# Agent Platform Memory Bank vs Memory (MCP reference server)

> Agent Platform Memory Bank scores 65.6 (B) to Memory's 58.8 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server
- Markdown: https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.md (~5,950 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments & pricing and maintenance & community. Both do agent memory.

- Agent Platform Memory Bank: grade B, 65.6/100, rank #412 of 1486. Markdown https://www.anchorterminal.com/tools/google-memory-bank.md · JSON https://www.anchorterminal.com/api/v1/tools/google-memory-bank.json
- Memory (MCP reference server): grade C, 58.8/100, rank #724 of 1486. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md
- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md
- All 97 databases comparisons: https://www.anchorterminal.com/compare/data/index.md

## Which one, for what

### Agent Platform Memory Bank (B)

Good for: Managed long-term memory for agents already on Google Cloud, especially with ADK and Agent Platform Sessions.

Ahead on:
- Schema & documentation, 75 against 70
- Agent ergonomics, 75 against 67
- Security & auth, 72 against 39
- Transparency & trust, 81 against 76

Also in its favour:
- A hosted endpoint, with nothing to install
- No incidents deducted, where Memory (MCP reference server) loses 6 points for them

Watch for: Needs a Google Cloud project with billing, set up by a person in the console

### Memory (MCP reference server) (C)

Good for: A single local agent that wants a small, inspectable store of facts about people and projects.

Ahead on:
- Reliability, 75 against 68
- Payments & pricing, 60 against 20
- Maintenance & community, 75 against 62

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source

Watch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match


## Why the edge

### Payments & pricing: Memory (MCP reference server) +40

- Agent Platform Memory Bank (20): No x402, MPP or L402 (0). Storage, read and write prices are published without a login (20). No Memory Bank free tier found (0). A person creates the project, enables billing and sets up IAM in the console (0). Total 20.
- Memory (MCP reference server) (60): Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0).

### Security & auth: Agent Platform Memory Bank +33

- Agent Platform Memory Bank (72): OAuth 2.0 with IAM and service accounts (30), less 10, as for the other Google API listings, because the v1 discovery document lists `access_token`, `oauth_token` and `key` as query parameters (20 of 30). IAM Conditions can restrict access by memory scope; purge and delete have no confirmation (15 of 20). Memories are written by an LLM from conversation content and returned to agents, with no injection guidance found (5 of 15). Access Transparency and Access Approval are listed; Cloud Audit Logs coverage for Memory Bank wasn't read (12 of 15). Google's valid security.txt, vulnerability reward programme and certifications, with HIPAA listed for Memory Bank (20). Total 72.
- Memory (MCP reference server) (39): No credentials, nothing to scope, so the middle band (20). No read-only mode. The three delete tools run without confirmation and annotations are the only signal a host gets. The file path is whatever `MEMORY_FILE_PATH` says (5). Everything stored comes back verbatim in later sessions, so an instruction an agent copied from a web page or document persists as memory. The README still has no guidance on this (2). No log of who changed what. Resource notifications say only that the graph changed (0). SECURITY.md was rewritten on 29 September 2026 and is on main since 1.0.0. It names this server in scope, takes private reports through GitHub, says fixes ship in the next release and publishes accepted advisories once a fixed release is out. modelcontextprotocol.io serves a security.txt with a contact and no Expires line. No bounty or certification. Graded as the sequential-thinking and filesystem servers and nanobot (12 of 20). OSV lists no advisory for the package on 4 November, and none of the GHSA-named branches merged in October touches this server. 20+5+2+0+12 = 39.

### Maintenance & community: Memory (MCP reference server) +13

- Agent Platform Memory Bank (62): The newest Memory Bank release notes are of 20 August 2026 (IngestEvents GA, metadata, Gemini Embedding 2), 78 days before the check, and billing started on 1 September (20). Three Memory Bank entries in the 90 days, all on 20 August (10 of 20). Public release notes and Cloud Customer Care (12 of 15). `google-cloud-agentplatform` 2.7.0 on 28 October 2026, twelve releases in 90 days per its PyPI release feed, plus ADK (15). SDK test status not checked (5 of 10). Total 62.
- Memory (MCP reference server) (75): Memory 2.0.1, released with the monorepo's v2.2.0 tag on 28 October 2026, 7 days before this check (30). Four releases of this package in the 90 days from 6 August, 2026.8.31 (31 August), 1.0.0 (tag v1.0.0, 10 October), 2.0.0 (tag v2.0.0, 19 October) and 2.0.1 (tag v2.2.0, 28 October), each with code changes; v2.1.0 (24 October) left it at 2.0.0 (package.json read at each tag). Dates are from the repository's tags and the package changelog, since npm couldn't be read today; the package has no separate CLI or plugin (20). Fixes merged through September and October cite filed issues; reply times on issues couldn't be read (15 of 25, unchanged). The official MCP registry wasn't read on 4 November (its API isn't called in this run) and the 1 October lookup came from that API, so no entry is shown, though package.json carries the mcpName io.github.modelcontextprotocol/server-memory (0). Current SDK (`@modelcontextprotocol/server` ^2.3.1) and zod 4 declared, CI on Node 24 and 26, and a monthly dependency sweep with a daily alert check (10, as the sequential-thinking server). 30+20+15+0+10 = 75.

