A skill that creates JSON Web Tokens, or JWTs, which are signed credentials used to authenticate requests to an MCP server. It collects a username and token lifetime, with optional request, IP, service, and extra settings.

It is for issuing tokens for users, setting how long they remain valid, and optionally restricting them by request, IP address, service, or other parameters.

It removes the need to construct authentication tokens by hand and helps apply the required lifetime and access details consistently.

How OlliMakarova/mcp-metro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OlliMakarova/mcp-metro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/OlliMakarova/mcp-metro/master/.claude/skills/gen-jwt/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/OlliMakarova/mcp-metro

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/gen-jwt/github.svg)](https://agentmods.dev/skills/ollimakarova/mcp-metro/gen-jwt)

Your own site

<a href="https://agentmods.dev/skills/ollimakarova/mcp-metro/gen-jwt"><img src="https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/gen-jwt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ollimakarova/mcp-metro/gen-jwt"><img src="https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/gen-jwt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,405 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 92% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.00045	$0.01405
Opus 5.5	$0.00018	$0.00562
Sonnet 5.5	$0.00009	$0.00281
Haiku 4.5	$0.00005	$0.00140

Measured 2mo ago against content hash 23a70b4caf70, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gen-jwt 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 2mo 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.

Origin

This is a copy

92% identical to gen-jwt — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/gen-jwt/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JWT Token Generator

Generate a JWT token by running node scripts/generate-jwt.js with the appropriate parameters.

Parameter Extraction

Parse $ARGUMENTS and the user's request to extract:

username (REQUIRED) — the user the token is issued to
ttl (REQUIRED) — token lifetime in format <N>s | <N>m | <N>d | <N>y (seconds, minutes, days, years)
request (optional) — ticket/issue ID if user mentions "ticket", "request", "issue", "REQ-", "JIRA-" etc. The param key is always request
ip (optional) — allowed IP addresses/CIDR masks, comma-separated
service (optional) — service name, passed via -s
extra params (optional) — any other key=value pairs

Interactive Flow

Step 1: Validate required params

If username is missing or empty:

Tell the user: "Username is required. Please specify the user the token should be issued to."
Wait for response. Do not proceed without it.

If ttl is missing, not provided, or doesn't match <N>s | <N>m | <N>d | <N>y:

Tell the user: "Token lifetime (TTL) is required in format: <N>s (seconds), <N>m (minutes), <N>d (days), or <N>y (years). For example: 30d, 1y, 8d. Please specify."
Wait for response. Do not proceed without a valid TTL.

Step 2: Ask about optional params (only if not already provided)

If the user did NOT mention a request/ticket:

Ask: "Bind to a ticket? (enter the ticket ID, or press Enter to skip)"
If user says "no", "skip", "-", or presses Enter — omit the request param.

If the user did NOT mention IP restrictions:

Ask: "Restrict by IP? (enter IP/CIDR values comma-separated, or press Enter to skip)"
If user says "no", "skip", "-", or presses Enter — omit the ip param.

Step 3: Build and run the command

Construct the CLI command:

node scripts/generate-jwt.js -u <username> -ttl <ttl> [-s <service>] [-p "<params>"]

The -p value is a semicolon-separated string of key=value pairs built from:

request=<ticket> (if provided)
ip=<addresses> (if provided)
Any extra key=value pairs from the user's message

Read the full file on GitHub · 112 lines

Changes

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.

2mo ago First seen · 112 lines · 45 tokens per session scan A 23a70b4caf70

Subscribe to this mod's changes

gen-jwt is a skill published in the GitHub repository OlliMakarova/mcp-metro (0 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,405 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to gen-jwt, differing in 17 lines, and is treated as a copy.

Backend and APIs Security

gen-jwt next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gen-jwtOlliMakarova/mcp-metro	Skill	0	3mo ago	MIT	A	45	Claude Code
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code
fastapi-router-pymicrosoft/skills	Skill	3.2k	yesterday	MIT	A	46	Claude Code
dev-runtimelangwatch/langwatch	Skill	5.0k	yesterday	Apache-2.0	A	172	Claude Code
api-designericrisco/rsc-harness	Skill	503	2d ago	MIT	A	105	Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1	Skill	252	yesterday	MIT	A	106	Claude Code

mcp-metro: Skill for Claude Code