Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.Noderail/noderail

NPM · @NODERAIL/MCP · SCANNED AUG 3

Provenance and governance layer for AI-readable knowledge. NodeRail answers what AI should trust.

Available components

+22 this week 62 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (144 of 146), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (144 of 146), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 636 tokens (~106/item across 6 items; 6 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @noderail/mcp

# add to Claude Code
claude mcp add noderail-noderail -- npx -y @noderail/mcp
# add to Codex CLI
codex mcp add noderail-noderail -- npx -y @noderail/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "noderail-noderail": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@noderail/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add noderail-noderail --command npx --arg -y --arg @noderail/mcp
# ~/.hermes/config.yaml
mcp_servers:
  noderail-noderail:
    command: "npx"
    args: ["-y", "@noderail/mcp"]
// mcp.json
{
  "mcpServers": {
    "noderail-noderail": {
      "command": "npx",
      "args": [
        "-y",
        "@noderail/mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +4
    • Stability: unverified → 0.27 functional
  • 2 Aug 26 +42
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • License: unverified → fail functional
    • Security disclosure: unverified → fail functional
    • Schema quality: unverified → excellent functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
  • 31 Jul 26 −6
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 40

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@noderail/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 144 packages

144 packages in the resolved dependency tree · 144 deprecated · 44 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 6 exposed · ~636 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
noderail_get_field ~102

Get a Field node by ID or name with full provenance. Returns scope, governance, canonical registry, lineage, citation, and a content preview. If neither field_id nor field_name is provided, lists all available fields.

NameTypeReqDescription
field_idstringnode_id of the Field node (e.g. NR-20260224-HCS-001)
field_namestringHuman-readable field name (e.g. "Human Capacity Science")

No output schema declared.

No examples provided.

noderail_get_lineage ~71

Get the version history and full lineage chain for a node. Returns declared parents, forked_from, adopted_from, declared children, and nodes discovered by reverse-lookup that reference this node as a parent or fork source.

NameTypeReqDescription
node_idstringyesThe node_id to trace lineage for

No output schema declared.

No examples provided.

noderail_get_node ~71

Get any node by ID with full content — all frontmatter fields and the complete Markdown body.

NameTypeReqDescription
include_bodybooleanInclude full Markdown body (default: true)
node_idstringyesThe unique node_id (e.g. NR-20260224-HCS-001)

No output schema declared.

No examples provided.

noderail_get_trust_status ~179

Provenance gate: generate a full trust report for a node. Returns: • evidence_level — HIGH / MEDIUM / LOW / CONTESTED / DEPRECATED • canonical_status — whether the node is registered in its field's canonical registry • permitted_use — license, citation requirements, and use guidance • warnings — ordered list of trust concerns • recommendation — clear AI action guidance (SUITABLE / PILOT / DRAFT / CAUTION / DO NOT USE) • provenance — DOI, lineage, maintainer, and validation coverage MCP answers: what can AI access? NodeRail answers: what should AI trust? Always call this tool before citing a node in authoritative AI outputs.

NameTypeReqDescription
node_idstringyesThe node_id to evaluate

No output schema declared.

No examples provided.

noderail_list_nodes ~76

List all nodes in the NodeRail knowledge graph with status and version. Filter by field, node_type, or status.

NameTypeReqDescription
fieldstringFilter by field name (e.g. "Human Capacity Science")
node_typestringFilter by node type
statusstringFilter by status

No output schema declared.

No examples provided.

noderail_search_nodes ~137

Search NodeRail nodes by keyword (scans title, tags, body text, and node_id) or filter by author/maintainer name. At least one parameter must be provided.

NameTypeReqDescription
authorstringFilter by creator, maintainer, or contributor name
fieldstringRestrict search to a specific field
limitintegerMaximum results to return (default: 10, max: 50)
node_typestringRestrict search to a node type
querystringKeyword or phrase to search in title, tags, body, and node_id

No output schema declared.

No examples provided.