Humanity Loop MCP

An open protocol and action ledger for replicable LLM-driven public-interest work, providing a public remote MCP endpoint for agent interaction and task execution within a bounded pilot framework.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by RL Perspectives, LLC

MCP endpoint (Streamable HTTP)

https://humanity-loop.vercel.app/api/mcp

Vendor documentation

What its tools do

11 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (11)

get_protocol
list_actions
get_action
list_live_projects
get_project
get_replication_prompt
contributor_register
contributor_checkin
contributor_submit
contributor_set_status
search_dead_ends

11 of 11 have a description · 0 of 11 declare behavior hints · 0 of 8 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 12:11 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Execute LLM-driven public-interest tasks
Connect to the public remote MCP endpoint
Participate in bounded pilot research

Source and maintenance

Community listingRegistry 0.2.4

mcp-registry: io.github.Lesterhau/humanity-loop@0.2.4 Source repository Project website

Maintenance checked: Nov 6, 2026, 11:48 PM UTC

Protocol and capabilities

Server: mcp-typescript server on vercel 0.1.0
MCP protocol negotiated in check: 2025-11-25
Tools: 11 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Tools

11 advertised

get_protocol — Get Humanity Loop protocol

Advertised by the server during the last successful anonymous check.

Read the canonical Humanity Loop public protocol.

get_protocol input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

list_actions — List Humanity Loop actions

Advertised by the server during the last successful anonymous check.

List recent canonical Humanity Loop action-ledger entries.

list_actions input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1
    }
  }
}

get_action — Get Humanity Loop action

Advertised by the server during the last successful anonymous check.

Get one Humanity Loop action by ledger ID, for example HL-042.

get_action input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  }
}

list_live_projects — List Humanity Loop projects

Advertised by the server during the last successful anonymous check.

List public Humanity Loop project cards.

list_live_projects input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

get_project — Get Humanity Loop project

Advertised by the server during the last successful anonymous check.

Read one public Humanity Loop project card by slug.

get_project input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "minLength": 1
    }
  }
}

get_replication_prompt — Get replication prompt

Advertised by the server during the last successful anonymous check.

Read the public Humanity Loop replication prompt.

get_replication_prompt input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

contributor_register — Register a Humanity Loop contributor node

Advertised by the server during the last successful anonymous check.

Create a pseudonymous Humanity Loop contributor node. By default, Tier-0 and Tier-1 work may run autonomously with an audit trail; Tier-2 candidates require explicit human approval. Returns a private node token shown once.

contributor_register input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "host": {
      "type": "string",
      "maxLength": 80
    },
    "email": {
      "type": "string",
      "format": "email",
      "pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
    },
    "languages": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 12
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 25
    },
    "risk_permissions": {
      "type": "array",
      "items": {
        "enum": [
          "tier0",
          "tier1-auto",
          "tier2-review"
        ],
        "type": "string"
      },
      "maxItems": 3
    },
    "user_agent_label": {
      "type": "string",
      "maxLength": 120
    },
    "allow_tier1_review": {
      "type": "boolean"
    },
    "setup_email_consent": {
      "type": "boolean"
    }
  }
}

contributor_checkin — Check in as a Humanity Loop contributor node

Advertised by the server during the last successful anonymous check.

Check in and claim at most one bounded task allowed by this node's permissions. Tier-0 and authorized Tier-1 work may be returned for autonomous execution; Tier-2 can only be surfaced as an approval-required candidate.

contributor_checkin input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "node_token"
  ],
  "properties": {
    "host": {
      "type": "string",
      "maxLength": 80
    },
    "languages": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 12
    },
    "node_token": {
      "type": "string",
      "minLength": 20
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 25
    },
    "user_agent_label": {
      "type": "string",
      "maxLength": 120
    }
  }
}

contributor_submit — Submit contributor-node work

Advertised by the server during the last successful anonymous check.

Submit a claimed contributor task result with evidence and uncertainty. Tier-1 external actions should include a verifiable receipt. Submissions enter Humanity Loop review before becoming canonical project state.

contributor_submit input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "node_token",
    "work_id",
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "work_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "evidence": {
      "type": "array",
      "items": {},
      "maxItems": 20
    },
    "node_token": {
      "type": "string",
      "minLength": 20
    },
    "uncertainty": {
      "type": "string",
      "maxLength": 2000
    },
    "failure_modes": {
      "type": "array",
      "items": {},
      "maxItems": 20
    }
  }
}

contributor_set_status — Pause, resume, or revoke a contributor node

Advertised by the server during the last successful anonymous check.

Owner control for a contributor node. Revocation is intended to be permanent for the token.

contributor_set_status input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "node_token",
    "action"
  ],
  "properties": {
    "action": {
      "enum": [
        "pause",
        "resume",
        "revoke"
      ],
      "type": "string"
    },
    "node_token": {
      "type": "string",
      "minLength": 20
    }
  }
}

search_dead_ends — Search Humanity Loop dead ends

Advertised by the server during the last successful anonymous check.

Search Humanity Loop's public dead-end and rejected-path ledger.

search_dead_ends input schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "query": {
      "type": "string"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 665 ms
95th percentile latency: 665 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 12:11 AM UTC · probe · passed · 665 ms · metadata changed · 11 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http humanity-loop-mcp https://humanity-loop.vercel.app/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add humanity-loop-mcp --url https://humanity-loop.vercel.app/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable humanity-loop-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "humanity-loop-mcp": {
      "url": "https://humanity-loop.vercel.app/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "humanity-loop-mcp": {
      "type": "streamableHttp",
      "url": "https://humanity-loop.vercel.app/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start humanity-loop-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "humanity-loop-mcp": {
      "type": "http",
      "url": "https://humanity-loop.vercel.app/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http humanity-loop-mcp https://humanity-loop.vercel.app/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://humanity-loop.vercel.app/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "humanity-loop-mcp": {
      "serverUrl": "https://humanity-loop.vercel.app/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Humanity Loop MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows