mcp-server-builder

Guidance for building MCP servers, which are small services that expose tools for an AI assistant to use. It covers tool definitions, access control, tests, setup, and integration planning.

In plain words
What is it for?
Use it to design or build an MCP server, wrap an API, add authentication, deploy a remote service, or review MCP server code. It also helps test tool schemas and failure cases.
Why use it?
It helps turn an API or other service into clearly limited tools with understandable inputs, errors, authentication, and safety boundaries.

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/codeinfinity1/stram/mcp-server-builder
Any agent
npx skills add CodeInfinity1/Stram --skill mcp-server-builder
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 405 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 $0.00033 $0.00405
Opus 5 $0.00016 $0.00202
Sonnet 5 $0.00007 $0.00081
Haiku 4.5 $0.00003 $0.00040

Measured 2d ago against content hash 5d3fe3566e4d, 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-builder 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.

skills/browser-web/mcp-server-builder/SKILL.md · 67 lines

What it actually says

MCP Server Builder

Purpose

Build or plan Model Context Protocol servers as explicit tool surfaces. This skill emphasizes schema clarity, auth, least privilege, and verification.

When To Use

Use when the user asks to build an MCP server, expose tools, wrap an API, add OAuth/auth, deploy a remote MCP service, or review MCP server code.

Inputs And Evidence

  • Desired tools/resources, auth model, host/runtime, deployment target, and client integration needs.
  • Existing code, API docs, schemas, and tests.

Tool Map

  • read_file
  • search_workspace
  • write_note
  • run_shell_command
  • tool_search
  • agent-api-integration

Workflow

  1. Define tool/resource contracts and user-visible capability boundaries.
  2. Choose runtime and auth model.
  3. Implement small typed tools with clear schemas and errors.
  4. Add tests for schema validation, auth, and failure cases.
  5. Document setup and secrets.
  6. Verify with local or deployed smoke tests.

Native Implementation Boundaries

  • Implement MCP code inside the user's project or Stram-owned adapters.
  • Do not import Anthropic MCP builder skill code as implementation.
  • Do not expose broad filesystem/network access without explicit policy.

Safety And Approval

  • Auth, secrets, and external APIs require careful setup.
  • Tools that mutate external state need approval modes.
  • Avoid logging tokens or private payloads.

Verification

  • Validate tool schemas.
  • Run local tests and an MCP client smoke where feasible.
  • Confirm auth failure behavior.

Failure Modes

  • Tools with vague inputs.
  • No error contract.
  • Overpowered server access.

References

  • Shortlist item: mcp-server-builder.
  • Upstream inspiration: Anthropic MCP builder reference only.
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 · 67 lines · 33 tokens per session scan A 5d3fe3566e4d

Subscribe to this mod's changes

mcp-server-builder is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 405 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 2026-08-31.