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/seedfast-ai/seedfast-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/seedfast-ai/seedfast-mcp/seedfast)<a href="https://agentmods.dev/mcp/seedfast-ai/seedfast-mcp/seedfast"><img src="https://agentmods.dev/badge/mcp/seedfast-ai/seedfast-mcp/seedfast/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/seedfast-ai/seedfast-mcp/seedfast"><img src="https://agentmods.dev/badge/mcp/seedfast-ai/seedfast-mcp/seedfast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
seedfast 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 8d 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
{
"seedfast": {
"command": "npx",
"args": [
"-y",
"seedfast@latest",
"mcp"
],
"env": {
"SEEDFAST_API_KEY": "sfk_live_your_api_key_here"
}
}
}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.
- 8d ago First seen · 13 lines scan A befaf721cf56
seedfast is an MCP server published in the GitHub repository seedfast-ai/seedfast-mcp (0 stars, last pushed 9d 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.
Other mcp servers, from other repositories
local-knowledge-rag
MCP server "local-knowledge-rag" as configured in patakuti/local-knowledge-rag-mcp. Runs /path/to/local-knowledge-rag-mcp/dist/mcp-server.js with node. Needs 3 environment variables to run.
pgmcp
MCP server "pgmcp" as configured in pascalallen/pgmcp. Runs in Docker (ghcr.io/pascalallen/pgmcp:1.1.0). Needs 1 environment variable to run.
safe-postgres-mcp
Safety-first, read-only PostgreSQL MCP server. Read-only isn't a regex — it's enforced by Postgres itself (READ ONLY transactions, statement timeouts, row caps). One npx command to give AI agents safe access to your database. Runs locally from the safe-postgres-mcp npm package.
postgresql-mcp-server
Model Context Protocol server for PostgreSQL database inspection and querying. Runs locally from the mdev-postgresql-mcp-server Python package. Needs 6 environment variables to run.
virtual-fs
PostgreSQL-backed virtual filesystem for agents: session isolation, shared stores, POSIX ops, RLS. Runs locally from the mcp-virtual-fs npm package. Needs 4 environment variables to run.
mcp-postgres
Model Context Protocol server for PostgreSQL database operations. Runs locally from the mcp-postgres npm package.