AI & Machine Learning
ioswarm.io
Manages AI-powered swarm runs that classify requests, launch multi-agent web research, and retrieve cited reports.
ENDPOINT 1
https://ioswarm.io/mcp
MCP server metadata
- Name
- swarmio
- Version
- 0.1.0
Hosted research swarm. launch_run starts a swarm job and bills the caller's credits; poll get_run until status is completed, then get_report. route_prompt classifies a request into the right mode first — it is never charged. get_balance reads your credit balance. No key yet? Onboard with no human per https://ioswarm.io/llms.txt — starter credits land automatically.
Known tools 8
route_promptClassify a freeform request into the right swarm mode (research, news, finance, astrology, …) before spending a run.
Inferred read-onlylaunch_runLaunch a swarm run: a team of agents searches the web, reads sources, and writes a cited report.
Inferred read-onlyget_reportThe finished, cited report for a completed run (report_text is markdown).
Inferred read-onlyget_topup_termsHow to refill credits machine-to-machine: USDC on Base to a published address, verified on-chain.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.swarmio]
url = "https://ioswarm.io/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"swarmio": {
"type": "http",
"url": "https://ioswarm.io/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: swarmio
Remote MCP URL: https://ioswarm.io/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"swarmio": {
"url": "https://ioswarm.io/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"swarmio": {
"type": "http",
"url": "https://ioswarm.io/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "swarmio",
"transport": "streamable-http",
"url": "https://ioswarm.io/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for ioswarm.io was fetched 2026-09-01T19:54:43.858Z.
ioswarm.io is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.