io.github.jyswee/agenticmemory
REMOTE · MCP.AGENTICMEMORY.AI · 2 COMPONENTS
Persistent memory for AI agents — history, context, semantic search, queues. 46 tools, stdio/SSE.
Available components
Last scanned (17 hours ago)
Scores higher than 58% of remote servers
Reachable. Last reached 4 Nov 2026.
Category Memory and Knowledge
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (memory_store). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 3158 tokens (~68/item across 46 items; 46 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 46 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
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.
- 4 Nov 26 0
- Stability: pass → 0.97 functional
- 24 Oct 26 +1
- Stability: fail → pass ▲ security
- 30 Sept 26 0
- Server version: 1.2.0 → 1.3.0 functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 0
- Stability: pass → fail ▼ security
- Tool “entry_add” was removed ▼ security
- New tool “webhook”, which the server declares destructive security
- New tool “thread”, which the server declares destructive security
- New tool “stream_group”, which the server declares destructive security
- New tool “stream_delete”, which the server declares destructive security
- New tool “stream_append”, which the server declares destructive security
- New tool “state_set”, which the server declares destructive security
- New tool “space_import”, which the server declares destructive security
- New tool “shared_memory”, which the server declares destructive security
- New tool “scratchpad_set”, which the server declares destructive security
- New tool “queue_nack”, which the server declares destructive security
- New tool “queue_lease”, which the server declares destructive security
- New tool “queue_dlq”, which the server declares destructive security
- New tool “queue_ack”, which the server declares destructive security
- New tool “kv_string”, which the server declares destructive security
- New tool “kv_set”, which the server declares destructive security
- New tool “kv_hash”, which the server declares destructive security
- New tool “knowledge”, which the server declares destructive security
- New tool “entry”, which the server declares destructive security
- New tool “entries_add_batch”, which the server declares destructive security
- New tool “entity”, which the server declares destructive security
- Schema quality: 52 → 68 ▼ functional
- Server version: 1.1.3 → 1.2.0 functional
- New tool “entities_list” functional
- New tool “usage_get” functional
- New tool “threads_list” functional
- New tool “stream_read” functional
- New tool “stream_info” functional
- New tool “state_get” functional
- New tool “spaces_get” functional
- New tool “space_export” functional
- New tool “scratchpad_get” functional
- New tool “memory_bootstrap_batch” functional
- “context_set” added an optional parameter “ttl” cosmetic
- “memory_recall” added an optional parameter “before” cosmetic
- “memory_search” added an optional parameter “includeEntities” cosmetic
- “memory_search” added an optional parameter “scope” cosmetic
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
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 4 Nov 2026 · Probed https://mcp.agenticmemory.ai/sse
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agenticmemory.ai | CN=YR2,O=Let's Encrypt,C=US | 6 Sept 2026 | 5 Dec 2026 | RSA 4096 | SHA256-RSA | 6b8854f26f41228a9b69cce0bd50961d460 |
| SANs: *.agenticmemory.ai, agenticmemory.ai | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.agenticmemory.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 1814, 3799 | 8, 8 | Verified |
| agenticmemory.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| sse | https://mcp.agenticmemory.ai/sse | Verified | 200 | |
| http (plaintext) | http://mcp.agenticmemory.ai/sse | HTTPS enforced | 301 | https://mcp.agenticmemory.ai/sse |
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 →
context_delete ~35
Delete a context key.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Context key to delete |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| deleted | boolean | yes | True when the key was deleted |
No examples provided.
context_get ~36
Get a context value by key.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Context key name |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| encrypted | boolean | – | True if the space is end-to-end encrypted (value is ciphertext) |
| key | string | yes | The requested key |
| value | – | – | The stored value (string, number, object, or array) |
No examples provided.
context_list ~29
List all context keys and values in a space.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| context | object | yes | Map of every context key to its stored value |
| encrypted | boolean | – | True if the space is end-to-end encrypted (values are ciphertext) |
No examples provided.
context_set ~71
Set a key-value context entry. Stores structured data (JSON or string).
