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.

SuperMemory

PYPI · SUPERMEMORY-AGENT · SCANNED SEP 20

MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.

Available components

−15 this week 57 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 Security50
  • Malware scan not yet available for this package.Unverified
  • 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
  • 1 of 33 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
Schema Quality & AI Usability61
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (poor).Fail
  • Tool/resource definitions use about 1096 tokens (~36/item across 30 items; 29 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage40
  • 45% of tools have a non-trivial description (not blank, and not just the tool's name).Partial
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 29 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 30 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 SuperMemory MCP server?

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

pypi · supermemory-agent

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

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 +1
    • Stability: 0.97 → pass security
  • 16 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.

  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
  • 13 Sept 26 +15
    • Malware scan: unverified → pass security
  • 12 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 11 Sept 26 +1
    • Stability: 0.97 → pass security
  • 9 Sept 26 −14
    • Malware scan: pass → unverified 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 20 Sept 2026 · Analysed pypi/supermemory-agent@0.2.5

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 hatchling.build

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

Dependencies 33 packages
Packages resolved 33
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 29 exposed · ~1,087 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
add_policy ~35

Add a local policy rule.

NameTypeReqDescription
namespacestring
priorityinteger
rulestringyes

Structured output declared, but exposes no named fields.

No examples provided.

add_skill ~66

Add a reusable skill/workflow block.

NameTypeReqDescription
descriptionstringyes
metadata
namestringyes
namespacestring
stepsarrayyes
tools
versionstring
workflow

Structured output declared, but exposes no named fields.

No examples provided.

get_policies ~24

Return active policies visible to a namespace.

NameTypeReqDescription
namespacestring

Structured output declared, but exposes no named fields.

No examples provided.

get_skill ~23

Read a reusable skill by ID.

NameTypeReqDescription
skill_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.analytics ~5

No description provided.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

learn.evaluate ~13

No description provided.

NameTypeReqDescription
run_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.experiment ~30

No description provided.

NameTypeReqDescription
resource_idstringyes
traffic_splitnumber
variant_bstringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.feedback ~23

No description provided.

NameTypeReqDescription
comment
ratingstringyes
run_id

Structured output declared, but exposes no named fields.

No examples provided.

learn.improvements ~18

No description provided.

NameTypeReqDescription
agent_id
workflow_id

Structured output declared, but exposes no named fields.

No examples provided.

learn.policies ~6

No description provided.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

learn.reflect ~52

No description provided.

NameTypeReqDescription
auto_promoteboolean
event_ids
failure
fix
root_cause
step
suggestion
workflow

Structured output declared, but exposes no named fields.

No examples provided.

learn.retrieve ~35

No description provided.

NameTypeReqDescription
max_tokensinteger
namespace
querystringyes
step
workflow

Structured output declared, but exposes no named fields.

No examples provided.

learn.rollback ~29

No description provided.

NameTypeReqDescription
resource_idstringyes
resource_typestringyes
target_versionstringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.run.end ~27

No description provided.

NameTypeReqDescription
lessons_used
run_idstringyes
successbooleanyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.run.event ~62

No description provided.

NameTypeReqDescription
after
agent
before
event_typestringyes
intent
run_idstringyes
snippet
step
tags
workflow

Structured output declared, but exposes no named fields.

No examples provided.

learn.run.start ~34

No description provided.

NameTypeReqDescription
agent
agents
namespace
step
workflow_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.skills ~12

No description provided.

NameTypeReqDescription
querystringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.store ~13

No description provided.

NameTypeReqDescription
lesson_jsonstringyes

Structured output declared, but exposes no named fields.

No examples provided.

learn.telemetry ~45

No description provided.

NameTypeReqDescription
acceptedboolean
improved
lesson_idstringyes
run_id
telemetry_id
usedboolean

Structured output declared, but exposes no named fields.

No examples provided.

learn.validate ~32

No description provided.

NameTypeReqDescription
event_ids
failurestringyes
fixstringyes
root_cause

Structured output declared, but exposes no named fields.

No examples provided.

process_promotions ~25

Process pending validated lessons and promote passing items.

NameTypeReqDescription
limitinteger

Structured output declared, but exposes no named fields.

No examples provided.

record_correction ~69

Record a bounded correction signal.

NameTypeReqDescription
agent
domain
environment
language
namespacestring
payload
step
summarystringyes
tool
workflow

Structured output declared, but exposes no named fields.

No examples provided.

record_event ~84

Record a bounded significant event. Full transcripts should not be sent here.

NameTypeReqDescription
agent
domain
environment
event_typestringyes
language
namespacestring
payload
step
summarystringyes
tool
workflow

Structured output declared, but exposes no named fields.

No examples provided.

record_failure ~68

Record a bounded failure signal.

NameTypeReqDescription
agent
domain
environment
language
namespacestring
payload
step
summarystringyes
tool
workflow

Structured output declared, but exposes no named fields.

No examples provided.

reflect ~34

Create a candidate lesson from evidence events.

NameTypeReqDescription
event_idsarrayyes
lesson_text
suggestion

Structured output declared, but exposes no named fields.

No examples provided.

report_outcome ~57

Report telemetry for a retrieved lesson.

NameTypeReqDescription
acceptedbooleanyes
improvedbooleanyes
lesson_idstringyes
retrieval_id
run_id
usedbooleanyes

Structured output declared, but exposes no named fields.

No examples provided.

retrieve ~80

Retrieve policy-first, stage-aware lessons.

NameTypeReqDescription
agent
domain
environment
language
max_tokensinteger
namespacestring
querystringyes
step
tool
top_kinteger
workflow

Structured output declared, but exposes no named fields.

No examples provided.

search_skills ~44

Search reusable skills visible to a namespace.

NameTypeReqDescription
namespacestring
querystringyes
top_kinteger
workflow

Structured output declared, but exposes no named fields.

No examples provided.

validate ~42

Validate a lesson candidate and enqueue approved lessons for promotion.

NameTypeReqDescription
candidate_lesson
event_ids
metadata
reflection_id

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the SuperMemory MCP server?

SuperMemory is an MCP server listed in the public MCP registry as io.github.YashvantHange/supermemory. MCP-first agent learning: capture failures, validate lessons, retrieve context, improve. This page covers its PyPI package (supermemory-agent).

Is the SuperMemory MCP server safe to use?

SuperMemory scores 57 out of 100 on VerifyMCP. We found no known CVEs affecting 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 SuperMemory MCP server expose?

SuperMemory exposes 29 tools: record_event, record_failure, record_correction, reflect, validate, and 24 more. Their descriptions and schemas cost roughly 1,087 tokens of context every time the server is loaded.

Is the SuperMemory MCP server still maintained?

SuperMemory 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.