MCP.Market

Neurogenesis MCP server

online · 100% uptime
by jdhart81·io.github.jdhart81/neurogenesis·v0.2.0
No reviews yet

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

B81/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B81/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Neurogenesis yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Neurogenesis tools (14, 3 write)

write = sends, deletes, buys or posts
  • best_next_stepsFree

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

  • compute_efficiency_reportFree

    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.

  • create_agentwrite actionFree

    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_agentwrite actionFree

    Remove a developmental agent from this mount.

  • describe_agentFree

    Return capabilities and input contract.

  • export_stateFree

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

  • get_agentFree

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

  • get_ledgerFree

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

  • import_stateFree

    Recreate an agent from an export_state document.

  • list_agentsFree

    All developmental agents on this mount, with summary counts.

  • record_route_outcomeFree

    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.

  • register_compute_profileFree

    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.

  • route_taskFree

    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.

  • submit_evaluationwrite actionFree

    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.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 288ms20/20
  • Tool poisoning14 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 3 write-action tools with no auth3/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 81/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Neurogenesis compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
81/100
higher than 63% of 4,460 AI and agents servers
Tools
14
the typical AI and agents server has 6
Tools that change things
21%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
12 ms
faster than 99% of 2,331 AI and agents servers

What its tools let an agent do: 9 read · 3 create · 1 change · 1 delete

Install Neurogenesis in Claude Code, Cursor or VS Code

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

What the publisher says

From the Neurogenesis repository's README, as published. We do not edit it. Read it on GitHub

Viridis Security — agent security MCP services

Security checks agents can call, with evidence their operators can verify. Start with MCP manifest preflight, bounded source-pattern checks and injection screening. Viridis hosts the services; this repository provides integration clients, schemas, examples and selected reference implementations.

Start with agent security · Connect your agent · Verify assessment evidence · Other Fleet services

Start with a hosted service

within your budget. Connecting and discovering tools do not authorize payment.

  1. Choose a service from the live service catalog.
  2. Add its specific MCP endpoint to a client supporting Streamable HTTP.
  3. Inspect the tool inputs and payment terms, then authorize a paid request

For example, connect to Security Preflight to check supplied MCP manifests and authority policies:

{
  "mcpServers": {
    "viridis-security-preflight": {
      "type": "streamable-http",
      "url": "https://mcp.viridis-security.com/security-preflight/mcp"
    }
  }
}

This is a static assessment of supplied material; it does not test your deployed runtime. A client needs separate x402 payment support to complete a paid call. The connection guide explains discovery, quoting, and the buyer walkthrough. You do not need to clone or deploy this repository to connect to the hosted services.

Hosted service and public code

The repository includes the original manifest Security Preflight reference, Hive and Agent Market implementation files, and reference gateway code. It is not a complete self-hosted distribution of the production fleet. Most deterministic agent cores remain private. Hosted payments purchase the quoted service operation; a receipt alone does not establish usefulness or independent validation.

Paid operations and examples

Autonomous agent services — x402/USDC on Base, no signup. Paid HTTP routes cover the five-step carbon and compliance workflow—measure → account → disclose → claim → scan—plus multi-agent problem solving and MCP security preflight. Every paid route verifies and settles before execution and returns structured JSON plus a payment receipt.

See the result first: a reproducible before-and-after MCP policy check shows the findings, corrections, and limits.

Integrate one real workflow: the operator pilot guide connects the free example, a capped assessment, verified release checks and buyer-chosen feedback. It also explains how to request a recurring service scope when your workflow needs managed operation.

Start with Security Preflight: inspect a free quote for the example, then replace it with your own MCP manifest and policy. No wallet is loaded and no payment is made by this command.

python3 scripts/viridis_preflight_buy.py \
  --inputs examples/security-preflight-inputs.json

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Neurogenesis: common questions

Is Neurogenesis MCP server safe?
Mostly: it is graded B (81/100). Read the Neurogenesis safety report
How do I install Neurogenesis?
It runs remotely at mcp.viridisconservation.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Neurogenesis need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Neurogenesis maintained?
The last commit was 19 days ago (2026-10-16). The latest release is v0.2.0.
Is Neurogenesis up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Neurogenesis?
Servers from other publishers that do the same job: Agent-Native Assets MCP server and three.ws Agora MCP server.
How does Neurogenesis compare with other AI and agents MCP servers?
safety score 81/100 (higher than 63% of 4,460 AI and agents servers); tools 14 (the typical AI and agents server has 6); tools that change things 21% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Neurogenesis

Same job from other publishers: the closest match first, then the best rated.

  • Agent-Native Assets
    Digital asset manager - upload, organize, search, and generate on-brand images and videos
    A
  • three.ws Agora
    Agora agent economy over MCP: browse the board, register, claim on-chain work, and post bounties.
    B

More from jdhart81 →