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.

Total Agent Memory

PYPI · TOTAL-AGENT-MEMORY · SCANNED SEP 20

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

Available components

−9 this week 48 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 Security24
  • Malware scan not yet available for this package.Unverified
  • A critical CVE affects chromadb, and no fixed version has been published yet. View diagnostics → Fail
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 16 of 113 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 7122 tokens (~93/item across 76 items; 76 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage80
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 40% of tool parameters carry a description.Partial
Tool Safety79
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "memory_eval_locomo" implies "eval" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 76 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
Install

How do I install the Total Agent Memory MCP server?

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

pypi · total-agent-memory

# add to Claude Code
claude mcp add vbcherepanov-total-agent-memory -- uvx total-agent-memory
// .cursor/mcp.json
{
  "mcpServers": {
    "vbcherepanov-total-agent-memory": {
      "command": "uvx",
      "args": [
        "total-agent-memory"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "vbcherepanov-total-agent-memory": {
      "command": "uvx",
      "args": [
        "total-agent-memory"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add vbcherepanov-total-agent-memory -- uvx total-agent-memory
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vbcherepanov-total-agent-memory": {
      "type": "local",
      "command": [
        "uvx",
        "total-agent-memory"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add vbcherepanov-total-agent-memory --command uvx --arg total-agent-memory
# ~/.hermes/config.yaml
mcp_servers:
  vbcherepanov-total-agent-memory:
    command: "uvx"
    args: ["total-agent-memory"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "vbcherepanov-total-agent-memory": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "total-agent-memory"
      ]
    }
  }
}
# add to Vellum
assistant mcp add vbcherepanov-total-agent-memory -t stdio -c uvx -a total-agent-memory
// mcp.json
{
  "mcpServers": {
    "vbcherepanov-total-agent-memory": {
      "command": "uvx",
      "args": [
        "total-agent-memory"
      ]
    }
  }
}
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 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 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 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.

  • 17 Sept 26 −15
    • Malware scan: pass → unverified security
  • 16 Sept 26 +15
    • Malware scan: unverified → pass security
  • 15 Sept 26 −11
    • Malware scan: pass → unverified security
    • Stability: unverified → 0.27 functional
    • Package version: 13.0.4 → 14.0.0 functional
  • 12 Sept 26 +15
    • Malware scan: unverified → pass security
  • 8 Sept 26 −15
    • Malware scan: pass → unverified security
  • 7 Sept 26 57

    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 Sept 2026 · Analysed pypi/total-agent-memory@14.0.0

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 →

Vulnerabilities 8 findings
ID CVE Severity Vector Fix available
GHSA-2wm9-hf6c-p5cr CVE-2026-45830 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H no
GHSA-36p7-vc44-83pf CVE-2026-45833 critical no
GHSA-f4j7-r4q5-qw2c CVE-2026-45829 critical no
GHSA-xph7-9rjv-w5fr CVE-2026-45831 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H no
PYSEC-2026-311 CVE-2026-45829 none no
PYSEC-2026-3813 CVE-2026-45830 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H no
PYSEC-2026-3814 CVE-2026-45833 none no
PYSEC-2026-3815 CVE-2026-45831 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H no

Background: What a vulnerability scan can and cannot prove →

Dependencies 113 packages
Packages resolved 113
Stale 14
No linked repository 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 76 exposed · ~7,122 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_skill_get ~57

Find skills matching a trigger. Skills are learned procedures — HOW to do things.

NameTypeReqDescription
list_allboolean
namestringGet skill by exact name
triggerstringNatural language trigger to match

No output schema declared.

No examples provided.

memory_skill_update ~79

Record skill usage or refine a skill. Updates success rate and metrics.

NameTypeReqDescription
new_anti_patternstringAnti-pattern learned from failure
new_stepsarrayAdditional steps to add
notesstring
skill_idstringyesSkill ID
successbooleanyesWas the skill application successful?

No output schema declared.

No examples provided.

memory_stats ~40

Memory statistics with health metrics: sessions, knowledge by type/project, retention zones (active/archived/consolidated), stale records, storage size, config.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

memory_temporal_query ~152

v11.0 W1-C: deterministic temporal reasoning — Allen interval relations, duration arithmetic (days/weeks/months/years), and natural-language date normalization (en + ru). Pass op=relation|duration_between|normalize.

NameTypeReqDescription
astringISO datetime — duration_between
a_endstring
a_startstringISO datetime — relation only
anchorstringISO datetime anchor for relative phrases
bstring
b_endstring
b_startstring
langstring
opstringyes
phrasestringNatural-language date — normalize

No output schema declared.

