Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.
Warning

Malware flagged

A supply-chain scanner flagged a high-severity malware risk in this package. Treat it as unsafe to install until the finding is cleared. See Supply Chain Security in the trust breakdown.

io.github.jyswee/agenticmemory

NPM · AGMRY · 2 COMPONENTS · SCANNED AUG 3

Persistent memory for AI agents — history, context, semantic search, queues. 17 tools, stdio/SSE.

−12 this week 48 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 Security55
  • Malware check failed: a supply-chain vendor flagged a high-severity malware risk. See how to fix → Fail
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability71
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 895 tokens (~52/item across 17 items; 17 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

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.

npm · agmry

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

  • 2 Aug 26 +1
    • Malware scan: unverified → fail security
  • 31 Jul 26 −11
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −2
    • Malware scan: fail → unverified security
    • Malware indicator gptMalware:QgESvOPDHF_L2DproytMWfrVYYre12tuIKkPe6bglQFU cleared security
    • Malware indicator gptMalware:QpemHmEw_G-J-q22oWn5Xy1F75GijPQDpPznTpqefbTk cleared security
    • Malware indicator gptMalware:QrgejRIxLENrpbANYiUQyf7u7xHA9xmFxEwnbdonFKqg cleared security
  • 27 Jul 26 +33
    • Tool coverage: unverified → 100 functional
    • First check of Schema quality: pass functional
    • First check of Tool coverage: 100 functional
    • First check of Tool coverage: 100 functional
    • First check of Schema quality: good functional
    • First check of Schema quality: fail functional
  • 26 Jul 26 27

    First indexed and scored.

    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 0 packages

0 packages in the resolved dependency tree.

MCP tools — 17 exposed · ~895 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
context_delete ~35

Delete a context key.

NameTypeReqDescription
keystringyesContext key to delete
spaceIdstringyesMemory space ID
NameTypeReqDescription
deletedbooleanyesTrue when the key was deleted

No examples provided.

context_get ~36

Get a context value by key.

NameTypeReqDescription
keystringyesContext key name
spaceIdstringyesMemory space ID
NameTypeReqDescription
encryptedbooleanTrue if the space is end-to-end encrypted (value is ciphertext)
keystringyesThe requested key
valueThe stored value (string, number, object, or array)

No examples provided.

context_list ~29

List all context keys and values in a space.

NameTypeReqDescription
spaceIdstringyesMemory space ID
NameTypeReqDescription
contextobjectyesMap of every context key to its stored value
encryptedbooleanTrue if the space is end-to-end encrypted (values are ciphertext)

No examples provided.

context_set ~60

Set a key-value context entry. Stores structured data (JSON or string).

NameTypeReqDescription
keystringyesContext key name
spaceIdstringyesMemory space ID
valueyesValue to store (string, number, object, array)
NameTypeReqDescription
keystringyesThe key that was set
valueThe stored value (string, number, object, or array)

No examples provided.

entries_list ~57

List long-term memory entries. Filter by tags.

NameTypeReqDescription
limitnumberMax entries (default: 20)
spaceIdstringyesMemory space ID
tagsstringComma-separated tags to filter by
NameTypeReqDescription
encryptedbooleanTrue if the space is end-to-end encrypted (content is ciphertext)
entriesarrayyesMatching long-term entries

No examples provided.

entry_add ~82

Add a long-term memory entry (summary, decision, extraction, artifact).

NameTypeReqDescription
contentstringEntry content
spaceIdstringyesMemory space ID
tagsarrayTags for filtering
titlestringyesEntry title
typestringType: extraction, summary, decision, artifact (default: extraction)
NameTypeReqDescription
entryobjectyes

No examples provided.

memory_bootstrap ~89

Load full context in one call: recent messages, entries, context, scratchpad. Run this at session start.