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Context key name |
| spaceId | string | yes | Memory space ID |
| ttl | number | – | Optional TTL in seconds |
| value | – | yes | Value to store (string, number, object, array) |
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | The key that was set |
| value | – | – | The stored value (string, number, object, or array) |
No examples provided.
entities_list ~56
List entities in a memory space, optionally filtered.
| Name | Type | Req | Description |
|---|---|---|---|
| knowsContains | string | – | Filter: entities that know this fact |
| namePrefix | string | – | Filter by name prefix |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
entity ~101
Entity (knowledge-graph node) operations: upsert (create), get, update, delete.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| doesNotKnow | array | – | Facts this entity does NOT know (upsert/update) |
| knows | array | – | Facts this entity knows (upsert/update) |
| name | string | yes | Entity name |
| role | string | – | Entity role (upsert) |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
entries_add_batch ~50
Append multiple journal entries in one call.
| Name | Type | Req | Description |
|---|---|---|---|
| entries | array | yes | Array of {title, content, type?, tags?, source?} entries |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
entries_list ~57
List long-term memory entries. Filter by tags.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max entries (default: 20) |
| spaceId | string | yes | Memory space ID |
| tags | string | – | Comma-separated tags to filter by |
| Name | Type | Req | Description |
|---|---|---|---|
| encrypted | boolean | – | True if the space is end-to-end encrypted (content is ciphertext) |
| entries | array | yes | Matching long-term entries |
No examples provided.
entry ~156
Single-entry operations on the tagged/versioned journal: add, get, update, versions, restore.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| content | string | – | Entry body (add/update) |
| entryId | string | – | Entry ID (required for get/update/versions/restore) |
| reason | string | – | Reason for the update (update) |
| source | string | – | Source attribution (add/update) |
| spaceId | string | yes | Memory space ID |
| tags | array | – | Tags (add/update) |
| title | string | – | Entry title (add) |
| type | string | – | Entry type: extraction | summary | decision | artifact (add) |
| version | number | – | Version number to restore (restore) |
Structured output declared, but exposes no named fields.
No examples provided.
knowledge ~125
Knowledge-base operations: create (with documents), list, delete, query (smart retrieval).
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| description | string | – | KB description (create) |
| documents | array | – | Documents to index (create) |
| kbId | string | – | KB ID (delete/query) |
| limit | number | – | Max results (query) |
| name | string | – | KB name (create) |
| query | string | – | Query text (query) |
| slug | string | – | KB slug (create/query) |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
kv_hash ~157
Hash operations (Redis-hash semantics, write-through durable): set, get (whole hash), keys, get_field, del_field, delete, setnx (atomic set-if-absent), cas (atomic compare-and-set).
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| deleteField | boolean | – | CAS: delete the field instead of setting (cas) |
| expected | – | – | Expected current value (cas — omit to require absent) |
| field | string | – | Single field (get_field/del_field/setnx/cas) |
| fields | object | – | Fields to set (set) |
| name | string | yes | Hash name |
| spaceId | string | yes | Memory space ID |
| value | – | – | Value (setnx/cas) |
Structured output declared, but exposes no named fields.
No examples provided.
kv_set ~78
Set operations (Redis-set semantics): add, members (with size), contains, remove, delete.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| member | string | – | Single member (contains) |
| members | array | – | Members (add/remove) |
| name | string | yes | Set name |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
kv_string ~84
String operations with optional TTL (survives rebuild): set, get (includes remaining ttlMs), delete.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| name | string | yes | String key name |
| spaceId | string | yes | Memory space ID |
| ttlSeconds | number | – | TTL in seconds (set) |
| value | string | – | Value to set (set) |
Structured output declared, but exposes no named fields.
