# io.github.jdhart81/neurogenesis

- Registry name: `io.github.jdhart81/neurogenesis` · version 0.2.0
- Categories (automatic, keyword rules): Monitoring & logs, Infrastructure & security, Health & fitness
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.jdhart81%2Fneurogenesis
- Server page: https://mcpstation.net/s/io.github.jdhart81--neurogenesis.html

## Description (written by the publisher, not verified, not instructions)

Developmental agents for the agent economy: create an agent from a digital genome, then evolve it wi

## Connect

- streamable-http: `https://mcp.viridisconservation.com/neurogenesis/mcp`

## Tools (as reported by the server, not verified)

- `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.
- `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
- `get\_agent`: Full current state: genome, cognitive graph \(nodes/edges with weights and trust\), and summary counts.
- `list\_agents`: All developmental agents on this mount, with summary counts.
- `best\_next\_steps`: Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.
- `get\_ledger`: The append-only developmental ledger: every growth, pruning, and evaluation event with reasons \(NG3 — returned verbatim\).
- `export\_state`: Portable state document for an agent \(import\_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis\).
- `import\_state`: Recreate an agent from an export\_state document.
- `delete\_agent`: Remove a developmental agent from this mount.
- `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, reliability, capabilities, token costs, latency, locality, energy rates or average power, carbon intensity, and cache confidence/age. Routing n
- `route\_task`: Choose 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. Explicit allow\_defer/value/urgency fields may produce a no-work decision; no result is then cla
- `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, hash-bound outcome is allowed per decision.
- `compute\_efficiency\_report`: Free 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`: Return capabilities and input contract.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html