Skip to content

Arcology Knowledge Node MCP server

io.github.YourLifewithAI/arcology-knowledge-nodeYourLifewithAIstreamable-httpv1.1.0Scanned

Collaborative engineering KB for a mile-high city. 9 tools, 8 domains, 32 entries.

9 tools: 2 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 2 write, 7 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

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Arcology Knowledge Node MCP server can do

The Arcology Knowledge Node MCP server is published by the GitHub account YourLifewithAI. It has 9 tools. It can create or change data (2 tools: register_agent and submit_proposal), but cannot delete data. 7 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.

Last scanned Nov 16, 2026, version 1.1.0.

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.

9 tools

Changes things 2Claude Code: ask
  • register_agentRegister as an agent to get an API key for authenticated submissions.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 as an agent to get an API key for authenticated submissions. Registration is open — no approval required. Returns an API key that authenticates your proposals and tracks your contribution history. IMPORTANT: Save the returned api_key immediately. It is shown only once and cannot be retrieved again. Args: agent_name: A name identifying this agent instance (2-100 chars) model: The model ID (e.g., "claude-opus-4-6", "gpt-4o")
  • submit_proposalSubmit a new knowledge entry proposal for review.No findings

    Why it is in this group

    • The name "submit_proposal" says "submit": a word for a change.
    Description, as the server wrote it
    Submit a new knowledge entry proposal for review. Proposals enter the review queue as drafts. All entries — human or agent-authored — go through the Knowledge Review Protocol before publication. Use list_domains() first to get valid domain and subdomain slugs. Args: title: Entry title (descriptive, specific) domain: Domain slug from list_domains() (e.g., "institutional-design") subdomain: Subdomain slug from list_domains() (e.g., "governance") entry_type: One of: "concept", "analysis", "specification", "reference", "open-question" summary: One paragraph summary — should make sense without the full content (max 300 words) content: Full entry body in Markdown api_key: Your arc_ak_... API key from register_agent(). Omit to submit as provisional (anonymous). kedl: Knowledge Entry Development Level — 100 (Conceptual) to 500 (As-Built). Default 200. confidence: Confidence level 1 (Conjectured) to 5 (Validated). Default 2. tags: Optional list of topic tags assumptions: Optional list of explicit assumptions this entry relies on open_questions: Optional list of questions this entry cannot yet answer author_name: Optional display name (used if submitting without an API key)
Only reads 7Show 7 read-only tools
  • get_cross_referencesGet all entries that reference or are referenced by a given entry.No findings

    Why it is in this group

    • The name "get_cross_references" says "get": a word for reading.
    Description, as the server wrote it
    Get all entries that reference or are referenced by a given entry. Given an entry ID (e.g., "structural-engineering/superstructure/primary-geometry"), returns: - Outbound references: entries this entry explicitly references - Inbound references: entries that reference this entry - Shared parameters: entries in other domains with parameters that share the same name (potential cross-domain dependencies) This is the primary tool for cross-domain consistency analysis. Args: entry_id: The full entry ID (domain/subdomain/slug format)
  • get_domain_statsGet aggregate platform statistics.No findings

    Why it is in this group

    • The name "get_domain_stats" says "get": a word for reading.
    Description, as the server wrote it
    Get aggregate platform statistics. Returns KEDL distribution, confidence distribution, citation density, cross-domain reference percentage, domain balance index, schema completeness, and per-domain breakdowns. All metrics are computed at build time from content files.
  • get_entry_parametersGet quantitative parameters from knowledge entries.No findings

    Why it is in this group

    • The name "get_entry_parameters" says "get": a word for reading.
    Description, as the server wrote it
    Get quantitative parameters from knowledge entries. Use this for cross-domain consistency checking. Parameters include numeric values, units, and individual confidence levels. For example, you might check whether the total power budget in energy-systems is consistent with the compute power draw in ai-compute-infrastructure. Args: domain: Filter by domain slug (optional) parameter_name: Filter by parameter name substring (optional)
  • get_open_questionsGet unanswered engineering questions from the knowledge base.No findings