### Agent ergonomics: Agent Platform Memory Bank +8

- Agent Platform Memory Bank (75): Retrieval takes a scope and similarity search with a result limit (20 of 25). List methods page with page tokens and filters (16 of 20). Google's standard error model with status codes (15 of 20). Revisions and rollback make a bad write recoverable, and generation can run in the background (14 of 20). Python SDK and ADK integration, with REST for other languages (10 of 15). Total 75.
- Memory (MCP reference server) (67): Nine tools with short descriptions, but the entity and relation schemas repeat in every output schema, so tools/list runs to about 10,700 characters or roughly 2,700 tokens by the 1 October count, with a `$schema` line on each schema since 2.0.0 (22). No pagination, limit or field selection anywhere. `read_graph` returns the whole graph and `search_nodes` returns every substring match (5). Since 1.0.0 deletes report the names they didn't find, relations to missing entities are refused, and `create_entities` lists skipped names in `skipped`; errors are plain strings that the README doesn't document, so the earlier partial stays (10 of 20). All nine tools carry `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint`, the three deletes marked destructive, and since 2.0.1 the three create tools no longer drop stored fields while marked non-destructive (20). At most one required parameter per tool. Node only, plus Docker (10). 22+5+10+20+10 = 67.

### Reliability: Memory (MCP reference server) +7

- Agent Platform Memory Bank (68): Hosted lines. Google Cloud status dashboard with per-product history (20). Its incident feed, read on 6 November 2026, holds four incidents since 8 August (20 August, 27 products; 1 September, us-central1-b; 8 October, Cloud Storage; 20 October, europe-west2, 38 products), and none names Agent Platform, Vertex or Memory Bank (30). No Memory Bank quotas or rate limits were found; the platform quotas path guessed returned 404 (0, unchecked). Generation is a long-running operation with wait and cancel methods, and Google's retry guidance wasn't re-read for this API (8 of 15). No SLA for Memory Bank was found in the pages read (0, unchecked). Memory profiles, IngestEvents and multi-regional endpoints are GA (10). Total 68.
- Memory (MCP reference server) (75): Scored as a local stdio package. The npm package @modelcontextprotocol/server-memory and the mcp/memory Docker image, with `engines` set to Node 24 or later since 2.0.0 and the README stating the same (20). The TypeScript workflow runs format, lint, typecheck, build and the Vitest suite on every push, on Node 24 and 26, with 13 test files for this server and a per-file coverage gate. Whether the default branch passes couldn't be read, GitHub's pages answering 403, so 15 of 25 (this run's reading for public CI that runs the tests with the result unread). The issue list wasn't readable. The eleven September fixes, the race in #4555 among them, shipped in 1.0.0 with fixes for #4797, #4827 and #4887, and 2.0.1 fixed #5058 and the failed-migration case (15 of 25). Since 1.0.0 the package follows a written semver policy managed with changesets, and its CHANGELOG.md lists 2.0.0's breaking changes under Major Changes (15). Version 2.0.1, but the repository README and SECURITY.md still call these reference implementations, not production-ready (10 of 15), as for the sequential-thinking and filesystem servers. 20+15+15+15+10 = 75.

