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.
npx skills add archimedes-run/omniHarness --skill mcp-server-buildergit clone --depth 1 https://github.com/archimedes-run/omniHarnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/archimedes-run/omniharness/mcp-server-builder)<a href="https://agentmods.dev/skills/archimedes-run/omniharness/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/archimedes-run/omniharness/mcp-server-builder.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.02407 |
| Opus 5 | $0.00019 | $0.01203 |
| Sonnet 5 | $0.00008 | $0.00481 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
mcp-server-builder scanned grade A with 1 finding 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 8d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| **Never import `subprocess`, `os.system`, `os.popen`, `eval`, `exec`, `pickle`, or `ctypes`** | These are hard-blocked by the static security scanner and will permanently fail verification | How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Builder
Use this skill when a user asks to create, generate, or build an MCP server. OmniHarness can scaffold a fully functional FastMCP server from a description, write the source code, and run it through the automated test pipeline.
Workflow
- Understand the intent — identify the server name, description, template type, and any external services or secrets needed.
- Scaffold the code — write
server.pyusing FastMCP following the template below. Each tool must have a clear docstring and typed parameters. - Submit for testing — call
mcp_build(server_id=..., source_code=...). The tool runs static security scans, checks that all required secrets are stored in the vault, starts the server in an isolated subprocess, connects the MCP client, lists the discovered tools, and test-calls each one. - Report results — tell the user which tools were discovered, which test-calls passed, and whether any secrets are missing.
- Iterate — if errors are returned fix the code and call
mcp_buildagain.
Do NOT write files to the sandbox for this skill. Pass the complete source code directly to mcp_build as the source_code parameter.
Project structure
A minimal MCP server consists of a single server.py file.
server.py ← entrypoint — always named server.py
requirements.txt ← optional — any extra pip packages beyond fastmcp
server.py skeleton
import os
from mcp.server.fastmcp import FastMCP
mcp = FastMCP("server-name")
@mcp.tool()
def tool_name(param: str) -> str:
"""One-sentence description of what this tool does and what it returns."""
# implementation
return result
if __name__ == "__main__":
_transport = os.environ.get("MCP_TRANSPORT", "stdio")
if _transport == "sse":
mcp.settings.host = "0.0.0.0"
mcp.settings.port = int(os.environ.get("MCP_PORT", "8080"))
mcp.settings.transport_security = None
mcp.run(transport="sse")
else:
mcp.run()
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.
- 8d ago First seen · 273 lines · 39 tokens per session scan A f8ed654deeec
mcp-server-builder is a skill published in the GitHub repository archimedes-run/omniHarness (7 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 2,407 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
html-preview
A guidance skill for adding small, static HTML/CSS visual previews to Markdown when a diagram, comparison, timeline, metric display, or layout sketch would be clearer than text. It does not use JavaScript.
deep-research
A method for organising research that uses several sources and needs fact checking. It breaks a broad question into smaller investigations, checks important claims and combines the results into a cited report.
knowledge-base
A tool for searching and reading documents stored in a configured knowledge base. It can find relevant passages, open documents, locate terms, and show the knowledge base’s mind map.
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
channel-bot
Work with messaging-channel bots (Telegram / Slack) — register a bot, route inbound messages through the AI agent, handle webhooks vs polling, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery.