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/akougkas/zulipchat-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/akougkas/zulipchat-mcp/claude-code-zulipchat)<a href="https://agentmods.dev/mcp/akougkas/zulipchat-mcp/claude-code-zulipchat"><img src="https://agentmods.dev/badge/mcp/akougkas/zulipchat-mcp/claude-code-zulipchat/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/akougkas/zulipchat-mcp/claude-code-zulipchat"><img src="https://agentmods.dev/badge/mcp/akougkas/zulipchat-mcp/claude-code-zulipchat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
zulipchat 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 6d 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
{
"zulipchat": {
"type": "stdio",
"command": "uvx",
"args": [
"zulipchat-mcp",
"--zulip-config-file",
"/absolute/path/to/.zuliprc",
"--extended-tools"
]
}
}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.
- 6d ago First seen · 12 lines scan A 0af45f3b95b0
zulipchat is an MCP server published in the GitHub repository akougkas/zulipchat-mcp (32 stars, last pushed 6d 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 2026-10-10.
Other mcp servers, from other repositories
microsoft-planner-mcp
MCP server "microsoft-planner-mcp", hosted remotely at localhost, as configured in aixolotl/microsoft-planner-mcp.
uspto-enriched-citation-mcp
MCP server "uspto-enriched-citation-mcp" as configured in john-walkoe/usptoenrichedcitationmcp. Runs locally from the uspto-enriched-citation-mcp Python package.
fpd-mcp
MCP server "fpd-mcp" as configured in Tam1379/usptofpdmcp. Runs locally from the fpd-mcp Python package.
openproject-mcp-server
MCP server for OpenProject: 89 tools for work packages, attachments, git activity, time tracking, meetings and reporting over the API v3. Runs locally from the openproject-mcp-server Python package. Needs 5 environment variables to run.
plane-workflow
MCP server "plane-workflow" as configured in amirhosseinkz/plane-workflow-mcp. Runs locally from the plane-workflow Python package.
mcp-jira-scoped
Jira MCP server with scoped API tokens via api.atlassian.com gateway. Runs locally from the mcp-jira-scoped npm package. Needs 5 environment variables to run.