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/openhonest/umbraWrote 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/openhonest/umbra/umbra-codex-umbra)<a href="https://agentmods.dev/mcp/openhonest/umbra/umbra-codex-umbra"><img src="https://agentmods.dev/badge/mcp/openhonest/umbra/umbra-codex-umbra/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/openhonest/umbra/umbra-codex-umbra"><img src="https://agentmods.dev/badge/mcp/openhonest/umbra/umbra-codex-umbra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
umbra 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 2mo 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
{
"umbra": {
"command": "uv",
"args": [
"run",
"--project",
"./pyproject.toml",
"python",
"./server.py"
],
"cwd": "."
}
}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.
- 2mo ago First seen · 13 lines scan A 094a514a10ee
umbra is an MCP server published in the GitHub repository openhonest/umbra (3 stars, last pushed 2mo ago), licensed Apache-2.0. 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
cejel
MCP server "cejel" as configured in BargLabs/cejel. Runs in Docker (ghcr.io/barglabs/cejel@sha256:12372dededed8fbdbe6d1061e6792e3d83e51d0640899dfbc1f8189f8ea67daa).
cejel
Offline trust certificate for your codebase — scores tests, secrets, isolation, claim-vs-reality, and CI discipline; especially useful for AI-written code. Supports JS/TS, Python, Go, Rust, Java, Ruby, PHP, C#, C/C++ and more — see README for the full lan. Runs locally from the @cejel/cejel npm package.
github
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.
vacuous-tests-mcp
MCP server "vacuous-tests-mcp" as configured in zegroged/vacuous-tests-mcp. Runs locally from the vacuous-tests-mcp Python package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
component-explorer
MCP server "component-explorer" as configured in microsoft/vscode. Launched with npm exec --no -- component-explorer mcp -p ./test/componentFixtures/component-ex.