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

ArkHive MCP

PYPI · ARKHIVE-MCP · SCANNED AUG 18

ArkHive MCP: governed, tamper-evident local memory for AI agents. Where context gives meaning.

Available components

+6 this week 68 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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 2 of 30 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability57
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 208 tokens (~41/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
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.

pypi · arkhive-mcp

# add to Claude Code
claude mcp add sammyboi81-arkhive -- uvx arkhive-mcp
# add to Codex CLI
codex mcp add sammyboi81-arkhive -- uvx arkhive-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sammyboi81-arkhive": {
      "type": "local",
      "command": [
        "uvx",
        "arkhive-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add sammyboi81-arkhive --command uvx --arg arkhive-mcp
# ~/.hermes/config.yaml
mcp_servers:
  sammyboi81-arkhive:
    command: "uvx"
    args: ["arkhive-mcp"]
// mcp.json
{
  "mcpServers": {
    "sammyboi81-arkhive": {
      "command": "uvx",
      "args": [
        "arkhive-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.

  • 18 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Aug 26 +4
    • Security disclosure: unverified → fail functional
    • Stability: unverified → 0.27 functional
  • 14 Aug 26 0
    • Security disclosure: fail → unverified functional
  • 12 Aug 26 0
    • Security disclosure: unverified → fail functional
  • 11 Aug 26 +3
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 7 Aug 26 59

    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 18 Aug 2026 · Analysed pypi/arkhive-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta
Dependencies 30 packages
Packages resolved 30
Stale 1
No linked repository 1
Tree resolution Complete
MCP tools · 5 exposed · ~171 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
birth ~37

Earn an identity (Law 5: born, not configured) before acting.

NameTypeReqDescription
covenantarrayyes
namestringyes

No output schema declared.

No examples provided.

govern ~38

Ask whether an action may proceed using deterministic rules.

NameTypeReqDescription
actionstringyes
flagsarray
rulesarray

No output schema declared.

No examples provided.

recall ~34

Read prior context so the AI need not re-derive it.

NameTypeReqDescription
actorstring
limitinteger

No output schema declared.

No examples provided.

remember ~45

Write a tamper-evident record. Requires a born soul_id as actor.

NameTypeReqDescription
actionstringyes
actorstringyes
dataobject

No output schema declared.

No examples provided.

verify ~17

Prove the entire memory chain is unbroken.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.