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/sepehrbayat/SEPCCWrote 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/sepehrbayat/sepcc/token-savior)<a href="https://agentmods.dev/mcp/sepehrbayat/sepcc/token-savior"><img src="https://agentmods.dev/badge/mcp/sepehrbayat/sepcc/token-savior/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/sepehrbayat/sepcc/token-savior"><img src="https://agentmods.dev/badge/mcp/sepehrbayat/sepcc/token-savior.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
token-savior 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 1mo 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
{
"token-savior": {
"args": [
"--from",
"token-savior-recall==4.4.1",
"token-savior",
"server"
],
"command": "uvx",
"env": {
"TOKEN_SAVIOR_CLIENT": "claude-code",
"TOKEN_SAVIOR_PROFILE": "optimized",
"WORKSPACE_ROOTS": "${CLAUDE_PROJECT_DIR:-.}"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 1mo ago First seen · 16 lines scan A 45ee38d74871
token-savior is an MCP server published in the GitHub repository sepehrbayat/SEPCC (43 stars, last pushed 2mo 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
AWSBedrock
MCP server "AWSBedrock" as configured in spacehendrix/clauder. Runs locally from the awslabs.bedrock-kb-retrieval-mcp-server@latest Python package. Needs 4 environment variables to run.
CloudflareAutoRag
MCP server "CloudflareAutoRag", hosted remotely at autorag.mcp.cloudflare.com, as configured in spacehendrix/clauder.
Pinecone
Model Context Protocol server for Pinecone - enables AI assistants to interact with Pinecone indexes and documentation. Runs locally from the @pinecone-database/mcp npm package. Needs 1 environment variable to run.
rag-rat
CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence. Runs locally from the @rag-rat/bin npm package.
context-engine
Task-aware context compression for logs, RAG, and coding workflows. Runs locally from the melonelish-context-engine Python package.
inspeximus
MCP server "inspeximus", hosted remotely at pypi.org, as configured in DanceNitra/inspeximus. Needs 1 environment variable to run.