CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-mcp-server

Scaffold and wire a brand-new MCP server into this google-docs-mcp hosting platform. Creates the server file, registers it in scopeMap + dispatch router + UserSession + catalog, and optionally clones a reference GitHub MCP repo and ports its tools into this codebase's FastMCP + Zod + UserSession pattern. Use this skill whenever the user mentions adding, creating, or wiring up a new MCP server, integration, or provider in this repo — even when phrased indirectly ("plug in Notion", "expose a new service", "stand up a server for X"). Also use when invoked as `/add-mcp-server <slug> [github-url]`.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exceptionally actionable, well-sequenced procedure with real validation and feedback loops — the cross-file invariants it exists to enforce are all captured concretely. Its weaknesses are verbosity (the same gotchas restated across procedure, verification, and failure-modes sections, plus incident-history anecdotes) and two missed progressive-disclosure opportunities (an orphaned references/railway.md and inline-able worked examples).

Suggestions

State each gotcha once: the scopeMap hard-coded count, dashboard paste-token allowlist, TRANSPORT typo, and gitignored-catalog points each appear in 2–4 sections at full length — keep the full explanation in the procedure step and reduce the Failure modes / step 9 entries to one-line pointers.

Extract the HubSpot OAuth worked example and the 'When another connector lands first' merge-conflict guide into reference files (e.g. references/oauth-setup.md, references/rebase-conflicts.md) and link them one level deep, mirroring how translation.md is gated on porting.

Reference the existing references/railway.md from the body (it is currently orphaned — never mentioned, so its content is undiscoverable) and add it to the File layout section's references/ listing.

DimensionReasoningScore

Conciseness

The body (~39KB) never explains concepts Claude already knows — nearly every line carries repo-specific invariants — but the same gotchas are restated at full length in multiple sections: the scopeMap hard-coded count appears in step 5a, step 8, the rebase section, and Failure modes; the dashboard paste-token allowlist in step 5f and Failure modes; the TRANSPORT typo and gitignored-catalog points likewise each appear twice or more, and incident-history anecdotes ("we hit exactly this gap with HubSpot", "#63/#68", "16 conflicts in one observed pass") pad the prose. Mostly efficient but could be tightened by stating each gotcha once and cross-referencing.

3 / 5

Actionability

Fully executable throughout: exact file paths, copy-paste command blocks (`git clone --depth 1`, `npm run typecheck`, `node scripts/buildMcpToolsDoc.mjs`, `git worktree add /tmp/mainwt origin/main --detach`), complete code snippets for the `createMcpCatalog` block and both catalog JSON shapes, the exact test assertions to add, and explicit template-to-output file mappings. Placeholders are parameterized (`<slug>`, `{{slugCamel}}`), which is appropriate for a scaffold skill.

5 / 5

Workflow Clarity

Nine clearly sequenced steps with abort-early uniqueness checks, input validation (slug regex, ask-if-missing), an explicit verification step (typecheck + test) with named failure modes and remediation, and genuine feedback loops: fix-and-re-run test guidance, "Reproduce on unmodified main before touching anything" for suspected environmental hangs, and explicit prohibitions ("Don't reach for `as any`"). The report step ends with a checklist of manual follow-ups.

5 / 5

Progressive Disclosure

Good structure: templates are externalized to `assets/` (all five referenced files exist), `references/translation.md` is gated ("read only when porting from a github-url"), references are one level deep, and the File layout section documents the bundle. Two gaps keep it from 5: `references/railway.md` exists in the bundle but is never referenced from SKILL.md or listed in the File layout (orphaned, undiscoverable), and the HubSpot OAuth worked example plus the merge-conflict resolution guide are substantial self-contained topics inlined in the body that belong in reference files.

4 / 5

Total

17

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete action list, explicit trigger clause with natural paraphrases, third-person voice, and tight repo scoping. The only weakness is mild trigger overlap with closely related sibling skills (notably 'integration' vs update-integrations and 'add MCP' vs add-mcp-tool).

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage: "Creates the server file, registers it in scopeMap + dispatch router + UserSession + catalog, and optionally clones a reference GitHub MCP repo and ports its tools into this codebase's FastMCP + Zod + UserSession pattern." Every action is specific and named down to the exact code artifacts touched; there is no vague filler.

5 / 5

Completeness

Explicitly answers both questions: the 'what' is the concrete scaffold-and-wire action list, and the 'when' is a dedicated "Use this skill whenever the user mentions..." clause with concrete trigger phrases and the repo scoping ("in this repo"). Matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and indirect paraphrases: "adding, creating, or wiring up a new MCP server, integration, or provider" plus explicitly coached phrasings users actually say ("plug in Notion", "expose a new service", "stand up a server for X") and the slash-command invocation form. It even covers the case where the user doesn't use the word 'server' at all.

5 / 5

Distinctiveness Conflict Risk

The niche is clear ("brand-new MCP server" on "this google-docs-mcp hosting platform", "in this repo") and unlikely to trigger for unrelated skills. However, the claimed trigger "integration" overlaps with the sibling `update-integrations` skill, and "adding... a new MCP server" sits close to `add-mcp-tool` territory — minor overlap risk with closely related skills rather than minimal.

4 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 3 possibly missing (references/tool-pattern.md, scripts/buildMcpToolsDoc.mjs, scripts/buildRestEndpointsDoc.mjs)

Warning

Total

14

/

16

Passed

Repository

boarlabsxyz/awesome-mcp

Path

.claude/skills/add-mcp-server/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.