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/aslanpour/mcp-switchboardWrote 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/aslanpour/mcp-switchboard/mcp-switchboard)<a href="https://agentmods.dev/mcp/aslanpour/mcp-switchboard/mcp-switchboard"><img src="https://agentmods.dev/badge/mcp/aslanpour/mcp-switchboard/mcp-switchboard.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
mcp-switchboard 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
{ "mcp-switchboard": { "command": "uvx", "args": [ "mcp-switchboard" ] } }
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 · 8 lines scan A d4db701e8442
mcp-switchboard is an MCP server published in the GitHub repository aslanpour/mcp-switchboard (0 stars, last pushed 8mo 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
fast-mcp-telegram
Multi-tenant Telegram gateway for AI agents — HTTP+stdio transport, 8 agent-optimized tools, MTProto User API. Runs locally from the fast-mcp-telegram Python package. Needs 4 environment variables to run.
n8n-pro-mcp
Manage self-hosted n8n (incl. queue mode): workflows, executions, users, audit — 51 tools. Runs locally from the n8n-pro-mcp npm package. Needs 3 environment variables to run.
multi-select-reorder-mcp
MCP server "multi-select-reorder-mcp", hosted remotely at 127.0.0.1, as configured in dhruv-anand-aintech/agent-rules-sync.
postforme-mcp-pro
Publish, schedule and analyze social posts across 9 platforms via the Post for Me API. Runs locally from the postforme-mcp-pro npm package. Needs 2 environment variables to run.
graphify
MCP server "graphify" as configured in bintangtimurlangit/threads-mcp. Launched with graphify-mcp graphify-out/graph.json --transport stdio.
threads
MCP server "threads" as configured in bintangtimurlangit/threads-mcp. Runs build/index.js with node.