SmartMemory
PYPI · SMARTMEMORY-MCP
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Available components
Last scanned (14 hours ago)
Scores higher than 71% of PyPI servers
Category Memory and Knowledge
Recent critical change
GHSA-6q48-6c7w-9gw2 affects this package (21 Oct 2026). See the changelog before you install this server.
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 22 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability71
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1901 tokens (~111/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage76
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 16% of tool parameters carry a description.Partial
- Structured output schemas are declared (82% 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 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 18 Nov 26 −16
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.97 functional
- 17 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 16 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 12 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 11 Nov 26 −15
- Malware scan: pass → unverified ▼ 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 21 Nov 2026 · Analysed pypi/smartmemory-mcp@1.4.94
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 22 packages
| Packages resolved | 22 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
get_working_context Get Working Context ~117
Retrieve a structured surfacing response (CORE-MEMORY-DYNAMICS-1 M1a). Returns JSON matching ``smart-memory-docs/docs/features/CORE-MEMORY-DYNAMICS-1/context-api-contract.json``. Cross-type retrieval, ``strategy_used="fast:recency"``. Standalone MCP does not currently compose anchors.
| Name | Type | Req | Description |
|---|---|---|---|
| k | integer | – | – |
| max_tokens | – | – | – |
| query | string | yes | – |
| session_id | string | yes | – |
| strategy | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
login Login ~31
Authenticate with a SmartMemory API key. Restart MCP server to unlock PRO tools.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_auto Memory Auto ~198
Enable or disable automatic memory lifecycle. When enabled, SmartMemory automatically recalls context at session start, observes tool calls, distills conversation turns, learns from errors, and persists session summaries. Zero manual tool calls needed. Session-scoped overrides — settings apply to the current session only, not persisted to config.toml.
| Name | Type | Req | Description |
|---|---|---|---|
| distill_turns | boolean | – | Save (prompt, response) pairs. |
| enabled | boolean | – | Activate (True) or deactivate (False) automatic lifecycle. |
| learn_from_errors | boolean | – | Capture PostToolUseFailure errors. |
| observe_tool_calls | boolean | – | Capture PostToolUse observations. |
| orient_budget | integer | – | Max tokens for session-start context injection. |
| recall_budget | integer | – | Max tokens for per-prompt context injection. |
| recall_strategy | string | – | "session_only" | "topic_change" | "every_prompt". |
| session_id | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_explain Explain a memory ~119
Explain a memory's full provenance: origin, every belief the system held for it over time, what replaced it, what it derives from, and whether its history is cryptographically intact. The single-call audit answer (PLAT-AUDITABLE-MEMORY-1). FREE tier by design: agents should always be able to answer "how do you know that?". chain_verified null means nothing to verify (legacy or unversioned) — it is NOT a tamper warning.
| Name | Type | Req | Description |
|---|---|---|---|
| memory_id | string | yes | – |
No output schema declared.
No examples provided.
memory_export Memory Export ~29
Export all memories as an OKF bundle directory or tar.gz archive.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_feedback Give search feedback ~129
Report which search results you used from a previous memory_search call. Call this after using results from memory_search to help SmartMemory learn which memories are actually useful. Pass the search_session_id from the memory_search response and the item_ids you incorporated into your response.
| Name | Type | Req | Description |
|---|---|---|---|
| result_used | array | yes | List of item_ids from the search results that you used. Pass an empty list if none of the results were useful. |
| search_session_id | string | yes | The session ID returned at the bottom of the memory_search output (e.g. "search:ws123:abc456def789"). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_get Get a memory ~28
Retrieve a memory item by ID with full content and metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| item_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_import Memory Import ~28
Losslessly import an OKF bundle through the direct add path.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_ingest Ingest a memory ~36
Ingest content through the full NLP pipeline with entity extraction.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | – |
| memory_type | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_migrate Memory Migrate ~31
Migrate all memories to a different backend via a temporary OKF bundle.
| Name | Type | Req | Description |
|---|---|---|---|
| target | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_policy_bundle Get policy bundle ~73
Compile active workspace decisions into a Stratum policy bundle. ``workflow`` is echoed in the selector for the runner. ``domain`` narrows the source decisions. The returned JSON is the policy-exchange contract bundle and is identical for local and hosted backends.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | – | – | – |
| workflow | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
memory_recall Recall memories ~113
**Deprecated:** Use ``get_working_context``. Legacy surface kept for backward compatibility. Internally delegates to the surfacing helper (CORE-MEMORY-DYNAMICS-1 M1a) and post-filters cross-type results through ``_LEGACY_RECALL_TYPE_SCOPE`` to preserve the pre-shim ``memory_type="working"`` scope.
| Name | Type | Req | Description |
|---|---|---|---|
| cite | boolean | – | – |
| query | string | yes | – |
| session_id | – | – | – |
| top_k | integer | – | – |
No output schema declared.
