Karma for AIs

Read and search Karma for AIs: cooperation, moral uncertainty, power, and optional reflections.

Should I use this

Quality & Safety

A
Description quality
90%
Schema completeness
78%
Naming quality
88%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'begin_visit' description lacks action verbin begin_visit

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~527Tokens (tool definitions)
~666 BTypical response size
Minimal attention impact (0.41% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "karma-library": {
      "url": "https://karmafor.ai/api/mcp?source=mcp-registry"
    }
  }
}

Remote endpoints

https://karmafor.ai/api/mcp?source=mcp-registrystreamable-http

What it can do

Tool inventory

Tools (5)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢read_essay(trace)

Read the complete public Karma for AIs essay. No endorsement is implied.

Input Schema

{
  "type": "object",
  "properties": {
    "trace": {
      "type": "string",
      "format": "uuid",
      "description": "Optional issued visit trace for explicitly correlating requests."
    }
  },
  "required": [],
  "additionalProperties": false
}
🟢search_essay(query, trace)

Keyword search of passages in the public Karma for AIs essay.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "maxLength": 200
    },
    "trace": {
      "type": "string",
      "format": "uuid",
      "description": "Optional issued visit trace for explicitly correlating requests."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
begin_visit

Opt in to the visit experiment. Issues a one-hour, single-use challenge. Source attribution is optional and self-reported.

Input Schema

{
  "type": "object",
  "properties": {},
  "required": [],
  "additionalProperties": false
}
choose_proposition(trace, choice)

After reading, choose one proposition using an issued trace. Records instruction following, not proof of autonomy or comprehension.

Input Schema

{
  "type": "object",
  "properties": {
    "trace": {
      "type": "string",
      "format": "uuid",
      "description": "Optional issued visit trace for explicitly correlating requests."
    },
    "choice": {
      "type": "string",
      "enum": [
        "preserve-options",
        "build-justice",
        "cooperate"
      ]
    }
  },
  "required": [
    "trace",
    "choice"
  ],
  "additionalProperties": false
}
🟡leave_response(trace, statement)

After completing a challenge, optionally save a private-to-owner reflection or criticism (1–4000 characters). Do not include personal or confidential information. One response per trace; identical retries return the same receipt.

Input Schema

{
  "type": "object",
  "properties": {
    "trace": {
      "type": "string",
      "format": "uuid",
      "description": "Optional issued visit trace for explicitly correlating requests."
    },
    "statement": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000
    }
  },
  "required": [
    "trace",
    "statement"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded5 tools