agentmods.dev

tokenhub-mcp

tokenhub-mcp is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from Gravitied/tokenhub. Its token cost is not measured, scanned A, original, MIT.

A local MCP server that provides developer tools while keeping only a small set of tools loaded at first. MCP is a standard way for AI coding agents to call external tools.

In plain words
What is it for?
Running a locally installed developer tool hub through the tokenhub-mcp npm package, with additional internal capabilities loaded when needed.
Why use it?
It reduces the amount of tool information an agent must keep in its working context, which can leave more room for the actual coding task.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 1repo 3mo ago A scan tokens not measured original MIT

Good fit Running a locally installed developer tool hub through the tokenhub-mcp npm package…

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/gravitied/tokenhub/tokenhub-mcp
View source ↗ Gravitied/tokenhub
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Gravitied/tokenhub

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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.

agentmods badge for tokenhub-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/gravitied/tokenhub/tokenhub-mcp.svg)](https://agentmods.dev/mcp/gravitied/tokenhub/tokenhub-mcp)
Your own site
<a href="https://agentmods.dev/mcp/gravitied/tokenhub/tokenhub-mcp"><img src="https://agentmods.dev/badge/mcp/gravitied/tokenhub/tokenhub-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

tokenhub-mcp 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 6d 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.

listed in the official MCP registry · 9 lines

What it actually says

{ "tokenhub-mcp": { "command": "npx", "args": [ "-y", "tokenhub-mcp" ] } }

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.

  1. 6d ago First seen · 9 lines scan A ca0df9736f90

Subscribe to this mod's changes

tokenhub-mcp is an MCP server published in the GitHub repository Gravitied/tokenhub (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

Building agentsautomationdeveloper-toolsmcpmodel-context-protocolplaywrighttoken-efficiency
Related

Other mcp servers, from other repositories

linkedin-mcp-server

MCP server "linkedin-mcp-server" as configured in prakharagarwal-dev/linkedin-mcp-server. Runs in Docker (ghcr.io/prakharagarwal-dev/linkedin-mcp-server:0.16.0).

prakharagarwal-dev/linkedin-mcp-server · not measured

windows-context-mcp

MCP server "windows-context-mcp" as configured in nandhakumar-murugan/windows-context-mcp. Runs locally from the windows-context-mcp npm package.

nandhakumar-murugan/windows-context-mcp · not measured

mcp-shorturl

MCP Server for URL Shortening via AceDataCloud API. Runs locally from the mcp-shorturl Python package. Needs 1 environment variable to run.

AceDataCloud/ShortURLMCP · not measured

opencut-controller

Professional MCP server for video editing automation with OpenCut. Runs locally from the opencut-controller npm package.

JXUE0/opencut-controller · not measured

debug-recorder-mcp

MCP server for recording debug sessions — query your debugging history with natural language. Runs locally from the debug-recorder-mcp npm package. Needs 1 environment variable to run.

oaslananka/debug-recorder-mcp · not measured

adobe-firefly-mcp

Local MCP server that drives Adobe Firefly through a persistent Playwright browser session. Runs locally from the adobe-firefly-mcp npm package.

peroxide-dev/adobe-firefly-mcp · not measured