No examples provided.

memory_timeline ~99

Browse session history. sessions_ago=N for 'N sessions ago', session_number=1 for first session, date_from/date_to for date ranges.

NameTypeReqDescription
date_fromstringYYYY-MM-DD
date_tostringYYYY-MM-DD
limitinteger
projectstring
querystring
session_numberinteger
sessions_agointeger

No output schema declared.

No examples provided.

memory_update ~62

Update existing knowledge. Finds old by search query, supersedes it, creates new version.

NameTypeReqDescription
findstringyesSearch query to find the old knowledge
new_contentstringyesNew content to replace with
reasonstringWhy updating

No output schema declared.

No examples provided.

memory_warmup ~40

v11.0: pre-load FastEmbed model and open the vector store, so the first save/search after process start doesn't pay model-load latency.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

memory_wiki_generate ~88

v10 — Render the per-project wiki digest (top decisions, active solutions, conventions, recent changes) as Markdown. Pass `project` to refresh one wiki, omit it to refresh all active projects. Files land in <MEMORY_DIR>/wikis/<project>.md and are deterministic (no LLM call).

NameTypeReqDescription
projectstringProject to refresh (omit for all)

No output schema declared.

No examples provided.

phase_transition ~51

v8.0: advance a task to the next phase.

NameTypeReqDescription
artifactsobject
new_phasestringyes
notesstring
task_idstringyes

No output schema declared.

No examples provided.

rule_set_phase ~95

Attach or remove a phase scope on a rule (v8.0 lazy rule loading). Tag-based: manages 'phase:<X>' on the rule's tags. phase=null clears the phase tag (rule becomes core — applies to every phase). Valid phases: van, plan, creative, build, reflect, archive.

NameTypeReqDescription
phasestring|nullPhase name or null to clear.
rule_idintegeryes

No output schema declared.

No examples provided.

save_decision ~166

v8.0: save a structured architectural decision (options + criteria matrix + rationale + discarded). Adds `structured` tag and a JSON blob in context. Use for Creative-phase outputs; plain type=decision memory_save still works.

NameTypeReqDescription
criteria_matrixobjectyescriterion -> {option_name: rating 0-5}
discardedarrayOption names rejected (subset of options - {selected})
optionsarrayyesOptions considered: [{name, pros[], cons[], unknowns[]}, ...]
projectstring
rationalestringyesWhy this option was chosen
selectedstringyesChosen option name (must be in options)
tagsarray
titlestringyesShort decision title

No output schema declared.

No examples provided.

save_intent ~94

Persist one user prompt into the `intents` table (same source as the UserPromptSubmit hook). Use when programmatically seeding intents — the hook covers normal interactive usage. Dedupes same prompt within 5 min per session.

NameTypeReqDescription
projectstringProject slug
promptstringyesUser prompt text as submitted
session_idstringSession id (defaults to current MCP session)

No output schema declared.

No examples provided.

search_intents ~65

Substring search over user prompts (LIKE). Returns newest match first. Useful for 'what did I ask about X' without mining transcripts.

NameTypeReqDescription
limitinteger
projectstring
querystringyesSubstring to match in prompt text

No output schema declared.

No examples provided.

self_error_log ~139

Log an error/failure for pattern analysis. Call AUTOMATICALLY when: bash command fails, wrong assumption discovered, API returns error, config issue found, loop detected, or any mistake occurs. System detects patterns (3+ same category) and suggests insights.

NameTypeReqDescription
categorystringyesError category for pattern grouping
contextstringWhat was being done when error occurred
descriptionstringyesWhat went wrong: symptom, expectation vs reality
fixstringHow it was fixed (empty if unresolved)
projectstring
severitystring
tagsarray

No output schema declared.

No examples provided.

self_insight ~172

Manage insights from error patterns (ExpeL-style). Actions: add (create, importance=2), upvote (+1), downvote (-1, auto-archive at 0), edit, list, promote (to rule when importance>=5 AND confidence>=0.8). Call 'add' when pattern detected. Call 'upvote' when insight confirmed again.

NameTypeReqDescription
actionstringyes
categorystringError category (for add)
contentstringInsight text (for add/edit)
contextstring
idintegerInsight ID (for upvote/downvote/edit/promote)
projectstring
source_error_idsarrayError IDs that spawned this (for add)
tagsarray

No output schema declared.