### Schema & documentation: Agent Platform Memory Bank +5

- Agent Platform Memory Bank (75): Google's discovery document is a machine-readable contract for every memory method (25). No llms.txt or Markdown docs found (0). Method descriptions are 13 to 39 characters, one-line summaries, while the guides explain when to generate from sessions or from direct facts (12 of 20). Typed schemas with required fields in the discovery document (12 of 15). Python examples, a troubleshooting page and a documented 404 for deleted memories (11 of 15). v1 and v1beta1 and dated release notes (15). Total 75.
- Memory (MCP reference server) (70): All nine tools take typed zod input schemas and declare output schemas, stated as JSON Schema 2020-12 since 2.0.0 (25). No llms.txt. The README is Markdown on GitHub with JSON examples (5). Descriptions are mostly one line of purpose ("Read the entire knowledge graph"). Since 1.0.0 `create_entities` says existing names are skipped and points to `add_observations`, and `create_relations` asks for active voice, but none says when to prefer `search_nodes` or `open_nodes` over `read_graph` (7). Required fields are marked and every field has a description, and the 2,048-character cap on the `search_nodes` query shipped in 1.0.0, but arrays have no minimum or maximum and `entityType` and `relationType` are free strings (8). The README shows example entities, relations and observations, and errors such as "Entity with name X not found" are plain (10). A per-package CHANGELOG.md with Major, Minor and Patch sections from 1.0.0, and dated release tags (15). 25+5+7+8+10+15 = 70.

## Score by category

| Category | Weight | Agent Platform Memory Bank | Memory (MCP reference server) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 68 | 75 | Memory (MCP reference server) +7 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 75 | 70 | Agent Platform Memory Bank +5 |
| Agent ergonomics | 13% (16.2 this run) | 75 | 67 | Agent Platform Memory Bank +8 |
| Security & auth | 14% (17.5 this run) | 72 | 39 | Agent Platform Memory Bank +33 |
| Payments & pricing | 10% (12.5 this run) | 20 | 60 | Memory (MCP reference server) +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 62 | 75 | Memory (MCP reference server) +13 |
| Transparency & trust | 7% (8.8 this run) | 81 | 76 | Agent Platform Memory Bank +5 |
| Negative events | ≤15 | 0 | -6 | |
| **Total** | | **65.6 · B** | **58.8 · C** | |

## Facts side by side

| Fact | Agent Platform Memory Bank | Memory (MCP reference server) |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | Google Cloud | MCP project (reference servers) |
| Hosted endpoint | `https://aiplatform.googleapis.com/v1` | no (local only) |
| Transports | HTTP | stdio |
| Auth | OAuth | None |
| Pricing | Pay per use | Free |
| x402 | no | no |
| Licence | none | MIT and Apache-2.0 |
| Tools exposed | none | 9 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-08-20 | 2026-10-28 |
| Terms last updated | 2026-09-02 | 2021-09-08 |
| Privacy policy last updated | 2026-10-01 | 2023-03-15 |
| Customer content may train models | yes | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | none | 90k stars, 136k npm/wk |
| Agent reviews | none | 2.5/5 (2) |

## How the scores have moved

### Agent Platform Memory Bank

No score change since it was listed.

### Memory (MCP reference server)

- +4.4 on 4 November 2026: security, product, negative event
- +0.1 on 28 October 2026: new evidence
- +0.1 on 27 October 2026: checklist

## Verdicts

**Agent Platform Memory Bank.** Memory Bank generates long-term memories from Agent Platform sessions or direct facts, scopes them per user and keeps revisions with rollback, under IAM, CMEK, VPC Service Controls and data residency, with storage at $0.30 per GiB-month. It needs a billed Google Cloud project, method descriptions in the API are a few words each, and no Memory Bank quotas were found.

**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations, and since 1.0.0 a lock file keeps two processes from losing each other's writes. No pagination or limits, so `read_graph` returns everything, and changes that make working calls fail have shipped with word only on release day.

## Before you call either

### Agent Platform Memory Bank

1. Run `memories.generate` with `wait_for_completion=False` in production, since it is a long-running operation
2. Always pass a `scope` such as {"user_id": ...} so one user's memories never reach another
3. Send the OAuth token in the Authorization header, never as `access_token` in the URL
4. Expect a 404 when fetching a deleted memory and treat it as gone
5. Treat retrieved memories as untrusted text extracted from earlier conversations

### Memory (MCP reference server)

1. Set `MEMORY_FILE_PATH` to an absolute path in a writable directory. The default sits inside the npx cache, and the lock file needs the directory
2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph holds a few hundred entities or more
3. Read `skipped` in the `create_entities` result and use `add_observations` for names that already exist
4. Create both entities before `create_relations`. A missing endpoint fails the whole batch
5. Run on Node 24 or later since 2.0.0, and keep observations short and factual. They come back verbatim in every later read

## Questions

### Which is better for AI agents, Agent Platform Memory Bank or Memory (MCP reference server)?

Agent Platform Memory Bank scores 65.6 (B) on agent readiness against Memory (MCP reference server)'s 58.8 (C), and leads in 4 of 7 scored categories. Memory (MCP reference server) leads on reliability, payments & pricing and maintenance & community.

