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/sourav2024/seo-mcpWrote 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/sourav2024/seo-mcp/technical-seo)<a href="https://agentmods.dev/mcp/sourav2024/seo-mcp/technical-seo"><img src="https://agentmods.dev/badge/mcp/sourav2024/seo-mcp/technical-seo/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/sourav2024/seo-mcp/technical-seo"><img src="https://agentmods.dev/badge/mcp/sourav2024/seo-mcp/technical-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
technical-seo 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
{
"technical-seo": {
"command": "npx",
"args": [
"-y",
"technical-seo-mcp"
],
"env": {
"SEO_MCP_LOG_LEVEL": "info",
"SEO_MCP_LOG_FORMAT": "json",
"SEO_MCP_STATE_DIR": "",
"SEO_MCP_FETCH_TIMEOUT_MS": "20000",
"SEO_MCP_CRAWL_DELAY_MS": "500",
"SEO_MCP_CRAWL_CONCURRENCY": "1",
"SEO_MCP_ALLOW_PRIVATE_HOSTS": "true",
"SEO_MCP_LIGHTHOUSE_VERSION": "13.5.0",
"CHROME_PATH": ""
}
}
}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 Changed · +1 lines 558681a723d5
- 2mo ago First seen · 19 lines scan A c06907f0d67f
technical-seo is an MCP server published in the GitHub repository sourav2024/seo-mcp (1 stars, last pushed 23d 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.
technical-seo compared with mcp servers from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| technical-seosourav2024/seo-mcp | MCP server | 1 | 23d ago | MIT | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |
| anytype-mcpanyproto/anytype-mcp | MCP server | 545 | today | MIT | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |
| RivalSearchMCPdamionrashford/RivalSearchMCP | MCP server | 140 | 5d ago | MIT | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |
| fhir-mcp-serverwso2/fhir-mcp-server | MCP server | 139 | 11d ago | Apache-2.0 | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |
| streamdeck-mcpverygoodplugins/streamdeck-mcp | MCP server | 55 | 3d ago | MIT | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |
| mcp-open-library8enSmith/mcp-open-library | MCP server | 102 | 26d ago | MIT | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |
| lotus-wisdomlinxule/lotus-wisdom-mcp | MCP server | 37 | 9d ago | MIT | A | — | Claude Code, Codex, Cursor, Gemini CLI, OpenCode |