What is run-jb-gateway-mcp?

A procedure for starting and checking the jb_gateway_mcp server through a real MCP client session. MCP is a protocol that lets an agent discover and call tools provided by another process.

Use it to launch, smoke-test, or verify jb_gateway_mcp, including cases where policy correctly allows or denies a tool call.

It verifies the server's handshake, available tools, policy-controlled calls, and audit logging instead of treating a process launch alone as proof that it works.

How jitheshb83/jb_gateway_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jitheshb83/jb_gateway_mcp. 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/jitheshb83/jb_gateway_mcp/main/.claude/skills/run-jb-gateway-mcp/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jitheshb83/jb_gateway_mcp

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/jitheshb83/jb_gateway_mcp/run-jb-gateway-mcp/github.svg)](https://agentmods.dev/skills/jitheshb83/jb_gateway_mcp/run-jb-gateway-mcp)

Your own site

<a href="https://agentmods.dev/skills/jitheshb83/jb_gateway_mcp/run-jb-gateway-mcp"><img src="https://agentmods.dev/badge/skills/jitheshb83/jb_gateway_mcp/run-jb-gateway-mcp/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/jitheshb83/jb_gateway_mcp/run-jb-gateway-mcp"><img src="https://agentmods.dev/badge/skills/jitheshb83/jb_gateway_mcp/run-jb-gateway-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,772 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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	$0.00071	$0.01772
Opus 5.5	$0.00028	$0.00709
Sonnet 5.5	$0.00014	$0.00354
Haiku 4.5	$0.00007	$0.00177

Measured 2mo ago against content hash 85e5043b1776, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

run-jb-gateway-mcp 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/smoke_test.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

to `curl`. "Running" it means launching it exactly as a real MCP client

.claude/skills/run-jb-gateway-mcp/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running jb_gateway_mcp

jb_gateway_mcp is a stdio MCP server — it has no port or health endpoint to curl. "Running" it means launching it exactly as a real MCP client would and driving a session against it, which is what scripts/smoke_test.py in this skill directory does.

Prerequisites

uv installed and on PATH
Run from the repo root: /Users/jithesh/Documents/GitHub/jb_gateway_mcp
policy.yaml should have grants under caller local for a fully "allowed" smoke test (see README.md §4) — but the script is useful either way: a denial is a correct, expected outcome when nothing is granted, not a failure.

Setup

Dependencies are managed by uv — there's no separate build step, uv run resolves/syncs the environment on first use. To pre-sync explicitly:

cd /Users/jithesh/Documents/GitHub/jb_gateway_mcp
uv sync

Run + verify (one command)

cd /Users/jithesh/Documents/GitHub/jb_gateway_mcp
uv run python .claude/skills/run-jb-gateway-mcp/scripts/smoke_test.py

What it does:

Spawns the real server via scripts/start.sh — the same entrypoint every client config in this repo (.mcp.json, config/*.example.json) uses.
Opens a real MCP ClientSession, does the protocol handshake.
Lists tools and checks all 8 expected ones are present (ping + 7 Google tools).
Calls ping, expects pong.
Calls gmail.list_messages, calendar.list_events, drive.list_files against a placeholder account, and reports ALLOWED/DENIED per tool (driven by policy.yaml, caller id local).
Prints the resulting audit log and fails the script if any token/secret material is found in it.
Exits 0 on success. The spawned process's lifecycle is fully owned by the stdio_client async context manager — it's cleanly terminated on exit, no manual kill required.

Testing against a real Google account

The script uses a placeholder account ([email protected]), so the Google API calls will fail/be denied regardless of policy — that's expected and still exercises the full router → policy → adapter → audit path. To test against real data, edit ACCOUNT at the top of scripts/smoke_test.py to an already-onboarded real address (see README.md §2–3) for a local one-off run — don't commit a real account email into this shared script.

Read the full file on GitHub · 140 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/smoke_test.py 4.9 KB runs code

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 · 140 lines · 71 tokens per session scan A 85e5043b1776

Subscribe to this mod's changes

run-jb-gateway-mcp is a skill published in the GitHub repository jitheshb83/jb_gateway_mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,772 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

run-jb-gateway-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
run-jb-gateway-mcpjitheshb83/jb_gateway_mcp	Skill	0	3mo ago	MIT	A	71	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

jb_gateway_mcp: Skill for Claude Code