No examples provided.
memory_bootstrap ~89
Load full context in one call: recent messages, entries, context, scratchpad. Run this at session start.
| Name | Type | Req | Description |
|---|---|---|---|
| entries | number | – | Number of entries to include (default: 10) |
| messages | number | – | Number of messages to include (default: 20) |
| query | string | – | Semantic query for relevant entries |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| activeThreads | array | – | Active conversation threads |
| contextEncoding | string | – | Context encoding mode (json or lln) |
| encryption | string | – | Encryption mode: none, managed, or e2e |
| entities | array | – | Known entities in the space |
| llnPrimer | string | – | LLN primer mode (inline, system, or none) |
| recentEntries | array | – | Most recent long-term entries |
| recentMessages | array | – | Most recent messages |
| semanticEntries | array | – | Entries matched by the optional semantic query |
| shared | object | – | Shared world context visible to all agents in the space |
| state | object | – | Current working state for the space |
No examples provided.
memory_bootstrap_batch ~97
Parallel bulk fetch: named context keys, entities, and optional semantic results in one call.
| Name | Type | Req | Description |
|---|---|---|---|
| entities | array | – | Entity names to fetch |
| entriesLimit | number | – | Max entries to include |
| keys | array | – | Context keys to fetch |
| query | string | – | Semantic query (with semantic=true) |
| semantic | boolean | – | Include semantic search results |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
memory_clear ~27
Clear all messages in a memory space.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| cleared | boolean | yes | True when messages were cleared |
No examples provided.
memory_recall ~63
Recall recent messages from conversation history. Returns newest first.
| Name | Type | Req | Description |
|---|---|---|---|
| before | string | – | Cursor: return messages before this message ID |
| limit | number | – | Number of messages to return (default: 20) |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| encrypted | boolean | – | True if the space is end-to-end encrypted (content is ciphertext) |
| messages | array | yes | Recalled messages, newest first |
No examples provided.
memory_search ~97
Semantic search across past conversations. Finds by meaning, not keywords.
| Name | Type | Req | Description |
|---|---|---|---|
| includeEntities | boolean | – | Include entity matches in results |
| limit | number | – | Max results (default: 10) |
| query | string | yes | Natural language search query |
| scope | string | – | Search scope: all | messages | entries | entities |
| spaceId | string | yes | Memory space ID |
| tags | array | – | Filter by tags |
| Name | Type | Req | Description |
|---|---|---|---|
| count | number | yes | Number of results returned |
| results | array | yes | Matching entries ranked by semantic relevance |
No examples provided.
memory_store ~62
Store a message in conversation history. Use for remembering what just happened.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | Message content |
| role | string | – | Role: user, assistant, system, tool (default: user) |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| _id | string | – | Message ID |
| content | string | – | Message text |
| createdAt | string | – | ISO 8601 creation timestamp |
| metadata | object | – | Optional caller-supplied metadata |
| role | string | – | Message role: user, assistant, system, or tool |
| seq | number | – | Monotonic sequence number within the space |
| spaceId | string | – | Owning memory space ID |
No examples provided.
memory_store_batch ~41
Store multiple messages at once.
| Name | Type | Req | Description |
|---|---|---|---|
| messages | array | yes | Array of {role, content} messages |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| messages | array | yes | The stored messages |
No examples provided.
queue_ack ~54
Acknowledge a leased envelope (deletes it permanently).
| Name | Type | Req | Description |
|---|---|---|---|
| leaseToken | string | yes | Lease token from queue_lease |
| queue | string | yes | Queue name |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
queue_dlq ~98
Dead-letter queue operations: push a failed envelope, or list DLQ items.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| envelope | object | – | Envelope to dead-letter (push) |
| limit | number | – | Max items (list) |
| offset | number | – | Offset (list) |
| queue | string | yes | Queue name |
| reason | string | – | Failure reason (push) |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
queue_lease ~104
Non-destructive lease (at-least-once): take the oldest envelope with a visibility timeout. Returns {item, leaseToken, deadline}. Ack with queue_ack, requeue with queue_nack.
| Name | Type | Req | Description |
|---|---|---|---|
| queue | string | yes | Queue name |
| spaceId | string | yes | Memory space ID |
| visibilitySeconds | number | – | Visibility timeout before auto-requeue |
| wait | number | – | Long-poll seconds, 0-25 (default 0) |
Structured output declared, but exposes no named fields.
