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.

CP Memory

PYPI · CP-MEMORY-MCP · SCANNED SEP 21

Local-first, governable long-term memory for AI coding agents

Available components

+3 this week 70 Trust /100
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 setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1952 tokens (~48/item across 40 items; 40 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
  • Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 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
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "memory_remove" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 41 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the CP Memory MCP server?

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

pypi · cp-memory-mcp

# add to Claude Code
claude mcp add cjhuochai-cp-memory -- uvx cp-memory-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "cjhuochai-cp-memory": {
      "command": "uvx",
      "args": [
        "cp-memory-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "cjhuochai-cp-memory": {
      "command": "uvx",
      "args": [
        "cp-memory-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add cjhuochai-cp-memory -- uvx cp-memory-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cjhuochai-cp-memory": {
      "type": "local",
      "command": [
        "uvx",
        "cp-memory-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add cjhuochai-cp-memory --command uvx --arg cp-memory-mcp
# ~/.hermes/config.yaml
mcp_servers:
  cjhuochai-cp-memory:
    command: "uvx"
    args: ["cp-memory-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "cjhuochai-cp-memory": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "cp-memory-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add cjhuochai-cp-memory -t stdio -c uvx -a cp-memory-mcp
// mcp.json
{
  "mcpServers": {
    "cjhuochai-cp-memory": {
      "command": "uvx",
      "args": [
        "cp-memory-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.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 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.

  • 11 Sept 26 +4
    • Stability: unverified → 0.23 functional
  • 7 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 6 Sept 26 0
    • Security disclosure: fail → unverified functional
  • 5 Sept 26 +15
    • Malware scan: unverified → pass security
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 21 Sept 2026 · Analysed pypi/cp-memory-mcp@1.8.1

Provenance No attestation

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

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

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

Dependencies 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 40 exposed · ~1,900 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_add ~82

Add or update a memory fact. Supports explicit category and optional long-form content payload.

NameTypeReqDescription
categorystring
confidencestring
contentstring
content_typestring
entitystringyes
propertystringyes
tagsstring
valuestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_alias_add ~40

Add or update an alias for a canonical entity.

NameTypeReqDescription
aliasstringyes
entitystringyes
tagsstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_alias_list ~32

List aliases, optionally filtered by canonical entity.

NameTypeReqDescription
entitystring
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_auto_extract_cleanup ~73

Preview or apply cleanup for auto-extracted noise records that look like implementation explanations rather than real user memory. Prefer action=mark_wrong for safer governance; use delete only when you really want to remove rows.

NameTypeReqDescription
actionstring
dry_runboolean
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_conflicts ~29

Find possible conflicting memories, including duplicate facts and personal-memory contradictions.

NameTypeReqDescription
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_correct ~56

Mark a memory as corrected, stale, wrong, scoped, or confirmed; optionally replace its value.

NameTypeReqDescription
idstringyes
reasonstring
statusstringyes
valuestring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_decision_add ~53

Record an architecture or technical decision and mirror it into facts with strong metadata.

NameTypeReqDescription
contextstringyes
decisionstringyes
rationalestring
titlestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_decision_list ~25

List recorded decisions, most recent first.

NameTypeReqDescription
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_episode_consolidate ~53

Preview or apply conservative Episode consolidation into long-term personal memories.

NameTypeReqDescription
dry_runboolean
episode_idstringyes
limitinteger
subjectstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_explain ~43

Explain a memory record, including meta, payload, and relations.

NameTypeReqDescription
entitystring
idstring
propertystring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_governance_report ~49

Build a non-destructive governance acceptance report over the current memory.db, including auto-extract review queue, conflict samples, corrected samples, and restore probes.

NameTypeReqDescription
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_health ~24

Return CP Memory health, migration state, FTS state, and active task.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

memory_inspect ~51

Inspect a memory record in a user-friendly way, including where the preview, payload, and relations live.

NameTypeReqDescription
entitystring
idstring
propertystring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_link_add ~57

Create an explicit memory relation between two records.

NameTypeReqDescription
relationstringyes
source_idstringyes
source_kindstringyes
target_idstringyes
target_kindstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_link_list ~53

List explicit memory relations.

NameTypeReqDescription
relationstring
source_idstring
source_kindstring
target_idstring
target_kindstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_list ~31

List recent facts, optionally filtered by category.

NameTypeReqDescription
categorystring
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_maintenance ~49

Run memory maintenance: backfill meta, rebuild indexes, and optionally expire low-value records.

