streamnative-mcp-server AGENTS.md

Repository instructions for a Go server that exposes StreamNative Cloud, Apache Kafka, and Apache Pulsar operations through the Model Context Protocol (MCP), a standard way for AI agents to call tools.

In plain words
What is it for?
Use them when changing the command-line server, its MCP tools, session handling, standard-input or HTTP event transport, builds, tests, Docker images, or Helm charts.
Why use it?
They explain the project layout, supported server modes, technology choices, and the expected local development workflow.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/streamnative/streamnative-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/streamnative/streamnative-mcp-server

Made for: Codex, OpenCode.

Per session 2,839 This file is loaded in full into every session.
When invoked 2,839 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02839 $0.02839
Opus 5 $0.01419 $0.01419
Sonnet 5 $0.00568 $0.00568
Haiku 4.5 $0.00284 $0.00284

Measured 2d ago against content hash ebdfef6d6f0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

streamnative-mcp-server 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 2d 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.

AGENTS.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guide for autonomous coding agents working in streamnative-mcp-server.


1 | Project Snapshot

  • What it is: A Go-based Model Context Protocol (MCP) server that exposes StreamNative Cloud, Apache Kafka, and Apache Pulsar operations through one MCP surface.
  • Primary binary: bin/snmcp, built from cmd/streamnative-mcp-server/main.go.
  • Server modes: stdio and sse.
  • Current stack: Go 1.25.12, cobra, mark3labs/mcp-go, Docker, Helm, GoReleaser.
  • Published container names: streamnative/mcp-server and streamnative/snmcp.

2 | Repository Map

Path Purpose Notes
cmd/streamnative-mcp-server/ Root CLI entrypoint Owns the snmcp command and top-level Cobra wiring
cmd/snmcp-e2e/ Go E2E client Used by chart and SSE authentication end-to-end tests
pkg/cmd/mcp/ Transport/bootstrap layer Completes config, creates sessions, starts stdio or sse servers
pkg/mcp/ Core MCP server logic Feature flags, prompts, context tools, wrapper registration, runtime instructions
pkg/mcp/internal/context/ Session/context plumbing Reuse these typed context helpers instead of introducing parallel context-key patterns
pkg/mcp/builders/kafka/ Kafka tool builders Preferred home for Kafka MCP tool schemas and handlers
pkg/mcp/builders/pulsar/ Pulsar tool builders Preferred home for Pulsar MCP tool schemas and handlers
pkg/mcp/session/ Multi-session Pulsar support SSE bearer-token session cache and eviction logic
pkg/config/ CLI/config resolution StreamNative Cloud, external Kafka, external Pulsar options
pkg/kafka/, pkg/pulsar/, pkg/auth/, pkg/schema/ Service/session/auth/schema helpers Touch carefully; these support the tool layer
docs/tools/ Tool-facing Markdown docs These docs are surfaced to MCP clients at runtime
agents/ Design notes and MCP proposals Review when changing protocol, auth, compliance, or multi-session behavior
charts/snmcp/ Helm chart Deploys SSE mode with multi-session Pulsar support
charts/snmcp/e2e/ Chart test fixtures Test tokens, local values, and auth fixtures for E2E
scripts/e2e-test.sh Local chart E2E harness Uses Docker, Kind, Helm, kubectl, and cmd/snmcp-e2e
sdk/sdk-apiserver/ Local generated SDK module Referenced via replace in root go.mod
sdk/sdk-kafkaconnect/ Local generated SDK module OpenAPI-generated code; avoid casual hand-edits
.github/workflows/ CI pipelines Unit tests, lint, GoReleaser, chart E2E

Read the full file on GitHub · 226 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.

  1. 2d ago First seen · 226 lines · 2,839 tokens per session scan A ebdfef6d6f0f

Subscribe to this mod's changes

streamnative-mcp-server AGENTS.md is an instructions file published in the GitHub repository streamnative/streamnative-mcp-server (24 stars, last pushed 19d ago), licensed Apache-2.0. It adds 2,839 tokens to every session, about $0.0142 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.

Related

Other instructions, from other repositories