No examples provided.
memory_recall_pack Build a recall pack ~230
Assemble the most useful context that fits in a token budget. Returns one priority-ordered block (active plan, anchors, latest snapshot, tier-1 user content, tier-2 graduated content, notes) packed to fit ``budget_tokens``, plus a manifest accounting every token spent and every item truncated or dropped (CORE-RECALL-BUDGET-1). ``query`` ranks each section by relevance; omit it to rank by recency. ``sections`` overrides the default list/order/caps as ``{name, cap_tokens}`` entries. ``preset`` selects a named section set instead: pass ``"wakeup"`` with a small budget (~300 tokens) at session start for an L1 orientation card (active plan, anchors, workspace topics, last-session headline) — the default sections go degenerate at that size. Use ``get_working_context`` for the L2 drill-in. Returns ``{block, manifest}``.
| Name | Type | Req | Description |
|---|---|---|---|
| budget_tokens | integer | yes | – |
| preset | – | – | – |
| query | – | – | – |
| sections | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
memory_search Search memories ~475
Search memories using semantic similarity with optional hybrid mode. hop_strategy: consensus follows entities several top results agree on; relevance follows best-result entities and one-off bridges; semantic asks an LLM. since/until: ISO-8601 or relative (7d, 24h, 30m), echoed as an absolute window. as_of_date (ISO-8601) travels transaction time: what the system believed at that instant. include_superseded keeps replaced items visible in results (PLAT-AUDITABLE-MEMORY-1). include_retracted keeps WITHDRAWN beliefs visible (CORE-RETRACTED-RECALL-1) — a separate lifecycle state with no replacement, not covered by include_superseded. include_archived keeps ARCHIVED items visible (CORE-ARCHIVED-RECALL-1) — memories the decay/prune evolvers retired, or the source an episodic-to-semantic promotion replaced; a third lifecycle state, again with no replacement and no version chain. All three default to false, so by default you will not be shown a memory the system already knows was replaced, withdrawn, or retired. Results from an as_of_date search carry as_of_resolution. A value of "unresolved" means that result is PRESENT-DAY content the system could not resolve to the requested time, so it must not be cited as what was believed then. Set as_of_strict to refuse a partial history outright rather than receive labelled results (gap #2).
| Name | Type | Req | Description |
|---|---|---|---|
| as_of_date | – | – | – |
| as_of_strict | boolean | – | – |
| budget_ms | integer | – | – |
| catalog_mode | boolean | – | – |
| channel_weights | – | – | – |
| cite | boolean | – | – |
| decompose | boolean | – | – |
| enable_hybrid | boolean | – | – |
| hop_strategy | – | – | – |
| include_archived | boolean | – | – |
| include_retracted | boolean | – | – |
| include_superseded | boolean | – | – |
| max_hops | integer | – | – |
| memory_type | – | – | – |
| multi_hop | boolean | – | – |
| query | string | yes | – |
| since | – | – | – |
| top_k | integer | – | – |
| until | – | – | – |
No output schema declared.
No examples provided.
read_around Read surrounding conversation ~219
Auto-centered conversation read (CORE-RECALL-CENTERED-1 Phase 2). Given a matched conversation-chunk ``item_id`` (from a recall hit's ``conversation_handle``), return a char-budgeted ASYMMETRIC window of the surrounding conversation chunks (~``before_ratio`` back / ``after_ratio`` forward; leftover spills to the other side) plus a continue-cursor — so a caller pulls just the relevant slice of a long conversation into context instead of the whole transcript. "Centered" is over neighbour 15-turn chunks, not individual turns. Returns ``{window_items, window_text, handle, continue_cursor:{prev_pos, next_pos}, chars_used, char_budget}``. Pass a returned ``continue_cursor`` back as ``cursor`` to page further in one direction without overlap.
| Name | Type | Req | Description |
|---|---|---|---|
| after_ratio | number | – | – |
| before_ratio | number | – | – |
| char_budget | integer | – | – |
| cursor | – | – | – |
| item_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
switch_team Switch Team ~23
Switch to a different workspace/team.
| Name | Type | Req | Description |
|---|---|---|---|
| team_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
whoami Whoami ~22
Show current session: user, team, tier, and backend mode.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the SmartMemory MCP server?
SmartMemory runs locally as a PyPI package, launched with uvx smartmemory-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · smartmemory-mcp
claude mcp add ai-smartmemory-smartmemory-mcp -- uvx smartmemory-mcp
What is the SmartMemory MCP server?
SmartMemory is an MCP server listed in the public MCP registry as ai.smartmemory/smartmemory-mcp. Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend. This page covers its PyPI package (smartmemory-mcp).
Is the SmartMemory MCP server safe to use?
SmartMemory scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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 SmartMemory MCP server expose?
SmartMemory exposes 17 tools: login, whoami, switch_team, memory_ingest, memory_search, and 12 more. Their descriptions and schemas cost roughly 1,901 tokens of context every time the server is loaded.
Is the SmartMemory MCP server still maintained?
SmartMemory is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the SmartMemory MCP server under?
SmartMemory declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the SmartMemory MCP server?
VerifyMCP ran 15 checks on SmartMemory, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about SmartMemory: Security disclosure. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.