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/sanity-io/agent-toolkitWrote 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/sanity-io/agent-toolkit/sanity)<a href="https://agentmods.dev/mcp/sanity-io/agent-toolkit/sanity"><img src="https://agentmods.dev/badge/mcp/sanity-io/agent-toolkit/sanity/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/sanity-io/agent-toolkit/sanity"><img src="https://agentmods.dev/badge/mcp/sanity-io/agent-toolkit/sanity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
Sanity 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
{
"Sanity": {
"type": "http",
"url": "https://mcp.sanity.io"
}
}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 · 6 lines scan A 910eb3ffd9ec
Sanity is an MCP server published in the GitHub repository sanity-io/agent-toolkit (192 stars, last pushed today), 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
fast-mcp-telegram
Multi-tenant Telegram gateway for AI agents — HTTP+stdio transport, 8 agent-optimized tools, MTProto User API. Runs locally from the fast-mcp-telegram Python package. Needs 4 environment variables to run.
nodejs-api-docs
An MCP Server for Node.js API documentation. Runs locally from the mcp-server-nodejs-api-docs npm package.
telegram-dev
MCP server "telegram-dev" as configured in leshchenko1979/fast-mcp-telegram. Runs src.server with python3.
kafka-schema-registry
MCP server "kafka-schema-registry" as configured in aywengo/kafka-schema-reg-mcp. Runs kafka_schema_registry_unified_mcp.py with python. Needs 3 environment variables to run.
stitchapi-docs
StitchAPI documentation search, running locally over MCP stdio. Bundled docs, no network calls per query — the offline/air-gapped counterpart to the hosted stitchapi.dev/api/mcp server. Runs locally from the @stitchapi/docs-mcp npm package.
shipmail-mcp
Shipmail MCP server for AI agent custom-domain email inboxes with REST API and webhooks. Runs locally from the shipmail-mcp npm package. Needs 1 environment variable to run.