No examples provided.
queue_nack ~59
Negative-acknowledge a leased envelope (requeues it to the tail).
| Name | Type | Req | Description |
|---|---|---|---|
| leaseToken | string | yes | Lease token from queue_lease |
| queue | string | yes | Queue name |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
queue_peek ~43
Peek at a queue without consuming: returns length and the head envelope.
| Name | Type | Req | Description |
|---|---|---|---|
| queue | string | yes | Queue name |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| head | object|null | – | The head envelope without consuming it, or null if empty |
| length | number | – | Current queue length |
| queue | string | yes | Queue 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.
| Name | Type | Req | Description |
|---|---|---|---|
| queue | string | yes | Queue name |
| spaceId | string | yes | Memory space ID |
| wait | number | – | Long-poll seconds, 0-25 (default: 0 = return immediately) |
| Name | Type | Req | Description |
|---|---|---|---|
| empty | boolean | – | True when the queue was empty |
| encrypted | boolean | – | True if the space is end-to-end encrypted (item is ciphertext) |
| item | object|null | – | The dequeued envelope, or null if the queue was empty |
| queue | string | yes | Queue 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.
| Name | Type | Req | Description |
|---|---|---|---|
| envelope | object | yes | JSON envelope to enqueue (opaque to the server) |
| queue | string | yes | Queue name (lowercase alphanumeric plus . _ : -, max 64 chars) |
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| length | number | yes | Queue length after the push |
| queue | string | yes | Queue name |
| queued | boolean | yes | True when the envelope was enqueued |
No examples provided.
scratchpad_get ~30
Get the scratchpad content from a memory space.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
scratchpad_set ~50
Set the scratchpad content for a memory space (ephemeral working memory).
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Scratchpad data (any JSON-serializable value) |
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
shared_memory ~84
Shared world-memory (one-write, all-see) operations: set, get, list, delete.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| key | string | – | Shared key (required for set/get/delete) |
| spaceId | string | yes | Memory space ID |
| ttl | number | – | TTL in seconds (set) |
| value | – | – | Value to set (set) |
Structured output declared, but exposes no named fields.
No examples provided.
space_export ~39
Export all data in a space (all primitives, schema v2) as a restorable payload.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
space_import ~66
Restore a space from an export payload. Mode: empty-only (default), merge, or replace.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | Import mode (default empty-only) |
| payload | object | yes | Export payload (from space_export) |
| spaceId | string | yes | Target memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
spaces_create ~33
Create a new memory space.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Space name |
| slug | string | yes | URL-safe slug |
| Name | Type | Req | Description |
|---|---|---|---|
| space | object | yes | – |
No examples provided.
spaces_get ~30
Get a single memory space (config, usage counters).
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| Name | Type | Req | Description |
|---|---|---|---|
| space | object | – | – |
No examples provided.
spaces_list ~18
List all memory spaces owned by this API key.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| spaces | array | yes | Every memory space owned by the caller |
No examples provided.
state_get ~28
Get a space's single JSON state snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
Structured output declared, but exposes no named fields.
No examples provided.
state_set ~43
Replace a space's single JSON state snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| state | object | yes | The full state object (replaces existing) |
Structured output declared, but exposes no named fields.
No examples provided.
stream_append ~70
Append an entry to a stream (XADD). Returns the entry ID.
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Entry data (flat object) |
| maxlen | number | – | Approximate max stream length (trim) |
| spaceId | string | yes | Memory space ID |
| stream | string | yes | Stream name |
Structured output declared, but exposes no named fields.
No examples provided.
stream_delete ~40
Delete a stream entirely (hot + durable) — irreversible.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| stream | string | yes | Stream name |
Structured output declared, but exposes no named fields.
