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.
npx agentmods add mcp/prelearn-code/deepseek-mcp/codex-deepseek-workergit clone --depth 1 https://github.com/prelearn-code/deepseek-mcpGrade A, and why
codex-deepseek-worker 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 yesterday.
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
{ "codex-deepseek-worker": { "command": "uvx", "args": [ "codex-deepseek-worker" ] } }
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.
- yesterday First seen · 8 lines scan A c83f399fa24f
codex-deepseek-worker is an MCP server published in the GitHub repository prelearn-code/deepseek-mcp (0 stars, last pushed 26d 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
codex-timicc-worker
MCP server "codex-timicc-worker" as configured in prelearn-code/timicc-mcp. Runs locally from the codex-timicc-worker Python package.
ip-as-logo
MCP server "ip-as-logo", hosted remotely at peri-mcpp-gateway.claude-code-best.workers.dev, as configured in KonghaYao/peri.
wireshark
MCP server "wireshark" as configured in khuynh22/mcp-wireshark. Launched with mcp-wireshark.
schemabrain
The trust and intelligence layer between AI agents and your database. Runs locally from the schemabrain Python package. Needs 1 environment variable to run.
chainweaver
Deterministic orchestration layer for MCP-based agents. Runs locally from the chainweaver Python package.
agent-audit
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot. Runs locally from the @fullstackdegen/agent-audit npm package.