A planning, implementation and evaluation guide for MCP servers that expose external services to agents.
Editorial review checked 2026-10-29 against this instruction snapshot. Supporting scripts and runtime behavior remain outside this editorial review.
This skill structures MCP server development around understanding the upstream service, designing discoverable tools, implementing the integration and evaluating realistic tasks. It pays attention to bounded responses and useful failures, which matter when an agent must choose and combine tools without reading a whole service manual for every request.
A team turning an existing API into an agent integration, or reviewing whether a proposed server exposes the operations users actually need. Start with concrete read and write tasks and identify the permissions each operation requires.
An MCP wrapper inherits the upstream API's authentication, limits and data-handling constraints. Installing a server does not grant permission to perform every exposed operation. SDK and transport examples must match the versions used by the project; the guide should not silently trigger an unrelated migration.
Unknown; inspect source requirements and supporting scripts.
Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.
npx skills add https://github.com/anthropics/skills/tree/ca45fc496a3436251f191354091d557da31c15b5/skills/mcp-builder --skill mcp-builderReview pinned skill folder ↗ · CLI documentation ↗
After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.
Static review only. This is not a security audit or a guarantee of safety.
SKILL.md text only; scripts, dependencies and runtime behavior not audited.
Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.
86/100 · Metadata coverage 100% · Model 1.0
Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.
Define the smallest useful tool surface, implement input validation and focused result schemas, then evaluate representative tasks against a test service or restricted account. Distinguish protocol compatibility from whether the workflow achieves the intended result.
Exercise pagination, invalid inputs, authorization failures and timeouts as well as successful calls. Inspect write operations separately and confirm that errors do not disclose credentials or private service responses.
Related by category; compare scope and dependencies before choosing an alternative.
Explore diagnosing superpowers as a automation & agents workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.
Explore using superpowers as a automation & agents workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.
Explore 10 andruia skill smith as a automation & agents workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore academy guide as a productivity & planning workflow from anthropics/skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore algorithmic art as a development workflow from anthropics/skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore brand guidelines as a design & ux workflow from anthropics/skills. Compare its source, maintenance and review signals before choosing it for your agent.