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 pjosols/pyfastmail-mcp --skill tool-registrationgit clone --depth 1 https://github.com/pjosols/pyfastmail-mcpWrote 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/pjosols/pyfastmail-mcp/tool-registration)<a href="https://agentmods.dev/skills/pjosols/pyfastmail-mcp/tool-registration"><img src="https://agentmods.dev/badge/skills/pjosols/pyfastmail-mcp/tool-registration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pjosols/pyfastmail-mcp/tool-registration"><img src="https://agentmods.dev/badge/skills/pjosols/pyfastmail-mcp/tool-registration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00232 |
| Opus 5.5 | $0.00000 | $0.00093 |
| Sonnet 5.5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
tool-registration scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
MCP Tool Registration
Pattern
from mcp.server import FastMCP
server = FastMCP("pyfastmail-mcp")
@server.tool()
async def tool_name(param: str, optional_param: int = 10) -> str:
"""Clear description of what this tool does."""
# Tools return strings (JSON formatted for structured data)
return json.dumps(result, indent=2)
Guidelines
- Tool functions are async.
- Use type hints on all parameters — MCP uses them to generate the schema.
- Default values define optional parameters.
- Return
stralways. Usejson.dumpsfor structured data. - Tool description (docstring) should be clear enough for an LLM to know when to use it.
- Keep tool functions thin: validate → call client → format response.
- Handle errors gracefully — return error messages, don't raise exceptions to the MCP layer.
Registration Pattern (per module)
def register(server: FastMCP, client: JMAPClient):
@server.tool()
async def my_tool(...) -> str:
...
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.
- 1mo ago First seen · 32 lines · 0 tokens per session scan A d8b6ef021104
tool-registration is a skill published in the GitHub repository pjosols/pyfastmail-mcp (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 232 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
calendar-contacts-tasks
Reads and changes the user's own calendars, contacts and to-dos on their CalDAV/CardDAV server (Nextcloud, iCloud, Baikal, Radicale and others) through the dav-mcp tools - finding events, free time, phone numbers and tasks, and creating, moving, cancelling or deleting them safely. Use whenever the user asks about or…
olk
Microsoft Outlook and OneDrive CLI and MCP for email, calendar, contacts, tasks, and files, for personal and enterprise accounts.
using-outlook-assistant
Safety, privacy and efficient-use rules for the Outlook Assistant (outlook) MCP tools, covering Outlook email, calendar, contacts, folders, rules, categories and mailbox settings on personal Outlook.com and work/school Microsoft 365 accounts. Read it before the first Outlook Assistant tool call in a session, and again…
Pear - iCloud Calendar, Reminders, Contacts & Mail
Pear provides hosted MCP access to iCloud Calendar, Contacts, Mail, and legacy CalDAV reminder data. Tools are prefixed with pear. Calendar and legacy reminders use CalDAV; Contacts use CardDAV; Mail uses IMAP/SMTP. Apple's upgraded Reminders store is not accessible through this connection.
nylas-api
Build email, calendar, and contacts integrations with the Nylas v3 API. Use when code imports nylas, @nylas/nylas, nylas-python, or user asks about Nylas API, email API integration, calendar API, contacts API, OAuth grants, agent accounts, webhooks, scheduler, notetaker, smart compose, or transactional send. DO NOT…
nylas-email-templates
Write, test, and deploy Nylas email templates and workflows with an API key. Use when user asks to create or edit a Nylas email template, set up a workflow for booking., event., grant., notetaker., or message. triggers, send email with a stored template through the Send API, translate or brand a Scheduler email, or…