Neurogenesis MCP Server

io.github.jdhart81/neurogenesis

answering

Neurogenesis is answering right now. Last checked 14 min ago. It exposes 13 tools. Last commit 3 Aug 2026.

Developmental agents + Wu Wei compute routing: evolve from outcomes, route to cheapest reliable.

Uptime history 41 hours of history

41 hours agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

343 ms

Response time

average over 24h

Stars

last commit 3 Aug 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add neurogenesis --transport http https://mcp.viridisconservation.com/neurogenesis/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "neurogenesis": {
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.neurogenesis]
url = "https://mcp.viridisconservation.com/neurogenesis/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "neurogenesis": {
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "neurogenesis": {
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}

Available tools 13

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent

create_agent

Create 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.

delete_agent

Remove a developmental agent from this mount.

get_agent

Full current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.

agents

list_agents

All developmental agents on this mount, with summary counts.

best

best_next_steps

Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.

compute

compute_efficiency_report

Free read: the routing decision log (per-profile counts, estimated costs, reasons) with the Landauer-floor physics context — honest compute-efficiency accounting in the Intelligence Bound frame.

describe

describe_agent

Return capabilities and input contract.

export

export_state

Portable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).

import

import_state

Recreate an agent from an export_state document.

ledger

get_ledger

The append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).

register_compute_profile

Wu Wei compute routing (NG7): register an execution profile — {id, kind?, quality_score [0,1], cost_per_1k_input_tokens?, cost_per_1k_output_tokens?, latency_ms?, gpu_memory_gb?, max_context_tokens?, local?}. A profile can be a local model, cloud API, rules engine, or cached workflow. Profiles are yours — routing never invents capacity.

route

route_task

Choose the cheapest RELIABLE compute path for a task: {id, task_type, expected_input_tokens, expected_output_tokens, min_quality [0,1], risk?, difficulty?, requires_local?}. Hard contract (NG7): profiles below your min_quality are ineligible regardless of cost — compute savings never silently regress quality. Deterministic; every decision is logged with its reason.

submit

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_nodes/used_edges}. Success strengthens the used edges, failure weakens them; growth and pruning follow the genome's rules under its safety axioms (NG1). Returns the new developmental-ledger events.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.viridisconservation.com/neurogenesis/mcp	streamable-http	answering	318 ms	14 min ago

Neurogenesis — questions

Answers built from our own checks of this server.

What can Neurogenesis do?

It exposes 13 tools, read directly from the server on our last check. Among them: best_next_steps, compute_efficiency_report, create_agent, delete_agent, describe_agent, export_state and 7 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Neurogenesis working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 343 ms. The bar chart above shows every period we have measured.

How do I connect Neurogenesis?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Neurogenesis need an API key?

No. Neurogenesis completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 13 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Neurogenesis?

It answers our handshake in 343 ms on average, which is faster than 41% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Neurogenesis open source?

Yes — written in Python, 0 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.