Create mcp integration
Skill richfrem/agent-plugins-skills/plugins/agent-scaffolders/skills/create-mcp-integration
repo for reusable plugins and skills
npx -y skills add richfrem/agent-plugins-skills --skill create-mcp-integrationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Adds an MCP server integration configuration to an existing plugin. NOT for scaffolding a brand-new plugin (use `create-plugin`) and NOT for Azure hosted agents (use `create-azure-agent`).
SKILL.md
1.4 KB, 255 tokens by cl100k_base, as published. Nobody here has run it
Follow the create-mcp-integration skill workflow to scaffold a new MCP server
integration for a Claude Code plugin.
Inputs
$ARGUMENTS— optional MCP server name or service description (e.g.postgres,github,slack). Omit to start with discovery.
Steps
- If
$ARGUMENTSnames a server or service, use it to seed Phase 1 discovery - Follow the create-mcp-integration phased workflow: confirm server type
(stdio / SSE / streamable-http), authentication method, which tools to expose,
configuration fields, then generate the
.mcp.jsonentry and any supporting config - Report the generated configuration and setup instructions
Output
.mcp.json server entry with full configuration (command/url, env vars, allowed tools)
and instructions for obtaining credentials and verifying the connection with /mcp.
Edge Cases
- If
$ARGUMENTSis empty: begin with server type selection - If the service requires OAuth: document the auth flow steps explicitly
- Prefer
streamable-httptransport for new hosted integrations over SSE - All MCP server URLs must use HTTPS/WSS — never HTTP/WS
What ships with it: 79 files
7.5 KB alongside SKILL.md
evals/
- evals.json881 B
- results.tsv417 B
references/
- acceptance-criteria.md42 B
- authentication.md37 B
- examples/http-server.json48 B
- examples/sse-server.json47 B
- examples/stdio-server.json49 B
- fallback-tree.md36 B
- hitl-interaction-design.md46 B
- pattern-decision-matrix.md46 B
- patterns/action-forcing-output-with-deadline-attribution.md82 B
- patterns/adversarial-objectivity-constraint.md69 B
- patterns/anti-pattern-vaccination.md59 B
- patterns/anti-symptom-triage.md54 B
- patterns/artifact-embedded-execution-audit-trail.md74 B
- patterns/artifact-generation-xss-compliance-gate.md74 B
- patterns/artifact-lifecycle.md53 B
- patterns/artifact-state-interrogative-routing.md71 B
- patterns/asynchronous-benchmark-metric-capture.md72 B
- patterns/audience-segmented-information-filtering.md75 B
- patterns/category-calibrated-benchmark-anchoring.md74 B
- patterns/category-semantic-deferred-tool-binding.md74 B
- patterns/chained-command-invocation.md61 B
- patterns/chained-commands.md51 B
- patterns/client-side-compute-sandbox-constraint.md73 B
- patterns/complexity-tiered-output.md59 B
- patterns/conditional-step-inclusion.md61 B
- patterns/connector-placeholders.md57 B
- patterns/cyclical-state-propagation-contract.md70 B
- patterns/delegated-constraint-verification-loop.md73 B
- patterns/dual-mode-degradation.md56 B
- patterns/dual-mode-meta-skill.md55 B
- patterns/dual-register-communication-enforcement.md74 B
- patterns/dynamic-specification-fetching.md65 B
- patterns/embedded-deterministic-scoring-formula.md73 B
- patterns/escalation-taxonomy.md54 B
- patterns/explicit-seed-anchored-determinism.md69 B
- patterns/graduated-autonomy.md53 B
- acceptance-criteria.md359 B
- fallback-tree.md1.4 KB
39 more files not listed here. See all 79 in the repository.