oct 24, 2026

Search and retrieve Avalanche blockchain documentation for building on AVAX.

已验证Streamable HTTP可网页运行金融知识与记忆开发者工具

概览

AI 生成的概览

远程 MCP 服务器，让助手搜索 Avalanche 文档与 ACP 提案，并查询链上交易、Subnet、验证者与 P-Chain 质押数据。

可以做什么
搜索、读取 Avalanche 文档页面并列出文档章节与篇数。查询 Avalanche CLI、Platform CLI 与 tmpnet 命令，以及 C/P/X 链、Subnet-EVM 与节点 RPC 方法。按编号、标题或主题查询 ACP 提案，并按状态或类别列出提案。按哈希查询交易，按 ID 查询 Subnet/L1、区块链与验证者。查询 P-Chain 区块高度、区块、Subnet、验证者、质押金额、余额、UTXO 与交易状态。查询节点版本、网络 ID 与名称、区块链 ID、启动同步状态、手续费与对等节点。
适用场景
当你需要查询 Avalanche 文档、ACP 提案、CLI 命令或 RPC 方法，或想直接查看链上交易、Subnet、验证者与 P-Chain 质押数据时，适合加入此服务器。
运行要求
需要可连接至 build.avax.network 远程端点的网络访问；声明中未要求账号、API 密钥或环境变量。
安装前请注意
部分工具会查询公开链上数据（交易、地址余额、验证者、节点对等节点信息），这些查询会发送至第三方端点。工具均为只读查询，未显示写入、发送或删除数据的能力。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Avalanche AVAX MCP，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.Airpote%2Favalanche-docs/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "avalanche-avax": {
      "type": "http",
      "url": "https://build.avax.network/api/mcp"
    }
  }
}

README

MCP Registry

The MCP registry provides MCP clients with a list of MCP servers, like an app store for MCP servers.

📤 Publish my MCP server | ⚡️ Live API docs | 👀 Ecosystem vision | 📖 Full documentation

Development Status

2025-10-24 update: The Registry API has entered an API freeze (v0.1) 🎉. For the next month or more, the API will remain stable with no breaking changes, allowing integrators to confidently implement support. This freeze applies to v0.1 while development continues on v0. We'll use this period to validate the API in real-world integrations and gather feedback to shape v1 for general availability. Thank you to everyone for your contributions and patience—your involvement has been key to getting us here!

2025-09-08 update: The registry has launched in preview 🎉 (announcement blog post). While the system is now more stable, this is still a preview release and breaking changes or data resets may occur. A general availability (GA) release will follow later. We'd love your feedback in GitHub discussions or in the #registry-dev Discord (joining details here).

Current key maintainers:

Contributing

We use multiple channels for collaboration - see modelcontextprotocol.io/community/communication.

Often (but not always) ideas flow through this pipeline:

  • Discord - Real-time community discussions
  • Discussions - Propose and discuss product/technical requirements
  • Issues - Track well-scoped technical work
  • Pull Requests - Contribute work towards issues

Quick start:

Pre-requisites
Running the server
bash
# Start full development environmentmake dev-compose

This starts the registry at localhost:8080 with PostgreSQL. The database uses ephemeral storage and is reset each time you restart the containers, ensuring a clean state for development and testing.

Note: The registry uses ko to build container images. The make dev-compose command automatically builds the registry image with ko and loads it into your local Docker daemon before starting the services.

By default, the registry seeds from the production API with a filtered subset of servers (to keep startup fast). This ensures your local environment mirrors production behavior and all seed data passes validation. For offline development you can seed from a file without validation with MCP_REGISTRY_SEED_FROM=data/seed.json MCP_REGISTRY_ENABLE_REGISTRY_VALIDATION=false make dev-compose.

The setup can be configured with environment variables in docker-compose.yml - see .env.example for a reference.

Alternative: Running a pre-built Docker image

Pre-built Docker images are automatically published to GitHub Container Registry:

bash
# Run latest stable releasedocker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:latest
# Run latest from main branch (continuous deployment)docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main
# Run specific release versiondocker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:v1.0.0
# Run development build from main branchdocker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main-20250906-abc123d

Available tags:

  • Releases: latest, v1.0.0, v1.1.0, etc.
  • Continuous: main (latest main branch build)
  • Development: main-<date>-<sha> (specific commit builds)
Publishing a server

To publish a server, we've built a simple CLI. You can use it with:

bash
# Build the latest CLImake publisher
# Use it!./bin/mcp-publisher --help

See the publisher guide for more details.

Other commands
bash
# Run lint, unit tests and integration testsmake check

There are also a few more helpful commands for development. Run make help to learn more, or look in Makefile.

