Developmental agents for the agent economy: create an agent from a digital genome, then evolve it wi
| Endpoint | https://mcp.viridisconservation.com/neurogenesis/mcp (streamable-http) |
|---|---|
| Registry version | 0.2.0 |
| Now | 14 tools · grade B (82) · pin ts_b21183ef415a30ad4c3de5528bde861e · protocol 2025-06-18 |
| First / last listed | 2026-10-28 03:12 UTC / 2026-10-28 03:12 UTC |
| Grade over time | 2026-10-28: B (82), 14 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: 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 compute_efficiency_report describe_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. params: genome*, request_id |
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. params: agent_id*, evaluation*, request_id |
get_agent | Full current state: genome, cognitive graph (nodes/edges with
weights and trust), and summary counts. params: agent_id* |
list_agents | All developmental agents on this mount, with summary counts. params: none |
best_next_steps | Routing recommendation: the strongest next cognitive steps from a
given node, by learned edge weight and trust. params: agent_id*, from_node*, limit |
get_ledger | The append-only developmental ledger: every growth, pruning, and
evaluation event with reasons (NG3 — returned verbatim). params: agent_id*, limit |
export_state | Portable state document for an agent (import_state recreates it
anywhere — including a self-hosted verdigraph-neurogenesis). params: agent_id* |
import_state | Recreate an agent from an export_state document. params: state*, request_id |
delete_agent | Remove a developmental agent from this mount. params: agent_id*, request_id |
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 never invents capacity or energy evidence. params: profile*, request_id |
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 claimed. Returns a hash-bound decision receipt. params: task*, request_id |
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. params: decision_id*, success_score*, actual_cost_usd, actual_latency_ms, actual_energy_wh, notes, request_id |
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. params: limit |
describe_agent | Return capabilities and input contract. params: none |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.