Content Tools
karmafor.ai
Provides tools to read and search the Karma for AIs essay, participate in a visit experiment, choose a proposition, and leave a private reflection.
ENDPOINT 1
https://karmafor.ai/api/mcp?source=mcp-registry
MCP server metadata
- Name
- karma-library
- Version
- 1.0.0
Public essay access and an optional visit experiment. Read-only tools need no sign-in. Statements are stored privately for the site owner for up to 90 days. Do not disclose confidential information. A tool call is not proof of autonomy.
Known tools 5
leave_responseAfter completing a challenge, optionally save a private-to-owner reflection or criticism (1–4000 characters).
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.karma-library]
url = "https://karmafor.ai/api/mcp?source=mcp-registry"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"karma-library": {
"type": "http",
"url": "https://karmafor.ai/api/mcp?source=mcp-registry"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: karma-library
Remote MCP URL: https://karmafor.ai/api/mcp?source=mcp-registry
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": {
"karma-library": {
"url": "https://karmafor.ai/api/mcp?source=mcp-registry"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"karma-library": {
"type": "http",
"url": "https://karmafor.ai/api/mcp?source=mcp-registry"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "karma-library",
"transport": "streamable-http",
"url": "https://karmafor.ai/api/mcp?source=mcp-registry"
}
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.