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.GCTRL-TECH/gctrl

NPM · GCTRL-MCP · SCANNED AUG 3

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.

Available components

+21 this week 67 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 (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (AGPL-3.0-or-later).Pass
  • Actively maintained (last published 14 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability64
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 5677 tokens (~103/item across 55 items; 55 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • 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 Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 94% of tool parameters carry a description.Partial
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 · gctrl-mcp

# add to Claude Code
claude mcp add gctrl-tech-gctrl -- npx -y gctrl-mcp
# add to Codex CLI
codex mcp add gctrl-tech-gctrl -- npx -y gctrl-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "gctrl-tech-gctrl": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "gctrl-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add gctrl-tech-gctrl --command npx --arg -y --arg gctrl-mcp
# ~/.hermes/config.yaml
mcp_servers:
  gctrl-tech-gctrl:
    command: "npx"
    args: ["-y", "gctrl-mcp"]
// mcp.json
{
  "mcpServers": {
    "gctrl-tech-gctrl": {
      "command": "npx",
      "args": [
        "-y",
        "gctrl-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 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Aug 26 +45
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Security disclosure: fail → unverified functional
    • Tool coverage: 100 → unverified functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Stability: unverified → 0.23 functional
    • Schema quality: unverified → good functional
    • First check of Schema quality: unverified functional
    • Licence: AGPL-3.0-or-later functional
  • 1 Aug 26 −7
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 46

    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/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

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

MCP tools — 55 exposed · ~5,376 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
gctrl_set_privacy_mode ~152

Raise a knowledge graph's privacy for cloud LLMs during setup: 'cloaked' (pseudonymize entities/PII before a cloud model sees them) or 'local_only' (never send it to a cloud model). Can only INCREASE privacy — loosening it back to 'open' needs the Settings UI. Never call this 'encryption'.

NameTypeReqDescription
compilationIdstringyesThe knowledge graph to make more private.
modestringyes'cloaked' = entities/PII are pseudonymized before any cloud model sees them (recommended when you are a cloud model); 'local_only' = this graph is never sent to a cloud model.

No output schema declared.

No examples provided.

gctrl_shortest_path ~73

Find the shortest path between two entities (how is A connected to B / does X depend on Y). Clearance-aware: a path is only returned if every node on it is one you are cleared to see.

NameTypeReqDescription
fromstringyesStart entity name
tostringyesEnd entity name

No output schema declared.

No examples provided.

gctrl_store ~160

WRITE your conclusions back into GCTRL — call this after ANY substantive task so your memory compounds across sessions (this is the point of GCTRL). Extracts entities + builds graph from the text, like saving notes but structured. IMPORTANT: always pass a compilationId for your assigned knowledge base (find it via gctrl_list_graphs) so nothing is orphaned.

NameTypeReqDescription
compilationIdstringTarget knowledge graph compilation ID. RECOMMENDED: always specify this to store into the correct agent graph. Use gctrl_list_graphs to find IDs.
ontologyIdstringOptional ontology to guide extraction
textstringyesText content to store as knowledge
titlestringOptional title/label for this knowledge

No output schema declared.

No examples provided.

gctrl_wiki_graph ~70

Get a WIKI compilation as a navigable graph: pages are nodes, [[wikilinks]] are edges. Clearance-filtered (pages above your clearance, and their links, are hidden). Useful for canvas/visual clients.

NameTypeReqDescription
compilationIdstringyesThe WIKI compilation ID

No output schema declared.

No examples provided.

gctrl_wiki_page ~119

Read distilled wiki pages from a WIKI compilation. Pass a slug to fetch one full page (markdown body + citations); omit the slug to list all pages (optionally filtered by query).

NameTypeReqDescription
compilationIdstringyesThe WIKI compilation ID.
querystringOptional: when no slug is given, filter the listed pages whose title contains this text.
slugstringSlug of a specific page to fetch (e.g. "fabio-chiaramonte"). Omit to list all pages.

No output schema declared.

No examples provided.