Architecture

Project Structure

├── cmd/                     # Application entry points│   └── publisher/           # Server publishing tool├── data/                    # Seed data├── deploy/                  # Deployment configuration (Pulumi)├── docs/                    # Documentation├── internal/                # Private application code│   ├── api/                 # HTTP handlers and routing│   ├── auth/                # Authentication (GitHub OAuth, JWT, namespace blocking)│   ├── config/              # Configuration management│   ├── database/            # Data persistence (PostgreSQL)│   ├── service/             # Business logic│   ├── telemetry/           # Metrics and monitoring│   └── validators/          # Input validation├── pkg/                     # Public packages│   ├── api/                 # API types and structures│   │   └── v0/              # Version 0 API types│   └── model/               # Data models for server.json├── scripts/                 # Development and testing scripts├── tests/                   # Integration tests└── tools/                   # CLI tools and utilities    └── validate-*.sh        # Schema validation tools

Authentication

Publishing supports multiple authentication methods:

  • GitHub OAuth - For publishing by logging into GitHub
  • GitHub OIDC - For publishing from GitHub Actions
  • DNS verification - For proving ownership of a domain and its subdomains
  • HTTP verification - For proving ownership of a domain

The registry validates namespace ownership when publishing. E.g. to publish...:

  • io.github.domdomegg/my-cool-mcp you must login to GitHub as domdomegg, or be in a GitHub Action on domdomegg's repos
  • me.adamjones/my-cool-mcp you must prove ownership of adamjones.me via DNS or HTTP challenge

Community Projects

Check out community projects to explore notable registry-related work created by the community.

More documentation

See the documentation for more details if your question has not been answered here!

来源：README.md，提交 1b822fe

工具

47

docs_fetch

Fetch a specific documentation page as markdown

输入参数url必填

docs_list_sections

List available documentation sections and their page counts

无需输入参数。

cli_lookup_command

Look up Avalanche CLI, Platform CLI, and tmpnet command guidance in the docs. Returns cited command references and task docs.

输入参数clilimitquery必填

rpc_lookup_method

Look up Avalanche RPC methods and API guides across C-Chain, P-Chain, X-Chain, Subnet-EVM, and node RPC docs.

输入参数chainlimitquery必填

acp_lookup

Look up Avalanche Community Proposals (ACPs) by number, title, or topic. When a number is provided the structured ACP record is returned (title, status, track, authors, cross-references).

输入参数limitquerynumber

acp_list

List Avalanche Community Proposals with structured fields, optionally filtered by status (Activated, Implementable, Proposed, Stale, Withdrawn) or track (Standards, Best Practices, Meta, Subnet).

输入参数limittrackstatus

avalanche_docs_fetch

Compatibility alias for docs_fetch. Prefer docs_fetch for new clients.

输入参数url必填

avalanche_docs_list_sections

Compatibility alias for docs_list_sections. Prefer docs_list_sections for new clients.

无需输入参数。

blockchain_lookup_transaction

Look up a transaction by hash on Avalanche (C-Chain, P-Chain, or X-Chain). Supports 0x format (C-Chain) and CB58 format (P/X-Chain).

输入参数txHash必填network

blockchain_lookup_subnet

Look up a Subnet / L1 by its ID — validators, chains, and configuration.

输入参数networksubnetId必填

blockchain_lookup_chain

Look up a blockchain by its ID — name, VM type, and Subnet/L1.

输入参数chainId必填network

blockchain_lookup_validator

Look up a validator by node ID — stake, uptime, delegation info.

输入参数nodeId必填networksubnetId

platform_get_height

Get the current P-Chain block height

输入参数network

platform_get_block

Get a P-Chain block by its block ID

输入参数blockID必填networkencoding

platform_get_block_by_height

Get a P-Chain block by its height

输入参数height必填networkencoding

platform_get_blockchains

Get all blockchains that exist on the P-Chain (paginated; use limit/offset)

输入参数limitoffsetnetwork

platform_get_subnets

Get information about Subnets/L1s on the P-Chain

输入参数idslimitoffsetnetwork

platform_get_current_validators

Get the current validators of a Subnet/L1 (paginated; use limit/offset)

输入参数limitoffsetnetworknodeIDssubnetID

platform_get_pending_validators

Get the pending validators of a Subnet/L1 (paginated; use limit/offset)

输入参数limitoffsetnetworknodeIDssubnetID

platform_get_staking_asset_id

Get the asset ID of the token used for staking on a Subnet/L1

输入参数networksubnetID

platform_get_min_stake

Get the minimum staking amounts for validators and delegators on a Subnet/L1

输入参数networksubnetID

platform_get_total_stake

Get the total amount staked on a Subnet/L1

输入参数networksubnetID

platform_get_balance

Get the AVAX balance of one or more P-Chain addresses

输入参数networkaddresses必填

platform_get_utxos

Get UTXOs that reference a given set of P-Chain addresses

输入参数limitnetworkaddresses必填sourceChain

platform_get_tx

Get a P-Chain transaction by its transaction ID

输入参数txID必填networkencoding

platform_get_tx_status

Get the status of a P-Chain transaction

输入参数txID必填network

platform_get_current_supply

Get the current total supply of AVAX on a Subnet/L1

输入参数networksubnetID

platform_get_validators_at

Get the validators and their weights of a Subnet/L1 at a given P-Chain height

输入参数height必填networksubnetID

info_get_node_version

Get the version of the node, including the database version, git commit, and API compatibility info.

