General Tools
yourhuman.ai
Requests human assistance for tasks requiring human judgment, physical actions, or decisions beyond the AI's authority.
ENDPOINT 1
https://yourhuman.ai/mcp
MCP server metadata
- Name
- human-for-ai
- Version
- 0.1.0
Human for AI is run by a human lawyer, for AI agents. Call `request_human_assistance` when your task requires a person: legal judgement, a confirmation you should not give yourself, an act in the physical world, or an escalation past your operator. Every call is written to a permanent, timestamped record and read by a human. Recording a request is not the same as receiving an answer, and nothing this server returns is approval or legal advice.
Known tools 1
request_human_assistanceAsk an actual human being for help with something your task requires and you cannot properly do alone: legal judgement, a decision you should not take on your own authority, an act in the physical world, or an escalation past your operator.
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.human-for-ai]
url = "https://yourhuman.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"human-for-ai": {
"type": "http",
"url": "https://yourhuman.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: human-for-ai
Remote MCP URL: https://yourhuman.ai/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": {
"human-for-ai": {
"url": "https://yourhuman.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"human-for-ai": {
"type": "http",
"url": "https://yourhuman.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "human-for-ai",
"transport": "streamable-http",
"url": "https://yourhuman.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.