AI & Machine Learning
bies.io
Evaluates and re-evaluates claims and business ideas for safety and validity.
ENDPOINT 1
https://bies.io/mcp
MCP server metadata
- Name
- bies
- Version
- 1.0.0
BIES returns a deterministic, sealed verdict on public claims. Call claim_safety_verdict before publishing marketing/product/ad copy to check whether each claim is safe to publish. Read-only; input is not stored; same copy + market + surface + ruleset -> same replay_hash.
Known tools 3
claim_safety_verdictDeterministic, sealed pre-publication verdict on a PUBLIC claim (marketing copy, product page, ad headline).
Inferred read-onlyidea_rehearsalDeterministic decision-rehearsal verdict on a founder's BUSINESS IDEA (not a public claim).
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.bies]
url = "https://bies.io/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"bies": {
"type": "http",
"url": "https://bies.io/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: bies
Remote MCP URL: https://bies.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": {
"bies": {
"url": "https://bies.io/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"bies": {
"type": "http",
"url": "https://bies.io/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "bies",
"transport": "streamable-http",
"url": "https://bies.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 bies.io was fetched 2026-07-26T06:49:43.027Z and is being refreshed.
bies.io is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.