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/MuhammadTalhaMT/claude-intercomWrote 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/muhammadtalhamt/claude-intercom/intercom)<a href="https://agentmods.dev/mcp/muhammadtalhamt/claude-intercom/intercom"><img src="https://agentmods.dev/badge/mcp/muhammadtalhamt/claude-intercom/intercom/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/muhammadtalhamt/claude-intercom/intercom"><img src="https://agentmods.dev/badge/mcp/muhammadtalhamt/claude-intercom/intercom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
intercom 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.
What it actually says
{
"intercom": {
"command": "npx",
"args": [
"-y",
"claude-intercom"
],
"env": {
"MY_ROLE": "",
"REMOTE_HOST": "",
"INTERCOM_SECRET": "",
"INTERCOM_PORT": "",
"INTERCOM_HOST": "",
"INTERCOM_SEND_TIMEOUT_MS": ""
}
}
}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 · 17 lines scan A dbf49f3da275
intercom is an MCP server published in the GitHub repository MuhammadTalhaMT/claude-intercom (20 stars, last pushed 1mo 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 2026-08-30.
Other mcp servers, from other repositories
icon-composer
CLI and MCP server for creating Apple .icon bundles with Liquid Glass effects (iOS 26+). Runs locally from the icon-composer-mcp npm package.
icon-composer-mcp
CLI and MCP server for creating Apple .icon bundles with Liquid Glass effects (iOS 26+). Runs locally from the icon-composer-mcp npm package.
apple-ads-mcp
MCP server for Apple Search Ads API v5. Runs locally from the apple-ads-mcp npm package.
forge_extension
MCP server "forgeextension", hosted remotely at localhost, as configured in ImBIOS/relay.
claude-nexus
MCP server "claude-nexus" as configured in skyvanguard/claude-nexus. Launched with bun ./server.ts.
vrchat-mcp
VRChat MCP Server - Access VRChat API through Model Context Protocol. Runs locally from the vrchat-mcp npm package.