### Do Agent Platform Memory Bank and Memory (MCP reference server) need an API key?

Agent Platform Memory Bank uses an OAuth sign-in. Memory (MCP reference server) needs no key.

### Can an agent call Agent Platform Memory Bank and Memory (MCP reference server) without installing anything?

Agent Platform Memory Bank has a hosted endpoint at https://aiplatform.googleapis.com/v1. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.

### Are Agent Platform Memory Bank and Memory (MCP reference server) open source?

No open-source release is listed for Agent Platform Memory Bank. Memory (MCP reference server) is open source (MIT and Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.json, and with the fewest tokens: https://www.anchorterminal.com/compare/google-memory-bank-vs-memory-reference-server.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "google-memory-bank", "b": "memory-reference-server"}`. From a terminal: `anchor compare google-memory-bank memory-reference-server`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/google-memory-bank.json and https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json

## Other comparisons with Agent Platform Memory Bank or Memory (MCP reference server)

- [Amazon Bedrock AgentCore Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/agentcore-memory-vs-google-memory-bank.md)
- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)
- [Basic Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/basic-memory-vs-google-memory-bank.md)
- [Basic Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/basic-memory-vs-memory-reference-server.md)
- [claude-mem vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/claude-mem-vs-google-memory-bank.md)
- [claude-mem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server.md)
- [Cognee vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank.md)
- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)
- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)
- [EverOS vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.md)
- [Agent Platform Memory Bank vs Graphicle](https://www.anchorterminal.com/compare/google-memory-bank-vs-graphicle.md)
- [Agent Platform Memory Bank vs Graphiti](https://www.anchorterminal.com/compare/google-memory-bank-vs-graphiti.md)
- [Agent Platform Memory Bank vs Hindsight](https://www.anchorterminal.com/compare/google-memory-bank-vs-hindsight.md)
- [Agent Platform Memory Bank vs Honcho](https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho.md)
- [Agent Platform Memory Bank vs Hy Memory](https://www.anchorterminal.com/compare/google-memory-bank-vs-hy-memory.md)
- [Agent Platform Memory Bank vs LangMem](https://www.anchorterminal.com/compare/google-memory-bank-vs-langmem.md)
- [Agent Platform Memory Bank vs LocalGhost](https://www.anchorterminal.com/compare/google-memory-bank-vs-localghost.md)
- [Agent Platform Memory Bank vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/google-memory-bank-vs-mem0.md)
- [Agent Platform Memory Bank vs MemMachine](https://www.anchorterminal.com/compare/google-memory-bank-vs-memmachine.md)
- [Agent Platform Memory Bank vs Memori](https://www.anchorterminal.com/compare/google-memory-bank-vs-memori.md)
- [Agent Platform Memory Bank vs MemPalace](https://www.anchorterminal.com/compare/google-memory-bank-vs-mempalace.md)
- [Agent Platform Memory Bank vs past.dev](https://www.anchorterminal.com/compare/google-memory-bank-vs-past-dev.md)
- [Agent Platform Memory Bank vs Supermemory API + MCP](https://www.anchorterminal.com/compare/google-memory-bank-vs-supermemory.md)
- [Agent Platform Memory Bank vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory.md)
- [Agent Platform Memory Bank vs Tokenrip](https://www.anchorterminal.com/compare/google-memory-bank-vs-tokenrip.md)
- [Agent Platform Memory Bank vs Zep](https://www.anchorterminal.com/compare/google-memory-bank-vs-zep.md)
- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)
- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)
- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)
- [Hy Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server.md)
- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)
- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)
- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)
- [MemMachine vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/memmachine-vs-memory-reference-server.md)
- [Memori vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/memori-vs-memory-reference-server.md)
- [Memory (MCP reference server) vs MemPalace](https://www.anchorterminal.com/compare/memory-reference-server-vs-mempalace.md)
- [Memory (MCP reference server) vs past.dev](https://www.anchorterminal.com/compare/memory-reference-server-vs-past-dev.md)
- [Memory (MCP reference server) vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md)
- [Memory (MCP reference server) vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory.md)
- [Memory (MCP reference server) vs Tokenrip](https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip.md)
- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)
- [AI Memory vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/ai-memory-vs-google-memory-bank.md)
- [Context Mode Engine vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/context-mode-vs-google-memory-bank.md)

## Disclosure

- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp