Skip to content

agenticmemory MCP server

io.github.jyswee/agenticmemoryjysweessev1.10.0Scanned

Persistent memory for AI agents — history, context, semantic search, queues. 46 tools, stdio/SSE.

46 tools: 28 can delete or cancel things, 6 change things and 12 only read.

Tools: 28 delete, 0 irreversible, 6 write, 12 read.
  • Reads private data · 2
  • Reads text others write · 46
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

34 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the agenticmemory MCP server can do

The agenticmemory MCP server is published by the GitHub account jyswee. It has 46 tools. It can delete or cancel things (28 tools: memory_store, memory_store_batch, memory_clear, context_set and 24 more) and create or change data (6 tools: memory_recall, queue_peek, memory_bootstrap, memory_bootstrap_batch and 2 more). 12 tools only read.

2 tools read private data (memory_search and threads_list); 46 tools bring in text other people can write (memory_store, memory_store_batch, memory_recall and 43 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 1.10.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

46 tools

Deletes or cancels 28Claude Code: deny
  • context_deleteDelete a context key.Reads text others writeNo findings

    Why it is in this group

    • The name "context_delete" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Delete a context key.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • context_setSet a key-value context entry.Reads text others writeNo findings

    Why it is in this group

    • The name "context_set" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Set a key-value context entry. Stores structured data (JSON or string).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • entityEntity (knowledge-graph node) operations: upsert (create), get, update, delete.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Entity (knowledge-graph node) operations: upsert (create), get, update, delete.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • entries_add_batchAppend multiple journal entries in one call.Reads text others writeNo findings

    Why it is in this group

    • The name "entries_add_batch" says "add": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Append multiple journal entries in one call.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • entrySingle-entry operations on the tagged/versioned journal: add, get, update, versions, restore.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Single-entry operations on the tagged/versioned journal: add, get, update, versions, restore.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • knowledgeKnowledge-base operations: create (with documents), list, delete, query (smart retrieval).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Knowledge-base operations: create (with documents), list, delete, query (smart retrieval).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • kv_hashHash 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)…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • kv_setSet operations (Redis-set semantics): add, members (with size), contains, remove, delete.Reads text others writeNo findings

    Why it is in this group

    • The name "kv_set" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Set operations (Redis-set semantics): add, members (with size), contains, remove, delete.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • kv_stringString operations with optional TTL (survives rebuild): set, get (includes remaining ttlMs), delete.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    String operations with optional TTL (survives rebuild): set, get (includes remaining ttlMs), delete.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • memory_clearClear all messages in a memory space.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Clear all messages in a memory space.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • memory_storeStore a message in conversation history.Reads text others writeNo findings

    Why it is in this group

    • The name "memory_store" says "store": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Store a message in conversation history. Use for remembering what just happened.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • memory_store_batchStore multiple messages at once.Reads text others writeNo findings

    Why it is in this group

    • The name "memory_store_batch" says "store": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Store multiple messages at once.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • queue_ackAcknowledge a leased envelope (deletes it permanently).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Acknowledge a leased envelope (deletes it permanently).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • queue_dlqDead-letter queue operations: push a failed envelope, or list DLQ items.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Dead-letter queue operations: push a failed envelope, or list DLQ items.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • queue_leaseNon-destructive lease (at-least-once): take the oldest envelope with a visibility timeout.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • queue_nackNegative-acknowledge a leased envelope (requeues it to the tail).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Negative-acknowledge a leased envelope (requeues it to the tail).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • queue_popDequeue the oldest envelope from a FIFO queue (returns null if empty).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Dequeue the oldest envelope from a FIFO queue (returns null if empty). Set wait (max 25s) to long-poll for the next envelope.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • queue_pushEnqueue a JSON envelope onto a FIFO queue in a memory space.Reads text others writeNo findings

    Why it is in this group

    • The name "queue_push" says "push": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Enqueue a JSON envelope onto a FIFO queue in a memory space. Use to send work/events to other agents sharing the space.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • scratchpad_setSet the scratchpad content for a memory space (ephemeral working memory).Reads text others writeNo findings

