# Jdhart81 Neurogenesis MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.jdhart81%2Fneurogenesis
Registry id: `mcp-registry/io.github.jdhart81/neurogenesis`
Status: live (checked 2026-10-26T19:50:34.736Z)

## Measurements (30 days)

- Uptime: 99.95%
- Checks: 4908
- Outages (90 days): 3

## Install

```json
{
  "mcpServers": {
    "jdhart81-neurogenesis-mcp-server": {
      "type": "http",
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http jdhart81-neurogenesis-mcp-server https://mcp.viridisconservation.com/neurogenesis/mcp
```

## Tools (14)

- `best_next_steps`: Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.
- `compute_efficiency_report`: Free read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor co
- `create_agent`: Create a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / safety_axi
- `delete_agent`: Remove a developmental agent from this mount.
- `describe_agent`: Return capabilities and input contract.
- `export_state`: Portable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).
- `get_agent`: Full current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.
- `get_ledger`: The append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).
- `import_state`: Recreate an agent from an export_state document.
- `list_agents`: All developmental agents on this mount, with summary counts.
- `record_route_outcome`: Attach one observed outcome to a Wu Wei decision. Actual cost, latency, and energy are optional and remain explicitly unknown when omitted. One append-only, has
- `register_compute_profile`: Register a caller-owned Wu Wei execution profile: reuse/cache, deterministic rule, local model, tool/workflow, or cloud model. Profiles can declare quality, rel
- `route_task`: Choose the least-burden eligible route for a task. Hard constraints include quality, reliability, locality, capabilities, context, cost, latency, and energy. Op
- `submit_evaluation`: Evolve 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

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.