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/tifa365/berlin-opendata-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/tifa365/berlin-opendata-mcp/berlin-opendata)<a href="https://agentmods.dev/mcp/tifa365/berlin-opendata-mcp/berlin-opendata"><img src="https://agentmods.dev/badge/mcp/tifa365/berlin-opendata-mcp/berlin-opendata/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/tifa365/berlin-opendata-mcp/berlin-opendata"><img src="https://agentmods.dev/badge/mcp/tifa365/berlin-opendata-mcp/berlin-opendata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
berlin-opendata 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 12d 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
{
"berlin-opendata": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/berlin-opendata-mcp",
"run",
"berlin-opendata-mcp"
],
"env": {}
}
}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.
- 12d ago First seen · 12 lines scan A 3a02c9e014d0
berlin-opendata is an MCP server published in the GitHub repository tifa365/berlin-opendata-mcp (5 stars, last pushed 6mo 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
ckan-mcp-server
MCP server for interacting with CKAN open data portals. Runs locally from the @aborruso/ckan-mcp-server npm package.
norwegian-data-mcp
Norwegian public data (companies, statistics, addresses) as MCP tools. No API keys. Runs locally from the norwegian-data-mcp Python package.
world-bank-indicators-mcp
MCP server "world-bank-indicators-mcp" as configured in ryanngit/world-bank-indicators-mcp. Runs locally from the world-bank-indicators-mcp npm package.
datos.gob.do-MCP-server
MCP server for datos.gob.do — Dominican Republic open government data portal (CKAN 2.11). Runs locally from the dominican-open-data-mcp Python package.
tdcc
MCP server "tdcc" as configured in asgard-ai-platform/mcp-tdcc. Runs mcp_server.py with python. Needs 1 environment variable to run.
datagovma-mcp
MCP server "datagovma-mcp" as configured in mohtamimad/datagovma-mcp. Runs locally from the datagovma-mcp Python package.