Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Create Mcp Server · gsd-build | DecimalAI

agent toolingby gsd-build

Create Mcp Server

gsd-build/create-mcp-server

Source gsd-build/gsd-2 ↗License MIT

Build, iterate, and evaluate Model Context Protocol (MCP) servers that expose external services as tools an LLM can call.

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 9/27/2026

What it changes

Passed 20 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill91%

Checks it passed that the model alone missed

Model output omits total page counts.
The evals.xml structure uses root evals tags.
Pagination avoids page-number style parameters.

and 10 more in the full report

7 fixed13 passed either way2 still failing0 broke

Pass-rate lift: +32 pp
Tokens: +42%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 9/27/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/gsd-build-create-mcp-server/SKILL.md https://app.decimal.ai/s/gsd-build-create-mcp-server/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gsd-build-create-mcp-server, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/gsd-build-create-mcp-server/ and pins it in .decimal/skills.lock

decimalai skills add gsd-build-create-mcp-server

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/gsd-build-create-mcp-server/SKILL.md https://app.decimal.ai/s/gsd-build-create-mcp-server/SKILL.md

Raw file: /s/gsd-build-create-mcp-server/SKILL.md ↗ · machine-readable summary at /s/gsd-build-create-mcp-server.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I need to build an MCP server so our team's AI assistant can interact with our internal incident management API. Please guide me through scoping the service down into a few high-leverage tools, setting up the Node.js project architecture, handling client authentication and clear error messages, verifying everything using the MCP Inspector tool, creating a suite of multi-turn evaluation test cases to confirm the assistant can use it reliably, and registering the finished server in our GSD configuration.

What was checked, without and with the skill
Checked	Without skill	With skill
The evaluation suite is specified in an evals.xml file.	Missed	Passed
The evaluation suite contains exactly 10 test questions.	Missed	Passed
The pagination design uses opaque cursor parameters in pagination.ts.	Missed	Passed

case-01 · gemini-3.6-flash · 9/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md116 linessingle file

Invocation points:

User describes a service or API they want an LLM to reach
/gsd mcp init scaffolds config but there's a tool integration to build
Replacing a hand-rolled extension with a standard MCP server

<core_principle> THE QUALITY METRIC IS TASK COMPLETION, NOT SCHEMA VALIDITY. A server that lists 30 tools with cryptic names and empty descriptions passes the protocol but fails the point. The tool description is the only thing an LLM has to decide whether to call it — write it like documentation for a stranger under time pressure.

DESIGN FOR THE MODEL, NOT THE API. A raw REST endpoint is rarely the right tool. Group, filter, and pre-shape responses so the model gets what it needs to reason, not a 40KB JSON blob it has to summarize. Fewer, deeper tools beat many, shallow ones. </core_principle>

Step 1: Research and scope

Study modern MCP design. Read the latest MCP protocol docs (not training data — fetch them). Read 2–3 reference implementations to see current patterns.
Pick a framework. TypeScript is the default — the reference SDK is the most mature. Python is fine for data-heavy or ML adjacencies.
Analyze the target API. Map the external service's endpoints, auth, rate limits, pagination, error shapes. Identify what a human workflow on top of it actually looks like — that's the cut line for tool design.
Produce a brief. One page: what the server does, who calls it, the 5–10 tools you plan to expose, and the top 3 design trade-offs. Confirm with the user.

Step 2: Set up the project

Skeleton:

server/
  src/
    index.ts         # MCP entry point — stdio or sse transport
    client.ts        # API client with auth, retries, typed errors
    tools/           # one file per tool, or grouped by domain
    pagination.ts    # shared cursor handling
    errors.ts        # MCP-friendly error formatting

Track record

Benchmark

20 / 22

test cases passed, vs 13 / 22 without

Adoption

Users: 1
Times used: 33

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/31/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

gsd-build / gsd-2

src/resources/skills/create-mcp-server/SKILL.md

View on GitHub ↗

License MITImported 8/31/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.