Neurogenesis MCP server
io.github.jdhart81/neurogenesisjdhart81streamable-httpv0.2.1Scanned
Developmental agents: create an agent from a digital genome, then evolve it by evaluation.
14 tools: 1 can delete or cancel things, 9 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Neurogenesis MCP server can do
The Neurogenesis MCP server is published by the GitHub account jdhart81. It has 14 tools. It can delete or cancel things (1 tool: delete_agent) and create or change data (9 tools: create_agent, submit_evaluation, best_next_steps, export_state and 5 more). 4 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.2.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Deletes or cancels 1Claude Code: deny
delete_agentRemove a developmental agent from this mount.No findings
Why it is in this group
- The name "delete_agent" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Remove a developmental agent from this mount.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Delete agent
Changes things 9Claude Code: ask
best_next_stepsRouting recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Best next steps
compute_efficiency_reportFree read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor context.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Compute efficiency report
create_agentCreate a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / safety_axioms}.No findings
Why it is in this group
- The name "create_agent" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Create agent
export_statePortable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Portable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Export state
import_stateRecreate an agent from an export_state document.No findings
Why it is in this group
- The name "import_state" says "import": a word for a change.
Description, as the server wrote it Recreate an agent from an export_state document.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Import state
record_route_outcomeAttach one observed outcome to a Wu Wei decision.No findings
Why it is in this group
- The description's first verb is "attach": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Record route outcome
register_compute_profileRegister a caller-owned Wu Wei execution profile: reuse/cache, deterministic rule, local model, tool/workflow, or cloud model.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Register compute profile
route_taskChoose the least-burden eligible route for a task.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Route task
submit_evaluationEvolve 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}.No findings
Why it is in this group
- The name "submit_evaluation" says "submit": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Submit evaluation
Only reads 4Show 4 read-only tools
describe_agentReturn capabilities and input contract.No findings
Why it is in this group
- The name "describe_agent" says "describe": a word for reading.
Description, as the server wrote it Return capabilities and input contract.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Describe this service
get_agentFull current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.No findings
Why it is in this group
- The name "get_agent" says "get": a word for reading.
Description, as the server wrote it Full current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Get agent
get_ledgerThe append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).No findings
Why it is in this group
- The name "get_ledger" says "get": a word for reading.
Description, as the server wrote it The append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Get ledger
list_agentsAll developmental agents on this mount, with summary counts.No findings
Why it is in this group
- The name "list_agents" says "list": a word for reading.
Description, as the server wrote it All developmental agents on this mount, with summary counts.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List agents
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:29 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (1 destructive, 9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.viridisconservation.com/neurogenesis/mcp: tools/list returned 14 tools to an anonymous client, including delete_agent (destructive), create_agent (write), submit_evaluation (write), best_next_steps (write), export_state (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools12 changed.~12 changedView diff
- Changed:best_next_stepsChanges thingsinputSchema
- Changed:compute_efficiency_reportChanges thingsinputSchema
- Changed:create_agentChanges thingsinputSchema
- Changed:delete_agentDeletes or cancelsinputSchema
- Changed:export_stateChanges thingsinputSchema
- Changed:get_agentOnly readsinputSchema
- Changed:get_ledgerOnly readsinputSchema
- Changed:import_stateChanges thingsinputSchema
- Changed:record_route_outcomeChanges thingsinputSchema
- Changed:register_compute_profileChanges thingsinputSchema
- Changed:route_taskChanges thingsinputSchema
- Changed:submit_evaluationChanges thingsinputSchema
Tools14 changed.~14 changedView diff
- Changed:best_next_stepsChanges thingstitleannotations
- Changed:compute_efficiency_reportChanges thingstitleannotations
- Changed:create_agentChanges thingstitleannotations
- Changed:delete_agentDeletes or cancelstitleannotations
- Changed:describe_agentOnly readstitleannotations
- Changed:export_stateChanges thingstitleannotations
- Changed:get_agentOnly readstitleannotations
- Changed:get_ledgerOnly readstitleannotations
- Changed:import_stateChanges thingstitleannotations
- Changed:list_agentsOnly readstitleannotations
- Changed:record_route_outcomeChanges thingstitleannotations
- Changed:register_compute_profileChanges thingstitleannotations
- Changed:route_taskChanges thingstitleannotations
- Changed:submit_evaluationChanges thingstitleannotations
Install
Pinned to version 0.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http neurogenesis https://mcp.viridisconservation.com/neurogenesis/mcpclaude mcp add --transport http neurogenesis https://mcp.viridisconservation.com/neurogenesis/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__neurogenesis__get_agent",
"mcp__neurogenesis__list_agents",
"mcp__neurogenesis__get_ledger",
"mcp__neurogenesis__describe_agent"
],
"ask": [
"mcp__neurogenesis__create_agent",
"mcp__neurogenesis__submit_evaluation",
"mcp__neurogenesis__best_next_steps",
"mcp__neurogenesis__export_state",
"mcp__neurogenesis__import_state",
"mcp__neurogenesis__register_compute_profile",
"mcp__neurogenesis__route_task",
"mcp__neurogenesis__record_route_outcome",
"mcp__neurogenesis__compute_efficiency_report"
],
"deny": [
"mcp__neurogenesis__delete_agent"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as neurogenesis. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.jdhart81/neurogenesis/verify?hash=0edf288efbc3e9e0837cad6a3b36717d853a0dcf8c0db0d70a9b0ffb94e62c11" | jq -e '.changed == false'Pinned hash 0edf288efbc3, from Nov 16, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.jdhart81/neurogenesis/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.jdhart81/neurogenesis)Source: MCP Registry · repository. Synced Nov 16, 2026, 02:18 UTC.
Neurogenesis MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Neurogenesis MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 10 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Neurogenesis MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: delete_agent.
Can the Neurogenesis MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Neurogenesis MCP server have?
- 14 tools: 1 destructive, 9 write, 4 read. delete_agent, create_agent, submit_evaluation, best_next_steps, export_state, import_state, register_compute_profile, route_task and 6 more.
Does the Neurogenesis MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Neurogenesis MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Neurogenesis MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.