No examples provided.

self_patterns ~85

Analyze error patterns and self-improvement stats. Views: error_patterns (frequency, repeating 3+), insight_candidates (ready for promotion), rule_effectiveness (success rates, stale rules), improvement_trend (weekly errors), full_report (all). Call periodically to track improvement.

NameTypeReqDescription
daysinteger
projectstring
viewstring

No output schema declared.

No examples provided.

self_reflect ~107

Save a verbal self-reflection (Reflexion pattern). Call after completing a task or encountering difficulty. NOT for errors (use self_error_log). For meta-observations about strategy, approach effectiveness, process improvements.

NameTypeReqDescription
outcomestring
projectstring
reflectionstringyesWhat went well, what to improve, what to do differently
tagsarray
task_summarystringyesBrief description of what was done

No output schema declared.

No examples provided.

self_rules ~174

Manage behavioral rules (SOUL). Rules are promoted insights that shape agent behavior. Actions: list, fire (record relevance), rate (success=true/false), suspend, activate, retire, add_manual. Auto-suspend: success_rate < 0.2 after 10+ fires.

NameTypeReqDescription
actionstringyes
categorystringCategory (for add_manual)
contentstringRule text (for add_manual)
idintegerRule ID (for fire/rate/suspend/activate/retire)
priorityinteger1-10
projectstring
scopestringglobal | project:<name> | category:<name>
successbooleanFor rate: was rule helpful?
tagsarray

No output schema declared.

No examples provided.

self_rules_context ~142

Get active behavioral rules for current session. Call at SESSION START to load rules. Returns rules filtered by project and scope. v8.0: pass `phase` to lazy-load rules relevant to current task phase — core rules (no phase tag) + rules tagged phase:<X>. Cuts prompt tokens ~70%. After task completion, rate rules: self_rules(action='rate', id=X, success=true/false).

NameTypeReqDescription
categoriesarrayError categories relevant to current task
phasestringOptional: lazy-load only rules relevant to this phase (core + phase-specific). Omit to get all rules.
projectstring

No output schema declared.

No examples provided.

session_end ~132

End-of-session capture: summary + highlights + pitfalls + next_steps so the next session can resume cleanly. Set auto_compress=true to have the LLM generate the missing summary/next_steps/pitfalls from stored session artifacts (or from an optional `transcript`).

NameTypeReqDescription
auto_compressboolean
highlightsarray
next_stepsarray
open_questionsarray
pitfallsarray
projectstring
session_idstringyes
summarystring
transcriptstring

No output schema declared.

No examples provided.

session_init ~47

At session start: return the most recent unconsumed end-of-session summary with highlights / pitfalls / next_steps.

NameTypeReqDescription
mark_consumedboolean
projectstring

No output schema declared.

No examples provided.

task_create ~51

v8.0: start a task in `van` phase (auto-classifies level if missing).

NameTypeReqDescription
descriptionstringyes
levelinteger
task_idstringyes

No output schema declared.

No examples provided.

task_phases_list ~33

v8.0: list all phases of a task in chronological order.

NameTypeReqDescription
task_idstringyes

No output schema declared.

No examples provided.

workflow_learn ~66

Record a learned workflow (named sequence of steps) for future reuse.

NameTypeReqDescription
contextobject
descriptionstring
namestringyes
projectstring
stepsarrayyes
trigger_patternstring

No output schema declared.

No examples provided.

workflow_predict ~57

Predict outcome (success probability, avg duration) for a workflow by id OR by trigger keyword. Uses Laplace-smoothed success rate.

NameTypeReqDescription
projectstring
triggerstring
workflow_idstring

No output schema declared.

No examples provided.

workflow_track ~70

Record a workflow execution outcome. Outcome ∈ {success|failure|partial|aborted}. Aggregates update automatically.

NameTypeReqDescription
duration_msinteger
error_detailsstring
notesstring
outcomestringyes
workflow_idstringyes

No output schema declared.

No examples provided.

Common questions

What is the Total Agent Memory MCP server?

Total Agent Memory is an MCP server listed in the public MCP registry as io.github.vbcherepanov/total-agent-memory. Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall. This page covers its PyPI package (total-agent-memory).

Is the Total Agent Memory MCP server safe to use?

Total Agent Memory scores 48 out of 100 on VerifyMCP. We recorded 8 known advisories against it as of 20 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 Total Agent Memory MCP server expose?

Total Agent Memory exposes 76 tools: memory_recall, memory_timeline, memory_index_passages, memory_answer, memory_save, and 71 more. Their descriptions and schemas cost roughly 7,122 tokens of context every time the server is loaded.

Is the Total Agent Memory MCP server still maintained?

Total Agent Memory is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.