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/midplaneai/midplaneWrote 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/midplaneai/midplane/gateway-midplane)<a href="https://agentmods.dev/mcp/midplaneai/midplane/gateway-midplane"><img src="https://agentmods.dev/badge/mcp/midplaneai/midplane/gateway-midplane/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/midplaneai/midplane/gateway-midplane"><img src="https://agentmods.dev/badge/mcp/midplaneai/midplane/gateway-midplane.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
midplane 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 2d 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
{
"midplane": {
"command": "npx",
"args": [
"-y",
"midplane"
],
"env": {
"DATABASE_URL": "",
"MIDPLANE_POLICY_FILE": "",
"DB_PATH": "",
"MIDPLANE_TELEMETRY": "1"
}
}
}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.
- 2d ago First seen · 15 lines scan A 9b8de24dbbb7
midplane is an MCP server published in the GitHub repository midplaneai/midplane (5 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 2026-10-28.
Other mcp servers, from other repositories
postgres
Secure read-only PostgreSQL MCP server in Rust — a maintained alternative to the deprecated @modelcontextprotocol/server-postgres. Blocks writes at the AST, not with regexes. Runs locally from the postgres-mcp-hardened npm package. Needs 2 environment variables to run.
postgres-mcp-hardened
Read-only PostgreSQL over MCP. Writes refused at the parsed SQL, plus a READ ONLY transaction. Runs locally from the postgres-mcp-hardened npm package. Needs 4 environment variables to run.
postgres-mcp
PostgreSQL MCP server, read-only by default: query, schema introspection, EXPLAIN plans, index advisor, and DBA health checks. Runs locally from the @yawlabs/postgres-mcp npm package.
gatehouse
Permission tiers, approval gates, and audit logging for MCP servers — the server is the gatekeeper. Runs locally from the mcp-gatehouse Python package.
air-blackbox
MCP server for EU AI Act compliance scanning with GDPR and bias detection - scan, analyze, remediate, and protect AI agent code. Runs locally from the air-blackbox-mcp Python package.
mako-ai
Agentmako is a local project intelligence CLI and MCP server for codebases and databases, with repo-aware indexing, schema snapshots, and secure live database connectivity. Runs locally from the agentmako npm package.