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.
git clone --depth 1 https://github.com/weijiafu14/pi2dshWrote 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/mcp/weijiafu14/pi2dsh/mcp-at-scale-many-tools)<a href="https://agentmods.dev/mcp/weijiafu14/pi2dsh/mcp-at-scale-many-tools"><img src="https://agentmods.dev/badge/mcp/weijiafu14/pi2dsh/mcp-at-scale-many-tools/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/mcp/weijiafu14/pi2dsh/mcp-at-scale-many-tools"><img src="https://agentmods.dev/badge/mcp/weijiafu14/pi2dsh/mcp-at-scale-many-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
many-tools 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 11d 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
{
"many-tools": {
"command": "node",
"args": [
"server/many-tools.mjs"
]
}
}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.
- 11d ago First seen · 8 lines scan A 03d8f2e1536a
many-tools is an MCP server published in the GitHub repository weijiafu14/pi2dsh (186 stars, last pushed 11d 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 2026-08-30.
Other mcp servers, from other repositories
dsh-web-search-free
A locally run web-search provider that can be connected to coding agents such as Claude Code and Codex. It supports a free search option, a paid search option, and two ways for software to connect to it.
url-manager-mcp
URL Manager MCP Server — Agent-first web link collection & knowledge management. Runs locally from the url-manager-mcp Python package. Needs 2 environment variables to run.
deepseek-harness-plugin-mcp
MCP server "deepseek-harness-plugin-mcp" as configured in bobleer/deepseek-harness-plugin-mcp. Runs locally from the deepseek-harness-plugin-mcp npm package.
gpt-dsh-bridge
MCP server "gpt-dsh-bridge" as configured in baochaofan0404/gpt-dsh-bridge. Runs locally from the gpt-dsh-bridge npm package.
dsh-safety
MCP server "dsh-safety" as configured in easygame921/dsh-safety. Runs locally from the dsh-safety npm package.
dsh-kanban-mcp
Filesystem-driven four-lane kanban board (todo / doing / blocked / done) exposed as a read-only MCP server and a Python API. Works with DeepSeek Harness and any MCP client. Runs locally from the dsh-kanban-mcp Python package.