bonk-mcp 服务器为 LetsBonk 启动板实现了 Solana 区块链功能。
代币发行：在 letsbonk.fun 上发行任何代币
代币交易：在 letsbonk.fun 上购买/出售任何代币
Related MCP server: Solana MCP Server
您可以在 Claude Desktop 中将 bonk-mcp 服务器添加到 MCP 服务器配置中来配置它。您需要提供以下信息：
bonk-mcp 目录的路径
环境变量：
KEYPAIR ：您的 Solana 密钥对
RPC_URL ：Solana RPC 端点（例如https://api.mainnet-beta.solana.com ）
在 MacOS 上： ~/Library/Application\ Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"bonk-mcp": {
"command": "uv",
"args": [
"--directory",
"<PATH_TO_BONK_MCP_DIRECTORY>/bonk-mcp",
"run",
"bonk-mcp"
],
"env": {
"KEYPAIR": "<YOUR_SOLANA_KEYPAIR>",
"RPC_URL": "https://api.mainnet-beta.solana.com"
}
}
}"mcpServers": {
"bonk-mcp": {
"command": "uvx",
"args": [
"bonk-mcp"
],
"env": {
"KEYPAIR": "<YOUR_SOLANA_KEYPAIR>",
"RPC_URL": "https://api.mainnet-beta.solana.com"
}
}
}准备分发包：
同步依赖项并更新锁文件：
uv sync构建软件包分发版：
uv build这将在dist/目录中创建源和轮子分布。
发布到 PyPI：
uv publish注意：您需要通过环境变量或命令标志设置 PyPI 凭据：
令牌： --token或UV_PUBLISH_TOKEN
或用户名/密码： --username / UV_PUBLISH_USERNAME和--password / UV_PUBLISH_PASSWORD
由于 MCP 服务器通过 stdio 运行，调试起来可能比较困难。为了获得最佳调试体验，我们强烈建议使用MCP Inspector 。
您可以使用以下命令通过npm启动 MCP Inspector：
npx @modelcontextprotocol/inspector uv --directory <PATH_TO_BONK_MCP_DIRECTORY>/bonk-mcp run bonk-mcp启动后，检查器将显示一个 URL，您可以在浏览器中访问该 URL 以开始调试。
Launch a new meme token on Solana using Raydium launchpad
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | Token description | |
| image_url | Yes | Image URL to use for token | |
| name | Yes | Token name | |
| symbol | Yes | Token symbol/ticker | |
| telegram | No | Telegram group URL (optional) | |
| No | Twitter handle/URL (optional) | ||
| website | No | Website URL (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the action ('Launch') which implies a write/mutation operation, but fails to disclose critical behavioral traits such as required permissions, cost implications, irreversible effects, rate limits, or what the response looks like. This leaves significant gaps for an agent to understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded with the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given this is a complex write operation (token launch) with no annotations and no output schema, the description is incomplete. It doesn't address behavioral aspects like permissions, costs, or response format, nor does it provide usage context. The 100% schema coverage helps with parameters, but overall context for safe and effective use is lacking.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no parameter-specific information beyond what's already in the input schema, which has 100% coverage with clear descriptions for all 7 parameters. The baseline score of 3 reflects adequate schema documentation, but the description adds no additional semantic context about parameter usage or relationships.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Launch') and target resource ('new meme token on Solana using Raydium launchpad'), providing specific verb+resource. However, since there are no sibling tools mentioned, it cannot demonstrate differentiation from alternatives, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or exclusions. It simply states what the tool does without context about appropriate scenarios or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0launch-tokenScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool has a clear and distinct purpose focused on launching meme tokens on Solana.
A single tool inherently has perfect naming consistency as there are no other tools to compare against. The name 'launch-token' follows a clear verb-noun pattern.
One tool is too few for a server with a domain like launching tokens, as it lacks essential operations like checking token status, managing launches, or handling transactions. This severely limits agent functionality.
The tool surface is severely incomplete; it only provides a launch function without supporting operations like querying token details, updating launches, or deleting/canceling tokens. This will cause frequent agent failures in real-world scenarios.
Non-custodial Solana toolkit: rug-checks, swaps, portfolios, token minting, multisig, Arweave.
Plan a Solana token launch
Launch Solana coins from your AI. You approve each launch in your wallet and earn creator fees.
Full Solana DeFi coverage: launchpads, tokens, trades, and wallets, decoded at scale.
