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

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

Available components

+18 this week 87 Trust /100

Last scanned (17 hours ago)

Scores higher than 90% of PyPI servers

Category Memory and Knowledge

Trust breakdown (7 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 → Why this is hard to 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 build step with no custom scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to logotheusneuro-cpu/procheiron-core). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 65 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
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.

  • 16 Oct 26 +16
    • Malware scan: unverified → pass ▲ security
    • Stability: 0.97 → pass security
  • 15 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
  • 14 Oct 26 +16
    • Malware scan: unverified → pass ▲ security
  • 12 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
  • 3 Oct 26 +12
    • Malware scan: unverified → pass ▲ security
    • Stability: pass → 0.80 functional
  • 2 Oct 26 +1
    • Stability: 0.97 → pass security
  • 30 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

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 16 Oct 2026 · Analysed pypi/procheiron@0.3.3

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo logotheusneuro-cpu/procheiron-core
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/logotheusneuro-cpu/procheiron-core/.github/workflows/release.yml@refs/tags/v0.3.3
Rekor log index 2421005057
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:f42c097374c38fe20fe7b9d20c61c4fb271585849b7df174bdbeb2ac53166830

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

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.

Install

How do I install the Procheiron MCP server?

Procheiron runs locally as a PyPI package, launched with uvx procheiron. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · procheiron

# add to Claude Code
claude mcp add logotheusneuro-cpu-procheiron -- uvx procheiron
Common questions

What is the Procheiron MCP server?

Procheiron is an MCP server listed in the public MCP registry as io.github.logotheusneuro-cpu/procheiron. Review gate for shared agent memory: an unreviewed or hand-edited memory is never served. This page covers its PyPI package (procheiron).

Is the Procheiron MCP server safe to use?

Procheiron scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Procheiron MCP server expose?

Procheiron exposes 4 tools: memory.search, memory.get, memory.propose, memory.promote. Their descriptions and schemas cost roughly 397 tokens of context every time the server is loaded.

Is the Procheiron MCP server still maintained?

Procheiron is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Procheiron MCP server under?

Procheiron declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.