mcp-go is a Go software development kit for building Model Context Protocol servers that expose data and functions to large language model applications in a standardized way. Go developers use it to create tools, resources, prompts, and server integrations without implementing the protocol details themselves.
Borrowing it
Nothing to install: this file belongs to mark3labs/mcp-go. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mark3labs/mcp-go/main/AGENTS.mdgit clone --depth 1 https://github.com/mark3labs/mcp-goWrote 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.
[](https://agentmods.dev/instructions/mark3labs/mcp-go/agents-md)<a href="https://agentmods.dev/instructions/mark3labs/mcp-go/agents-md"><img src="https://agentmods.dev/badge/instructions/mark3labs/mcp-go/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mark3labs/mcp-go/agents-md"><img src="https://agentmods.dev/badge/instructions/mark3labs/mcp-go/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00464 | $0.00464 |
| Opus 5.5 | $0.00186 | $0.00186 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
mcp-go AGENTS.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 2mo 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.
What it actually says
Commands
- Test all:
go test ./... -race - Test package:
go test ./mcp -vorgo test ./server -v - Test single:
go test -run TestName ./package -v - Coverage:
go test -coverprofile=coverage.txt -covermode=atomic $(go list ./... | grep -v '/examples/' | grep -v '/testdata' | grep -v '/mcptest' | grep -v '/server/internal/gen') - Lint:
golangci-lint run(uses .golangci.yml config) - Generate:
go generate ./...(regenerates hooks and request handlers)
Git
- Verified commits: When possible, make verified (signed) commits using GPG, SSH, or S/MIME signing keys
Code Style
- Imports: Standard library first, then third-party, then local packages (goimports handles this)
- Naming: Use Go conventions - exported names (PascalCase), unexported names (camelCase), acronyms uppercase (HTTP, JSON, MCP)
- Error handling: Return sentinel errors (e.g.,
ErrMethodNotFound), wrap withfmt.Errorf("context: %w", err), useerrors.Is/Asfor checking - Types: Use explicit types; avoid
anyexcept for protocol flexibility (e.g.,Arguments any); prefer strongly-typed structs - Comments: All exported types/functions MUST have godoc comments starting with the name; no inline comments unless necessary
- Testing: Use
testify/assertandtestify/require; table-driven tests withtests := []struct{ name, ... }; test files end in_test.go - Context: Always accept
context.Contextas first parameter in handlers and long-running functions - Thread safety: Use
sync.Mutexfor shared state; document thread-safety requirements in comments - JSON: Use json tags with
omitemptyfor optional fields; usejson.RawMessagefor flexible/deferred parsing
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.
- 2mo ago First seen · 22 lines · 464 tokens per session scan A 827ba09174f0
mcp-go AGENTS.md is an instructions file published in the GitHub repository mark3labs/mcp-go (9,225 stars, last pushed 3d ago), licensed MIT. It adds 464 tokens to every session, about $0.0019 per session on Opus 5.5. 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.
mcp-go AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-go AGENTS.mdmark3labs/mcp-go | Instructions file | 9.2k | 3d ago | MIT | A | 464 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |