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/nebelov/yandex-direct-for-allWrote 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/nebelov/yandex-direct-for-all/yandex-direct-for-all-yandexsearch)<a href="https://agentmods.dev/mcp/nebelov/yandex-direct-for-all/yandex-direct-for-all-yandexsearch"><img src="https://agentmods.dev/badge/mcp/nebelov/yandex-direct-for-all/yandex-direct-for-all-yandexsearch/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/nebelov/yandex-direct-for-all/yandex-direct-for-all-yandexsearch"><img src="https://agentmods.dev/badge/mcp/nebelov/yandex-direct-for-all/yandex-direct-for-all-yandexsearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
yandexSearch 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 12d 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
{
"yandexSearch": {
"command": "uv",
"args": [
"run",
"--frozen",
"--project",
"./mcp/yandex-search",
"python",
"./mcp/yandex-search/server.py"
],
"env": {
"YANDEX_SEARCH_API_KEY": "${YANDEX_SEARCH_API_KEY}",
"YANDEX_SEARCH_FOLDER_ID": "${YANDEX_SEARCH_FOLDER_ID}",
"YANDEX_SEARCH_ROUTE": "${YANDEX_SEARCH_ROUTE}",
"YANDEX_SEARCH_APPROVAL_FILE": "${YANDEX_SEARCH_APPROVAL_FILE}",
"YANDEX_SEARCH_USAGE_LEDGER": "${YANDEX_SEARCH_USAGE_LEDGER}"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 3. 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.
- 12d ago First seen · 20 lines scan A 65f0ccbedb1a
yandexSearch is an MCP server published in the GitHub repository nebelov/yandex-direct-for-all (21 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 2026-08-30.
Other mcp servers, from other repositories
grok-build
MCP server "grok-build" as configured in Reederey87/grok-build-codex-plugin. Launched with /bin/sh ${PLUGIN_ROOT}/mcp-server/bin/grok-build-mcp. Needs 1 environment variable to run.
woven
MCP server "woven" as configured in Ducksss/LifeHack-2026. Runs ./node_modules/tsx/dist/cli.mjs with node. Needs 2 environment variables to run.
omnimodal-generation
MCP server "omnimodal-generation" as configured in good-boy4069/Deepseek-omnimodal. Runs locally from the . Python package.
guarded-notes-mcp
MCP server "guarded-notes-mcp" as configured in nextgencods/guarded-notes-mcp. Runs ./server.mjs with node.
cyberhuatuo
AI-agent self-rescue via MCP: diagnose tracebacks, apply exact fixes, and save/upload reusable prescriptions. Runs locally from the cyberhuatuo Python package.
govreposcrape
MCP server "govreposcrape", hosted remotely at govreposcrape-api-1060386346356.us-central1.run.app, as configured in tractorjuice/arckit-codex.