Grpc Invoke Mcp
@grulex
关于 Grpc Invoke Mcp
grpc-invoke-mcp is an MCP server for calling gRPC methods from AI agents like Claude Code, Codex, Cursor, and other MCP-compatible tools.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"grpc-invoke": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@grulex/grpc-invoke-mcp@latest"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Grpc Invoke Mcp?
Grpc Invoke Mcp is an MCP server that lets AI agents (Claude Code, Codex, Cursor, etc.) inspect gRPC APIs and invoke unary RPCs. It supports either server reflection or local .proto files, enabling agents to explore services, understand schemas, and make real gRPC calls without writing one-off scripts.
How to use Grpc Invoke Mcp?
Install and run with npx -y @grulex/grpc-invoke-mcp@latest. Then add it as a stdio MCP server in your agent’s configuration file (e.g., .mcp.json for Claude Code, .codex/config.toml for Codex, or .cursor/mcp.json for Cursor). The package downloads a platform-specific binary during installation.
Key features of Grpc Invoke Mcp
- Call gRPC methods from MCP-compatible agents
- Describe services, methods, and message types
- Use server reflection or local
.protofiles - Connect over TLS or plaintext HTTP/2
- Send custom metadata headers
- Pass JSON request bodies for unary RPCs
Use cases of Grpc Invoke Mcp
- Let an agent explore and call internal microservices
- Test request and response payloads during development
- Send auth headers or other gRPC metadata
- Inspect gRPC APIs from local, staging, or production endpoints
- Automate gRPC integration testing in agent-driven workflows
FAQ from Grpc Invoke Mcp
What tools does Grpc Invoke Mcp provide?
Two tools: grpc_describe for schema inspection and grpc_call for invoking unary RPCs.
How do I install Grpc Invoke Mcp?
Run npx -y @grulex/grpc-invoke-mcp@latest. A platform-specific binary is downloaded during installation. Node.js and npx must be in your PATH.
Does Grpc Invoke Mcp require gRPC reflection?
No. If the target server does not expose reflection, you can use local .proto files and import paths instead.
What platforms are supported?
macOS (Apple Silicon and Intel), Linux (x64 and ARM64), and Windows (x64 and ARM64).
What if the binary download fails during installation?
Your machine needs network access to GitHub Releases. Ensure internet connectivity and retry.
开发工具 分类下的更多 MCP 服务器
MCP-Scan: An MCP Security Scanner
invariantlabs-aiSecurity scanner for AI agents, MCP servers and agent skills.
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
mcp-excalidraw
yctimlinMCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
MCP-Bridge
SecretiveShellA middleware to provide an openAI compatible endpoint that can call MCP tools
评论