mcp-server-workflows

A set of instructions for developing MCP servers, which let coding agents expose tools through a standard protocol. It covers tool registration, JSON-RPC request handling, and related TypeScript code.

In plain words
What is it for?
Use it when adding or modifying MCP tools, JSON-RPC handlers, schemas, or utilities in an MCP server's source folder.
Why use it?
It gives developers a consistent way to change server tools and handlers while preserving argument schemas, logging, and protocol rules.

Skill for Claude CodeCodex

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 skills/sap-samples/hana-developer-cli-tool-example/mcp-server-workflows
Any agent
npx skills add SAP-samples/hana-developer-cli-tool-example --skill mcp-server-workflows
Clone the repo
git clone --depth 1 https://github.com/SAP-samples/hana-developer-cli-tool-example

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 267 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.00267
Opus 5 $0.00015 $0.00133
Sonnet 5 $0.00006 $0.00053
Haiku 4.5 $0.00003 $0.00027

Measured 2d ago against content hash 5bad1ce3b1e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-workflows 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.

.github/skills/mcp-server-workflows/SKILL.md · 31 lines

What it actually says

MCP Server Workflows Skill

Use this skill for MCP server updates, tool registration, and JSON-RPC handling.

When to Use

  • Adding or modifying tools in the MCP server
  • Adjusting JSON-RPC handlers or schemas
  • Updating MCP server utilities in mcp-server/src/

Procedure

  1. Identify the target MCP file(s) and tool/handler scope.
  2. Apply MCP server development instructions for JSON-RPC compliance.
  3. Ensure tool registration and schema conversion patterns are preserved.
  4. Make minimal, testable changes and keep logging consistent.
  5. Recommend validation steps (build or tests) as needed.

Notes

  • Keep tool naming and argument schemas aligned with CLI metadata.
  • Use structured logging (stderr) and avoid console.log for protocol data.

References

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 · 31 lines · 31 tokens per session scan A 5bad1ce3b1e2

Subscribe to this mod's changes

mcp-server-workflows is a skill published in the GitHub repository SAP-samples/hana-developer-cli-tool-example (109 stars, last pushed 7d ago), licensed Apache-2.0. It adds 31 tokens to every session and 267 once invoked, about $0.0002 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 skills, from other repositories

backseat-driver-internals

Backseat Driver extension internals — Ex framework contracts, app-db state architecture, MCP socket server lifecycle, enrichment system, Datascript output log, activation sequences, and namespace reference. Use when: modifying core extension code, debugging state issues, working with app-db or Ex framework…

BetterThanTomorrow/calva-backseat-driver · 82 tokens

agents-sdk

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.

Kilo-Org/kilocode · 59 tokens

phone-a-friend

Ask Antigravity, Codex, Gemini, Claude, OpenCode, or Ollama for a second opinion through the phone-a-friend CLI while preserving the user's request in --prompt.

freibergergarcia/phone-a-friend · 43 tokens

joyride-workspace-scripting

Joyride Workspace scope scripting — scripts and source files in /.joyride/. Covers workspace activation, project-specific automation, workspace vs user scope precedence, and team sharing. Use when: creating or editing Workspace scripts/source files, setting up workspaceactivate.cljs, or building project-specific…

BetterThanTomorrow/joyride · 66 tokens

joyride-update-llm-contexts

One-time migration: modernize a Joyride project's copilot-instructions.md to use bundled skills instead of duplicated API docs or fetch URLs. Use when: the instructions file tells you to check for migration, or the user asks about updating their Joyride AI context.

BetterThanTomorrow/joyride · 62 tokens

agentv-bench

Run AgentV evaluations and optimize agents through eval-driven iteration. Triggers: run evals, benchmark agents, optimize prompts/skills against evals, compare agent outputs across providers, analyze eval results, offline evaluation of recorded sessions, run autoresearch, optimize unattended, run overnight…

EntityProcess/agentv · 101 tokens