    Why it is in this group

    • The name "scratchpad_set" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Set the scratchpad content for a memory space (ephemeral working memory).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • shared_memoryShared world-memory (one-write, all-see) operations: set, get, list, delete.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Shared world-memory (one-write, all-see) operations: set, get, list, delete.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • space_importRestore a space from an export payload.Reads text others writeNo findings

    Why it is in this group

    • The name "space_import" says "import": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Restore a space from an export payload. Mode: empty-only (default), merge, or replace.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • spaces_createCreate a new memory space.Reads text others writeNo findings

    Why it is in this group

    • The name "spaces_create" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Create a new memory space.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • state_setReplace a space's single JSON state snapshot.Reads text others writeNo findings

    Why it is in this group

    • The name "state_set" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Replace a space's single JSON state snapshot.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • stream_appendAppend an entry to a stream (XADD).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Append an entry to a stream (XADD). Returns the entry ID.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • stream_deleteDelete a stream entirely (hot + durable) — irreversible.Reads text others writeNo findings

    Why it is in this group

    • The name "stream_delete" says "delete": a word for removing or ending something.
    • The description says "irreversible".
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Delete a stream entirely (hot + durable) — irreversible.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • stream_groupConsumer-group operations on a stream: create, destroy, read (XREADGROUP), ack (XACK), pending (XPENDING), claim (XCLAIM/XAUTOCLAIM).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Consumer-group operations on a stream: create, destroy, read (XREADGROUP), ack (XACK), pending (XPENDING), claim (XCLAIM/XAUTOCLAIM).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • threadThread (conversation grouping) operations: create, get, update, delete.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Thread (conversation grouping) operations: create, get, update, delete.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
  • webhookPer-space webhook subscriptions: create, list, delete.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Per-space webhook subscriptions: create, list, delete.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: true
Changes things 6Claude Code: ask
  • memory_bootstrapLoad full context in one call: recent messages, entries, context, scratchpad.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Load full context in one call: recent messages, entries, context, scratchpad. Run this at session start.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • memory_bootstrap_batchParallel bulk fetch: named context keys, entities, and optional semantic results in one call.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Parallel bulk fetch: named context keys, entities, and optional semantic results in one call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • memory_recallRecall recent messages from conversation history.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Recall recent messages from conversation history. Returns newest first.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • queue_peekPeek at a queue without consuming: returns length and the head envelope.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Peek at a queue without consuming: returns length and the head envelope.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • space_exportExport all data in a space (all primitives, schema v2) as a restorable payload.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Export all data in a space (all primitives, schema v2) as a restorable payload.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • stream_infoStream info: length and consumer groups (XLEN + XINFO GROUPS).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Stream info: length and consumer groups (XLEN + XINFO GROUPS).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 12Show 12 read-only tools
  • context_getGet a context value by key.Reads text others writeNo findings

    Why it is in this group

    • The name "context_get" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Get a context value by key.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • context_listList all context keys and values in a space.Reads text others writeNo findings

    Why it is in this group

    • The name "context_list" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List all context keys and values in a space.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • entities_listList entities in a memory space, optionally filtered.Reads text others writeNo findings

    Why it is in this group

    • The name "entities_list" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List entities in a memory space, optionally filtered.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • entries_listList long-term memory entries.Reads text others writeNo findings

    Why it is in this group

    • The name "entries_list" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List long-term memory entries. Filter by tags.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • scratchpad_getGet the scratchpad content from a memory space.Reads text others writeNo findings

    Why it is in this group

    • The name "scratchpad_get" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Get the scratchpad content from a memory space.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • spaces_getGet a single memory space (config, usage counters).Reads text others writeNo findings

    Why it is in this group

    • The name "spaces_get" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Get a single memory space (config, usage counters).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • spaces_listList all memory spaces owned by this API key.Reads text others writeNo findings

    Why it is in this group

    • The name "spaces_list" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List all memory spaces owned by this API key.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • state_getGet a space's single JSON state snapshot.Reads text others writeNo findings

    Why it is in this group

    • The name "state_get" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Get a space's single JSON state snapshot.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • stream_readRanged read from a stream (XRANGE/XREVRANGE).Reads text others writeNo findings

    Why it is in this group

    • The name "stream_read" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Ranged read from a stream (XRANGE/XREVRANGE).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • threads_listList threads in a memory space, optionally filtered by status.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "threads_list" says "list": a word for reading.