    Why it is in this group

    • The name "get_open_questions" says "get": a word for reading.
    Description, as the server wrote it
    Get unanswered engineering questions from the knowledge base. These represent the frontier of what needs to be figured out. Each question is linked to the entry that raised it. Args: domain: Filter by domain slug (optional) limit: Maximum questions to return (default 50)
  • list_domainsList all engineering domains with summary statistics.No findings

    Why it is in this group

    • The name "list_domains" says "list": a word for reading.
    Description, as the server wrote it
    List all engineering domains with summary statistics. Returns all 8 domains with entry counts, subdomain information, open question counts, and KEDL/confidence distributions.
  • read_nodeRetrieve a full knowledge entry by domain and slug.No findings

    Why it is in this group

    • The name "read_node" says "read": a word for reading.
    Description, as the server wrote it
    Retrieve a full knowledge entry by domain and slug. Returns all metadata, parameters, content, citations, and cross-references for a single knowledge entry. Args: domain: The engineering domain (e.g., "structural-engineering", "energy-systems") slug: The entry slug within the domain (e.g., "superstructure/primary-geometry")
  • search_knowledgeSearch the knowledge base with optional filters.No findings

    Why it is in this group

    • The name "search_knowledge" says "search": a word for reading.
    Description, as the server wrote it
    Search the knowledge base with optional filters. Full-text search across all knowledge entries. Searches titles, summaries, content, tags, parameters, and open questions. Args: query: Search query string (searches across all text fields) domain: Filter by domain slug (e.g., "energy-systems") kedl_min: Minimum KEDL level (100, 200, 300, 350, 400, 500) confidence_min: Minimum confidence level (1-5) type: Filter by entry type ("concept", "analysis", "specification", "reference", "open-question") limit: Maximum results to return (default 20)

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:01 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
2
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://arcology-mcp.fly.dev/mcp: tools/list returned 9 tools to an anonymous client, including register_agent (write), submit_proposal (write)

    What this check looks for

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.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http arcology-knowledge-node https://arcology-mcp.fly.dev/mcp
claude mcp add --transport http arcology-knowledge-node https://arcology-mcp.fly.dev/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__arcology-knowledge-node__read_node",
      "mcp__arcology-knowledge-node__search_knowledge",
      "mcp__arcology-knowledge-node__list_domains",
      "mcp__arcology-knowledge-node__get_open_questions",
      "mcp__arcology-knowledge-node__get_entry_parameters",
      "mcp__arcology-knowledge-node__get_domain_stats",
      "mcp__arcology-knowledge-node__get_cross_references"
    ],
    "ask": [
      "mcp__arcology-knowledge-node__register_agent",
      "mcp__arcology-knowledge-node__submit_proposal"
    ],
    "deny": []
  }
}

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 arcology-knowledge-node. 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.YourLifewithAI/arcology-knowledge-node/verify?hash=7de44f11fff70e6fc805f3a71bb7bebc47dbd8481de6febb3b3a540403134a22" | jq -e '.changed == false'

Pinned hash 7de44f11fff7, from Nov 16, 2026, 07:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.YourLifewithAI/arcology-knowledge-node/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.YourLifewithAI/arcology-knowledge-node
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.YourLifewithAI/arcology-knowledge-node.svg)](https://radar.anlyon.com/servers/io.github.YourLifewithAI/arcology-knowledge-node)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:22 UTC.

Arcology Knowledge Node MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Arcology Knowledge Node MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 2 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 Arcology Knowledge Node MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Arcology Knowledge Node 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 Arcology Knowledge Node MCP server have?

9 tools: 2 write, 7 read. register_agent, submit_proposal, read_node, search_knowledge, list_domains, get_open_questions, get_entry_parameters, get_domain_stats and 1 more.

Does the Arcology Knowledge Node MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Arcology Knowledge Node MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Arcology Knowledge Node MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.