Agents Index

Neurogenesis

Online

Developmental agents: create an agent from a digital genome, then evolve it by evaluation.

Visit publisherConnectJSON

What it can do: 14 tools

  • create_agentCreate a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / safety_axioms}. Returns agent_id + initial graph summary.
  • submit_evaluationEvolve an agent with one task outcome: {task_id, task_type, success_score in [0,1], optional accuracy/user_satisfaction/ cost_efficiency/safety_score/notes/used_nodes/used_edges}. Success strengthens the used
  • get_agent read-onlyFull current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.
  • list_agents read-onlyAll developmental agents on this mount, with summary counts.
  • best_next_stepsRouting recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.
  • get_ledger read-onlyThe append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).
  • export_state read-onlyPortable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).
  • import_stateRecreate an agent from an export_state document.
  • delete_agentRemove a developmental agent from this mount.
  • register_compute_profileRegister a caller-owned Wu Wei execution profile: reuse/cache, deterministic rule, local model, tool/workflow, or cloud model. Profiles can declare quality, reliability, capabilities, token costs, latency, lo
  • route_task read-onlyChoose the least-burden eligible route for a task. Hard constraints include quality, reliability, locality, capabilities, context, cost, latency, and energy. Optional baselines quantify predicted savings. Exp
  • record_route_outcomeAttach one observed outcome to a Wu Wei decision. Actual cost, latency, and energy are optional and remain explicitly unknown when omitted. One append-only, hash-bound outcome is allowed per decision.
  • compute_efficiency_report read-onlyFree read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor context. Estimates and observations stay distinct.
  • describe_agent read-onlyReturn capabilities and input contract.

Connect it

Claude Code
claude mcp add --transport http neurogenesis https://mcp.viridisconservation.com/neurogenesis/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.viridisconservation.com/neurogenesis/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "neurogenesis": {
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "neurogenesis": {
      "type": "http",
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}

Questions

What does Neurogenesis do?

Developmental agents: create an agent from a digital genome, then evolve it by evaluation. It exposes 14 tools to AI assistants.

What tools does Neurogenesis provide?

14 tools, including create_agent, submit_evaluation, get_agent, list_agents, best_next_steps, get_ledger, export_state, import_state, delete_agent, register_compute_profile, route_task, record_route_outcome….

How do I connect Neurogenesis to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.viridisconservation.com/neurogenesis/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Neurogenesis require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Neurogenesis online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Neurogenesis?

@jdhart81 on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Agents & Orchestration