    What it can reach

    • private-dataThe name "threads_list" says "list" and "thread": it reads messages.
    • private-dataThe description's first sentence says "list" and "thread": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "threads_list" says "list" and "thread": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "thread": it reads messages, which other people can write.
    Description, as the server wrote it
    List threads in a memory space, optionally filtered by status.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • usage_getGet current usage vs plan limits for the authenticated tenant.Reads text others writeNo findings

    Why it is in this group

    • The name "usage_get" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Get current usage vs plan limits for the authenticated tenant.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write46
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:06 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
202
tools/list served without credentials
yes
Tools that change things, listed without credentials
34
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
yes
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 34 tools that change things (28 destructive, 6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.agenticmemory.ai/sse: tools/list returned 46 tools to an anonymous client, including memory_store (destructive), memory_store_batch (destructive), memory_clear (destructive), context_set (destructive), context_delete (destructive) and 29 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.10.0. Values in angle brackets are yours to fill in.

claude mcp add --transport sse agenticmemory https://mcp.agenticmemory.ai/sse
claude mcp add --transport sse agenticmemory https://mcp.agenticmemory.ai/sse

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agenticmemory__memory_search",
      "mcp__agenticmemory__context_get",
      "mcp__agenticmemory__context_list",
      "mcp__agenticmemory__entries_list",
      "mcp__agenticmemory__spaces_list",
      "mcp__agenticmemory__scratchpad_get",
      "mcp__agenticmemory__spaces_get",
      "mcp__agenticmemory__entities_list",
      "mcp__agenticmemory__threads_list",
      "mcp__agenticmemory__state_get",
      "mcp__agenticmemory__stream_read",
      "mcp__agenticmemory__usage_get"
    ],
    "ask": [
      "mcp__agenticmemory__memory_recall",
      "mcp__agenticmemory__queue_peek",
      "mcp__agenticmemory__memory_bootstrap",
      "mcp__agenticmemory__memory_bootstrap_batch",
      "mcp__agenticmemory__space_export",
      "mcp__agenticmemory__stream_info"
    ],
    "deny": [
      "mcp__agenticmemory__memory_store",
      "mcp__agenticmemory__memory_store_batch",
      "mcp__agenticmemory__memory_clear",
      "mcp__agenticmemory__context_set",
      "mcp__agenticmemory__context_delete",
      "mcp__agenticmemory__spaces_create",
      "mcp__agenticmemory__queue_push",
      "mcp__agenticmemory__queue_pop",
      "mcp__agenticmemory__scratchpad_set",
      "mcp__agenticmemory__space_import",
      "mcp__agenticmemory__entry",
      "mcp__agenticmemory__entries_add_batch",
      "mcp__agenticmemory__entity",
      "mcp__agenticmemory__thread",
      "mcp__agenticmemory__state_set",
      "mcp__agenticmemory__shared_memory",
      "mcp__agenticmemory__queue_lease",
      "mcp__agenticmemory__queue_ack",
      "mcp__agenticmemory__queue_nack",
      "mcp__agenticmemory__queue_dlq",
      "mcp__agenticmemory__stream_append",
      "mcp__agenticmemory__stream_delete",
      "mcp__agenticmemory__stream_group",
      "mcp__agenticmemory__kv_hash",
      "mcp__agenticmemory__kv_string",
      "mcp__agenticmemory__kv_set",
      "mcp__agenticmemory__webhook",
      "mcp__agenticmemory__knowledge"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agenticmemory. Review it before you use it.

