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/shrimansoft/tpu-managerWrote 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/shrimansoft/tpu-manager/tpu-manager)<a href="https://agentmods.dev/mcp/shrimansoft/tpu-manager/tpu-manager"><img src="https://agentmods.dev/badge/mcp/shrimansoft/tpu-manager/tpu-manager.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
tpu-manager 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 7d 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
{ "tpu-manager": { "command": "uvx", "args": [ "tpu-manager" ] } }
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.
- 7d ago First seen · 8 lines scan A f6f35bf8139b
tpu-manager is an MCP server published in the GitHub repository shrimansoft/tpu-manager (0 stars, last pushed 1mo 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.
Other mcp servers, from other repositories
inferbench
Vendor-neutral local-LLM-inference benchmark and hardware-config advisor for omlx and llama.cpp -- measures real tokens/second on your own hardware, live. Runs locally from the inferbench-cli Python package.
vhdl-rag-mcp
MCP server "vhdl-rag-mcp" as configured in ru551n/vhdl-rag-mcp. Runs locally from the vhdl-rag-mcp Python package.
rag-mcp
Minimal, honest RAG-over-a-corpus MCP retrieval tool: searchknowledge(query, k) -> cited chunks. Local embeddings + embedded vector store. Auth-scoped, fail-soft, version-pinned. Runs locally from the jaimenbell-rag-mcp Python package.
intel-npu-tools
MCP server "intel-npu-tools" as configured in etreby/intel-npu-tools. Runs locally from the intel-npu-tools Python package.
forge-mcp
Cross-OEM industrial machine intelligence: identity, normalization, automation, attestation. Remote server at foundrynet-mcp-production.up.railway.app.
xilinx-rag
MCP server "xilinx-rag" as configured in Can-Y/docsearch. Runs locally from the xilinx-rag Python package.