What is protoc-gen-go-mcp CLAUDE.md?

A Go compiler plugin and runtime library that generates Model Context Protocol server handlers from gRPC service definitions. gRPC is a system for defining and calling services, while MCP lets AI clients use server-provided tools.

Use it to generate Go MCP servers, create JSON schemas, register tools dynamically, build generated code, and run unit, integration, conformance, and lint checks.

It connects existing gRPC service definitions to MCP handlers, reducing the need to write those handlers manually and keeping generated interfaces aligned with the service definitions.

How redpanda-data/protoc-gen-go-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to redpanda-data/protoc-gen-go-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/redpanda-data/protoc-gen-go-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/redpanda-data/protoc-gen-go-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/redpanda-data/protoc-gen-go-mcp/claude-md.svg)](https://agentmods.dev/instructions/redpanda-data/protoc-gen-go-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/redpanda-data/protoc-gen-go-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/redpanda-data/protoc-gen-go-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,015 This file is loaded in full into every session.

When invoked 1,015 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01015	$0.01015
Opus 5	$0.00508	$0.00508
Sonnet 5	$0.00203	$0.00203
Haiku 4.5	$0.00102	$0.00102

Measured 8d ago against content hash 3eac5b725c7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

protoc-gen-go-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

protoc-gen-go-mcp

Protoc plugin + runtime library for generating MCP (Model Context Protocol) server handlers from gRPC service definitions.

Build & Test

just build                # bazelisk build //...
just test-unit            # bazelisk test //... (no API keys needed)
just test                 # All tests including conformance/integration (needs API keys)
just test-cover           # Tests with coverage report
just generate             # Regenerate proto code + descriptor set
just lint                 # Run golangci-lint
just conformancetest      # Run conformance tests against LLM providers (needs API keys)
just integrationtest      # Run all integration tests (needs API keys)
just gazelle              # Sync BUILD files from go.mod

Architecture

cmd/protoc-gen-go-mcp/     Entry point for protoc plugin
pkg/gen/                    Core library (THE important package):
  schema.go                 JSON schema generation from protoreflect descriptors
  register.go               Dynamic MCP tool registration at runtime
pkg/generator/              Protoc plugin: Go template output, delegates to pkg/gen
pkg/runtime/                MCPServer interface, FixOpenAI, error handling, extra properties
  server.go                 MCPServer interface + Tool/CallToolRequest/CallToolResult types
  mark3labs/                Adapter: mark3labs/mcp-go -> runtime.MCPServer
  gosdk/                    Adapter: modelcontextprotocol/go-sdk -> runtime.MCPServer
pkg/testdata/               Proto files + generated code for testing
conformancetest/            E2E tests against real LLM providers (Gemini, OpenAI, Anthropic)

Two modes of operation

Static (codegen): protoc-gen-go-mcp generates *.pb.mcp.go with pre-computed schemas
Dynamic (runtime): gen.RegisterService() creates MCP tools from any protoreflect.ServiceDescriptor at runtime - no codegen needed. This is the proxy/gateway mode.

Key APIs

Creating an MCP server (pick your library)

// Official go-sdk
raw, s := gosdk.NewServer("name", "1.0")    // s is runtime.MCPServer
raw.Run(ctx, &mcp.StdioTransport{})

// mark3labs/mcp-go
raw, s := mark3labs.NewServer("name", "1.0") // s is runtime.MCPServer
server.ServeStdio(raw)

Read the full file on GitHub · 102 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 102 lines · 1,015 tokens per session scan A 3eac5b725c7c

Subscribe to this mod's changes

protoc-gen-go-mcp CLAUDE.md is an instructions file published in the GitHub repository redpanda-data/protoc-gen-go-mcp (220 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,015 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Building agents

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

protoc-gen-go-mcp: Instructions file for Claude Code