NameTypeReqDescription
entriesnumberNumber of entries to include (default: 10)
messagesnumberNumber of messages to include (default: 20)
querystringSemantic query for relevant entries
spaceIdstringyesMemory space ID
NameTypeReqDescription
activeThreadsarrayActive conversation threads
contextEncodingstringContext encoding mode (json or lln)
encryptionstringEncryption mode: none, managed, or e2e
entitiesarrayKnown entities in the space
llnPrimerstringLLN primer mode (inline, system, or none)
recentEntriesarrayMost recent long-term entries
recentMessagesarrayMost recent messages
semanticEntriesarrayEntries matched by the optional semantic query
sharedobjectShared world context visible to all agents in the space
stateobjectCurrent working state for the space

No examples provided.

memory_clear ~27

Clear all messages in a memory space.

NameTypeReqDescription
spaceIdstringyesMemory space ID
NameTypeReqDescription
clearedbooleanyesTrue when messages were cleared

No examples provided.

memory_recall ~48

Recall recent messages from conversation history. Returns newest first.

NameTypeReqDescription
limitnumberNumber of messages to return (default: 20)
spaceIdstringyesMemory space ID
NameTypeReqDescription
encryptedbooleanTrue if the space is end-to-end encrypted (content is ciphertext)
messagesarrayyesRecalled messages, newest first

No examples provided.

memory_search ~67

Semantic search across past conversations. Finds by meaning, not keywords.

NameTypeReqDescription
limitnumberMax results (default: 10)
querystringyesNatural language search query
spaceIdstringyesMemory space ID
tagsarrayFilter by tags
NameTypeReqDescription
countnumberyesNumber of results returned
resultsarrayyesMatching entries ranked by semantic relevance

No examples provided.

memory_store ~62

Store a message in conversation history. Use for remembering what just happened.

NameTypeReqDescription
contentstringyesMessage content
rolestringRole: user, assistant, system, tool (default: user)
spaceIdstringyesMemory space ID
NameTypeReqDescription
_idstringMessage ID
contentstringMessage text
createdAtstringISO 8601 creation timestamp
metadataobjectOptional caller-supplied metadata
rolestringMessage role: user, assistant, system, or tool
seqnumberMonotonic sequence number within the space
spaceIdstringOwning memory space ID

No examples provided.

memory_store_batch ~41

Store multiple messages at once.

NameTypeReqDescription
messagesarrayyesArray of {role, content} messages
spaceIdstringyesMemory space ID
NameTypeReqDescription
messagesarrayyesThe stored messages

No examples provided.

queue_peek ~43

Peek at a queue without consuming: returns length and the head envelope.

NameTypeReqDescription
queuestringyesQueue name
spaceIdstringyesMemory space ID
NameTypeReqDescription
headobject|nullThe head envelope without consuming it, or null if empty
lengthnumberCurrent queue length
queuestringyesQueue name

No examples provided.

queue_pop ~84

Dequeue the oldest envelope from a FIFO queue (returns null if empty). Set wait (max 25s) to long-poll for the next envelope.

NameTypeReqDescription
queuestringyesQueue name
spaceIdstringyesMemory space ID
waitnumberLong-poll seconds, 0-25 (default: 0 = return immediately)
NameTypeReqDescription
emptybooleanTrue when the queue was empty
encryptedbooleanTrue if the space is end-to-end encrypted (item is ciphertext)
itemobject|nullThe dequeued envelope, or null if the queue was empty
queuestringyesQueue name

No examples provided.

queue_push ~84

Enqueue a JSON envelope onto a FIFO queue in a memory space. Use to send work/events to other agents sharing the space.

NameTypeReqDescription
envelopeobjectyesJSON envelope to enqueue (opaque to the server)
queuestringyesQueue name (lowercase alphanumeric plus . _ : -, max 64 chars)
spaceIdstringyesMemory space ID
NameTypeReqDescription
lengthnumberyesQueue length after the push
queuestringyesQueue name
queuedbooleanyesTrue when the envelope was enqueued

No examples provided.

spaces_create ~33

Create a new memory space.

NameTypeReqDescription
namestringyesSpace name
slugstringyesURL-safe slug
NameTypeReqDescription
spaceobjectyes

No examples provided.

spaces_list ~18

List all memory spaces owned by this API key.

Input schema present but exposes no named parameters.

NameTypeReqDescription
spacesarrayyesEvery memory space owned by the caller

No examples provided.