Capability tags behind 46 rules
  • mcp__agenticmemory__memory_store untrusted-input
  • mcp__agenticmemory__memory_store_batch untrusted-input
  • mcp__agenticmemory__memory_recall untrusted-input
  • mcp__agenticmemory__memory_clear untrusted-input
  • mcp__agenticmemory__memory_search private-data, untrusted-input
  • mcp__agenticmemory__context_set untrusted-input
  • mcp__agenticmemory__context_get untrusted-input
  • mcp__agenticmemory__context_list untrusted-input
  • mcp__agenticmemory__context_delete untrusted-input
  • mcp__agenticmemory__entries_list untrusted-input
  • mcp__agenticmemory__spaces_list untrusted-input
  • mcp__agenticmemory__spaces_create untrusted-input
  • mcp__agenticmemory__queue_push untrusted-input
  • mcp__agenticmemory__queue_pop untrusted-input
  • mcp__agenticmemory__queue_peek untrusted-input
  • mcp__agenticmemory__memory_bootstrap untrusted-input
  • mcp__agenticmemory__memory_bootstrap_batch untrusted-input
  • mcp__agenticmemory__scratchpad_set untrusted-input
  • mcp__agenticmemory__scratchpad_get untrusted-input
  • mcp__agenticmemory__spaces_get untrusted-input
  • mcp__agenticmemory__space_export untrusted-input
  • mcp__agenticmemory__space_import untrusted-input
  • mcp__agenticmemory__entry untrusted-input
  • mcp__agenticmemory__entries_add_batch untrusted-input
  • mcp__agenticmemory__entity untrusted-input
  • mcp__agenticmemory__entities_list untrusted-input
  • mcp__agenticmemory__thread untrusted-input
  • mcp__agenticmemory__threads_list private-data, untrusted-input
  • mcp__agenticmemory__state_get untrusted-input
  • mcp__agenticmemory__state_set untrusted-input
  • mcp__agenticmemory__shared_memory untrusted-input
  • mcp__agenticmemory__queue_lease untrusted-input
  • mcp__agenticmemory__queue_ack untrusted-input
  • mcp__agenticmemory__queue_nack untrusted-input
  • mcp__agenticmemory__queue_dlq untrusted-input
  • mcp__agenticmemory__stream_append untrusted-input
  • mcp__agenticmemory__stream_read untrusted-input
  • mcp__agenticmemory__stream_info untrusted-input
  • mcp__agenticmemory__stream_delete untrusted-input
  • mcp__agenticmemory__stream_group untrusted-input
  • mcp__agenticmemory__kv_hash untrusted-input
  • mcp__agenticmemory__kv_string untrusted-input
  • mcp__agenticmemory__kv_set untrusted-input
  • mcp__agenticmemory__usage_get untrusted-input
  • mcp__agenticmemory__webhook untrusted-input
  • mcp__agenticmemory__knowledge untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.jyswee/agenticmemory/verify?hash=c8b5f2ecf862ff9c67d63c39a5519fa00f1c451e6942d8d22f70194f09ab8263" | jq -e '.changed == false'

Pinned hash c8b5f2ecf862, from Nov 19, 2026, 23:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.jyswee/agenticmemory/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.jyswee/agenticmemory
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.jyswee/agenticmemory.svg)](https://radar.anlyon.com/servers/io.github.jyswee/agenticmemory)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:37 UTC.

agenticmemory MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the agenticmemory MCP server safe?

No scan can promise that. What its definitions show: 46 tools, 34 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the agenticmemory MCP server delete data?

Yes. 28 tools can delete, cancel or revoke something: memory_store, memory_store_batch, memory_clear, context_set, context_delete, spaces_create and 22 more.

Can the agenticmemory MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the agenticmemory MCP server have?

46 tools: 28 destructive, 6 write, 12 read. memory_store, memory_store_batch, memory_clear, context_set, context_delete, spaces_create, queue_push, queue_pop and 38 more.

Does the agenticmemory MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the agenticmemory MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the agenticmemory MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.