NameTypeReqDescription
dry_runboolean
expireboolean
limitinteger
NameTypeReqDescription
resultstringyes

No examples provided.

memory_personal_add ~132

Add or update a long-term personal assistant memory using Profile, Preference, Relationship, Ongoing, Episode, or BeliefDecision.

NameTypeReqDescription
confidencestring
detailsstring
evidence_countinteger
keystringyes
memory_typestringyes
scopestring
sensitivitystring
stability_scoreinteger
subjectstringyes
tagsstring
valid_fromstring
valid_untilstring
valuestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_personal_derive ~105

Derive a long-term personal memory from an existing Episode and link it back to the source episode.

NameTypeReqDescription
confidencestring
detailsstring
episode_idstringyes
evidence_countinteger
keystringyes
memory_typestringyes
stability_scoreinteger
subjectstringyes
tagsstring
valuestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_personal_list ~46

List personal assistant memories, optionally filtered by the six-model memory type.

NameTypeReqDescription
limitinteger
memory_typestring
subjectstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_personal_resolve ~90

Resolve a personal-memory conflict by confirming or merging one winner and marking other memories stale, wrong, or scoped with audit links.

NameTypeReqDescription
loser_idsstring
loser_statusstring
merged_valuestring
reasonstring
scopestring
valid_untilstring
winner_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_personal_review ~44

Return a user-facing personal memory review dashboard with counts, recent memories, conflicts, and consolidation candidates.

NameTypeReqDescription
limitinteger
subjectstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_probe ~31

Get all facts about an entity. Aliases resolve to the canonical entity first.

NameTypeReqDescription
entitystringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_recall ~78

CP Memory-first recall入口。任何记忆相关问题都先查 CP Memory 主库,再根据主库命中质量决定是否补查 Codex 自带 memory 作为辅助背景。

NameTypeReqDescription
allow_auxiliaryboolean
intentstring
limitinteger
querystringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_remove ~31

Delete a fact by ID, including its metadata, payload, and graph links.

NameTypeReqDescription
idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_restore_context ~39

Build a compact restored context for startup, history recovery, or project continuation.

NameTypeReqDescription
max_charsinteger
promptstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_review_apply ~61

Apply one explicit memory review action: confirm, wrong, stale, scoped, or skip. This never physically deletes memory.

NameTypeReqDescription
actionstringyes
idstringyes
reasonstring
scopestring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_review_digest ~48

Return a Markdown memory review digest with recent memories, pending auto-extracts, conflicts, stale candidates, and resolution suggestions.

NameTypeReqDescription
limitinteger
subjectstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_review_inbox ~43

Show a small actionable inbox for pending memory review. This previews items only and never deletes memory.

NameTypeReqDescription
limitinteger
subjectstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_schema ~20

Return CP Memory schema explanations and whether FTS is available.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

memory_search ~54

Search memories using FTS when available, with OR ranking by default or strict AND matching.

NameTypeReqDescription
categorystring
limitinteger
modestring
querystringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_stats ~26

Get memory statistics across facts, payloads, decisions, workflows, aliases, and relations.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

memory_task_done ~27

Mark the current task as complete with a result summary.

NameTypeReqDescription
resultstring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_task_get ~15

Get the current active task.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

memory_task_set ~30

Set the current active task.

NameTypeReqDescription
descriptionstring
task_namestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_touch ~32

Mark matching memories as accessed, optionally by IDs.

NameTypeReqDescription
idsstring
querystring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_update ~65

Update an existing fact value, confidence, category, or content payload.

NameTypeReqDescription
categorystring
confidencestring
contentstring
content_typestring
idstringyes
valuestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_workflow_get ~24

Get a saved workflow by name.

NameTypeReqDescription
namestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

memory_workflow_list ~21

List saved workflows.

NameTypeReqDescription
categorystring
NameTypeReqDescription
resultstringyes

No examples provided.

memory_workflow_save ~38

Save a reusable workflow or procedure.

NameTypeReqDescription
categorystring
namestringyes
stepsstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the CP Memory MCP server?

CP Memory is an MCP server listed in the public MCP registry as io.github.CJhuochai/cp-memory. Local-first, governable long-term memory for AI coding agents. This page covers its PyPI package (cp-memory-mcp).

Is the CP Memory MCP server safe to use?

CP Memory scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 CP Memory MCP server expose?

CP Memory exposes 40 tools: memory_schema, memory_add, memory_personal_add, memory_personal_derive, memory_episode_consolidate, and 35 more. Their descriptions and schemas cost roughly 1,900 tokens of context every time the server is loaded.

Is the CP Memory MCP server still maintained?

CP Memory is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.