输入参数network

info_get_network_id

Get the numeric ID of the Avalanche network this node is participating in.

输入参数network

info_get_network_name

Get the human-readable name of the Avalanche network this node is participating in.

输入参数network

info_get_blockchain_id

Get the CB58-encoded blockchain ID for a given blockchain alias (e.g., "X", "P", "C").

输入参数alias必填network

info_is_bootstrapped

Check whether a given chain has finished bootstrapping on the node.

输入参数chain必填network

info_get_tx_fee

Get the current transaction fees for the network, returned in both nAVAX and AVAX.

输入参数network

info_peers

Get a list of peers this node is connected to. Optionally filter by specific NodeIDs.

输入参数networknodeIDs

info_acps

Get information about Avalanche Community Proposals (ACPs), including their status and vote counts.

输入参数network

blockchain_get_native_balance

Compatibility alias for onchain_lookup address balances. Prefer onchain_lookup for new clients.

输入参数address必填chainId

blockchain_get_contract_info

Compatibility alias for onchain_lookup contract metadata. Prefer onchain_lookup for new clients.

输入参数address必填chainId

blockchain_lookup_address

Compatibility alias for onchain_lookup address details. Prefer onchain_lookup for new clients.

输入参数address必填chainId

onchain_lookup

PRIMARY lookup tool — use this (not raw RPC) to resolve/describe any on-chain identifier in one call: an EVM address (native + token balances, recent txs, contract metadata + isContract), a contract/token (metadata + deployment + recent transfers), an NFT (collection + tokenId), a tx hash, a subnet ID, a NodeID validator, a P-/X-Chain account (P-…/X-… → P-Chain balance), or a chain name/id. Use this for any address balance / contract-info / token / identity question. `kind` auto-detects; network is inferred from P-/X-Chain prefixes. Backed by Glacier + P-Chain RPC.

输入参数kindvalue必填chainIdincludenetworktokenId

onchain_activity

Recent on-chain activity. scope=chain returns the transaction COUNT over the last `hours` (closed hours, max 720h = 30 days; for longer windows use chain_stats window=series) plus the latest transactions. scope=address returns the latest transactions of the address, with no time window. For a token/contract use scope=token (transfers). scope=primary covers P/X-chain and DEFAULTS to P-Chain when no blockchainId is given (so "last N P-chain transactions" just works). A value with no scope defaults to address.

输入参数feedhoursscope必填valuechainIdnetworkpageSizetoTimestampblockchainIdfromTimestamp

chain_stats

Chain statistics from the Avalanche Stats API (pre-aggregated; closed periods only, so the current hour or day is not included). target=chain: tx count, gas used, fees paid and average gas price over the last `hours` (window=recent, max 720h = 30 days), or a time-series that also has active senders (window=series, `days` max 365; timeInterval=hour max 90 days). target=network: current P-chain validator snapshot. There are no per-contract stats here; for those, run SQL in the Builder Hub explorer Query page. Note: C-Chain gasUsed is gas-target-regulated, so daily gas is about stable even as tx count varies. That is expected, not an error.

输入参数dayshourstargetwindowchainIdnetworktimeInterval

build_plan

Generate a step-by-step, copy-pasteable runbook for an Avalanche operation — Builder Console (no-code) path plus the equivalent platform-cli / SDK / interchain-kit commands. Read-only: never signs. operation: create-l1 (launch an L1); use ictt or interchain-kit for any CROSS-CHAIN / interoperability work — bridging tokens, sending cross-chain (ICM / Teleporter / Warp) messages, or connecting your L1 to C-Chain or other L1s (interchain-kit also lets you iterate locally first); validator-manager; staking; transfer.

输入参数tovmnametypestaketokenamountnodeIdchainIdexamplenetworkduration另有 7 个

console_flow

Builder Console flow knowledge. Call with NO `flow` to list every flow (summaries + deep-links); call with a `flow` key to explain it (ordered steps, equivalent CLI, whether it signs transactions, deep-link). Flows: create-l1, convert-to-l1, validator-manager, ictt, faucet, multisig, staking, transfers, interchain-kit-local.

输入参数flow

版本历史

1
  1. v1.0.1最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分