add-mcp

A command for adding an MCP server to an Agency Swarm agent. MCP, or Model Context Protocol, is a standard way for an agent to connect to outside tools and data.

In plain words
What is it for?
Connecting an Agency Swarm agent to an external MCP server from a URL, repository, local path, or command-line tool.
Why use it?
It helps choose the right connection method for hosted services, streaming servers, OAuth services, local scripts, and command-line tools.

Command for Cursor

Install

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.

agentmods
npx agentmods add commands/vrsen/openswarm/add-mcp
Clone the repo
git clone --depth 1 https://github.com/VRSEN/OpenSwarm

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04691
Opus 5 $0.00000 $0.02346
Sonnet 5 $0.00000 $0.00938
Haiku 4.5 $0.00000 $0.00469

Measured yesterday against content hash 1755d2188e6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-mcp 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • add-mcp — 89% identical, 3 lines differ
.cursor/commands/add-mcp.md · 629 lines

How it starts

The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Creation Task

Your task is to add Model Context Protocol (MCP) server to an Agency Swarm agent. MCP servers expose external tools and data sources to agents through a standardized protocol.


Quick Reference: MCP Server Types

Server Type When to Use URL Pattern Class to Use
Hosted Remote Publicly accessible web service Any public URL HostedMCPTool
Hosted Remote (OAuth) Publicly accessible web service with OAuth Any public URL MCPServerStdio + mcp-remote
Streamable HTTP HTTP streaming server Ends in /mcp MCPServerStreamableHttp
SSE Server-Sent Events server Ends in /sse MCPServerSse
Local/Stdio GitHub repo, local script, or CLI tool GitHub URL or local path MCPServerStdio

Step-by-Step Process

Step 1: Determine Server Type

If user provides a URL:

  • Check if it's a public/internet-accessible URL:
    • Requires OAuth authentication? → Use mcp-remote with MCPServerStdio
    • No authentication or token-based auth? → Use HostedMCPTool
  • Check if URL ends with /mcp → Use MCPServerStreamableHttp (or HostedMCPTool if public)
  • Check if URL ends with /sse → Use MCPServerSse (or HostedMCPTool if public)

If user provides a GitHub URL or mentions "local":

  • Use MCPServerStdio

If unclear, ask:

  1. Is this a publicly accessible URL? (HostedMCPTool or mcp-remote)
  2. Does it require OAuth authentication? (Use mcp-remote)
  3. Is this a local server you'll run? (MCPServerStdio, MCPServerSse, or MCPServerStreamableHttp)
  4. What's the server endpoint URL? (check /mcp or /sse suffix)
  5. Which agent do you want to add this MCP server to?

Read the full file on GitHub · 629 lines

Changes

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.

  1. yesterday First seen · 629 lines · 0 tokens per session scan A 1755d2188e6b

Subscribe to this mod's changes

add-mcp is a command published in the GitHub repository VRSEN/OpenSwarm (2,856 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,691 tokens. 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.