# neurogenesis MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-jdhart81-neurogenesis
- Repository: https://github.com/jdhart81/viridis-agent-fleet

## Install
- Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp

## Tools
- 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. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- 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. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- get_agent - Full current state: genome, cognitive graph (nodes/edges with
    weights and trust), and summary counts. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- list_agents - All developmental agents on this mount, with summary counts. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- best_next_steps - Routing recommendation: the strongest next cognitive steps from a
    given node, by learned edge weight and trust. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- get_ledger - The append-only developmental ledger: every growth, pruning, and
    evaluation event with reasons (NG3 — returned verbatim). Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- export_state - Portable state document for an agent (import_state recreates it
    anywhere — including a self-hosted verdigraph-neurogenesis). Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- import_state - Recreate an agent from an export_state document. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- delete_agent - Remove a developmental agent from this mount. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- 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. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- 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. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- 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. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp
- describe_agent - Return capabilities and input contract. Endpoint: https://mcp.viridisconservation.com/neurogenesis/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.jdhart81
- Version: 0.1.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 18, 2026
- Source: https://registry.modelcontextprotocol.io