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.

Procheiron

PYPI · PROCHEIRON · SCANNED AUG 20

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Available components

+4 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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency35
  • 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
  • License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
  • Actively maintained (last published 8 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability41
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 465 tokens (~93/item across 5 items; 4 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 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 current MCP spec version (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 · procheiron

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

  • 20 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 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.

  • 16 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Aug 26 +15
    • Malware scan: unverified → pass security
  • 12 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Aug 26 −8
    • Malware scan: pass → unverified security
    • Schema quality: 81 → 93 functional
    • Stability: unverified → 0.03 functional
    • MCP protocol: fail → pass functional
    • Schema quality: poor → good functional
    • Package version: 0.3.2 → 0.3.3 functional
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 10 Aug 26 50

    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 20 Aug 2026 · Analysed pypi/procheiron@0.3.3

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 hatchling.build
Dependencies 0 packages
Packages resolved 0
Tree resolution Complete
MCP tools · 4 exposed · ~397 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
memory.get ~55

Get one memory record by id (read-only). Returns the record plus a top-level `trusted` boolean and `trust_reason` — do not read `status` as trust on its own.

NameTypeReqDescription
memory_idstringyes

No output schema declared.

No examples provided.

memory.promote ~127

Promote a memory record — GATED. The reviewer/authorizer IS the bound MCP --actor; you cannot promote a record you created, and cannot act as another identity by passing a string. Reviewer/approver args, if sent, must equal the bound actor.

NameTypeReqDescription
approver_rolestring
dry_runboolean
memory_idstringyes
new_statusstringyes
reasonstringyes
reviewer_rolestring
transition_fromstringyes
transition_tostringyes

No output schema declared.

No examples provided.

memory.propose ~76

Append a CANDIDATE memory (proposal-only, via the sanctioned writer).

NameTypeReqDescription
confidencenumberyes
dry_runboolean
scopestringyes
source_pathsarrayyes
statementstringyes
subjectstringyes
typestringyes

No output schema declared.

No examples provided.

memory.search ~139

Search Procheiron memory records (read-only). Every row carries `trusted` and `trust_reason` — never read `status` as trust on its own. A record claiming active/validated is returned only when the audit log's latest transition backs that claim; filters like status='active' narrow the results and never bypass that check. Pass include_untrusted=true to also receive records that failed it (each one labelled with why).

NameTypeReqDescription
include_untrustedboolean
limitinteger
querystring
scopestring
statusstring
typestring

No output schema declared.

No examples provided.