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/ThoTischner/observability-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/thotischner/observability-mcp/observability)<a href="https://agentmods.dev/mcp/thotischner/observability-mcp/observability"><img src="https://agentmods.dev/badge/mcp/thotischner/observability-mcp/observability/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/thotischner/observability-mcp/observability"><img src="https://agentmods.dev/badge/mcp/thotischner/observability-mcp/observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
observability 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.
This is a copy
80% identical to drawio — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"observability": {
"type": "http",
"url": "http://localhost:3000/mcp"
}
}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 ee2bb3a24aa3
observability is an MCP server published in the GitHub repository ThoTischner/observability-mcp (7 stars, last pushed 3d 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. It is 80% identical to drawio, differing in 2 lines, and is treated as a copy.
Other mcp servers, from other repositories
aisix
MCP server "aisix" as configured in api7/aisix. Runs in Docker (ghcr.io/api7/aisix:1.3.0).
mcp-gtw
A generic MCP gateway whose tools are registered and executed asynchronously by browser applications over WebSocket. Runs locally from the mcp-gtw Python package.
mcp-gateway
MCP server "mcp-gateway" as configured in MikkoParkkola/mcp-gateway. Runs in Docker (ghcr.io/mikkoparkkola/mcp-gateway:3.5.1).
codex
MCP server "codex" as configured in SSC-STUDIO/Ai-Model-Gateway. Launched with codex mcp-server. Needs 1 environment variable to run.
memocall
Recall past Claude Code conversations from any project as clean, compact Markdown. Runs locally from the memocall npm package.
mcp-bash-server
MCP server "mcp-bash-server" as configured in uditk2/mcp-bash-server. Runs locally from the mcp-bash-server Python package.