No examples provided.
stream_group ~197
Consumer-group operations on a stream: create, destroy, read (XREADGROUP), ack (XACK), pending (XPENDING), claim (XCLAIM/XAUTOCLAIM).
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| consumer | string | – | Consumer name (read/pending/claim) |
| count | number | – | Max entries (read/pending/claim) |
| from | string | – | Start position for create (default $ = new entries only, use 0 for all) |
| group | string | yes | Consumer group name |
| ids | array | – | Entry IDs (ack/claim) |
| minIdleMs | number | – | Min idle ms before claim (claim) |
| spaceId | string | yes | Memory space ID |
| start | string | – | Autoclaim scan start (claim) |
| stream | string | yes | Stream name |
| waitSeconds | number | – | Long-poll seconds ≤25 (read) |
Structured output declared, but exposes no named fields.
No examples provided.
stream_info ~44
Stream info: length and consumer groups (XLEN + XINFO GROUPS).
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| stream | string | yes | Stream name |
Structured output declared, but exposes no named fields.
No examples provided.
stream_read ~90
Ranged read from a stream (XRANGE/XREVRANGE).
| Name | Type | Req | Description |
|---|---|---|---|
| count | number | – | Max entries |
| end | string | – | End ID (default +) |
| reverse | boolean | – | Read newest-first (XREVRANGE) |
| spaceId | string | yes | Memory space ID |
| start | string | – | Start ID (default -) |
| stream | string | yes | Stream name |
Structured output declared, but exposes no named fields.
No examples provided.
thread ~101
Thread (conversation grouping) operations: create, get, update, delete.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| metadata | object | – | Metadata (create) |
| name | string | – | Thread name (create/update) |
| spaceId | string | yes | Memory space ID |
| status | string | – | Thread status (update) |
| summary | string | – | Thread summary (update) |
| threadId | string | – | Thread ID (required for get/update/delete) |
Structured output declared, but exposes no named fields.
No examples provided.
threads_list ~41
List threads in a memory space, optionally filtered by status.
| Name | Type | Req | Description |
|---|---|---|---|
| spaceId | string | yes | Memory space ID |
| status | string | – | Filter by status |
Structured output declared, but exposes no named fields.
No examples provided.
usage_get ~19
Get current usage vs plan limits for the authenticated tenant.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
webhook ~98
Per-space webhook subscriptions: create, list, delete.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operation |
| events | array | – | Event types to subscribe to (create) |
| filter | object | – | Event filter (create) |
| hookId | string | – | Webhook ID (delete) |
| secret | string | – | Signing secret (create) |
| spaceId | string | yes | Memory space ID |
| url | string | – | Webhook URL (create) |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the io.github.jyswee/agenticmemory MCP server?
io.github.jyswee/agenticmemory is a hosted endpoint at https://mcp.agenticmemory.ai/sse, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.agenticmemory.ai
claude mcp add --transport http jyswee-agenticmemory 'https://mcp.agenticmemory.ai/sse'
What is the io.github.jyswee/agenticmemory MCP server?
io.github.jyswee/agenticmemory is an MCP server listed in the public MCP registry as io.github.jyswee/agenticmemory. Persistent memory for AI agents, history, context, semantic search, queues. 46 tools, stdio/SSE. This page covers its hosted endpoint (https://mcp.agenticmemory.ai/sse).
Is the io.github.jyswee/agenticmemory MCP server safe to use?
io.github.jyswee/agenticmemory scores 72 out of 100 on VerifyMCP. 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 io.github.jyswee/agenticmemory MCP server expose?
io.github.jyswee/agenticmemory exposes 46 tools: memory_store, memory_store_batch, memory_recall, memory_clear, memory_search, and 41 more. Their descriptions and schemas cost roughly 3,158 tokens of context every time the server is loaded.
Does the io.github.jyswee/agenticmemory MCP server require authentication?
No. We connected to io.github.jyswee/agenticmemory without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the io.github.jyswee/agenticmemory MCP server still maintained?
io.github.jyswee/agenticmemory is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.