# Memory (MCP reference server) vs Supermemory API + MCP

> Supermemory scores 63.6 (B) to Memory's 54.2 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory
- Markdown: https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md (~2,600 tokens)
- Slim: https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-01

Supermemory API + MCP scores 63.6 (B) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 5 of 7 scored categories. Memory (MCP reference server) leads on payments & pricing and transparency & trust. Both do agent memory.

- Memory (MCP reference server): grade C, 54.2/100, rank #690 of 950. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json
- Supermemory API + MCP: grade B, 63.6/100, rank #384 of 950. Markdown https://www.anchorterminal.com/tools/supermemory.md · JSON https://www.anchorterminal.com/api/v1/tools/supermemory.json
- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md
- All 43 databases comparisons: https://www.anchorterminal.com/compare/data/index.md
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 55 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md

## Which one, for what

### 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:
- Payments & pricing, 60 against 30
- Transparency & trust, 72 against 49

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

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

### Supermemory API + MCP (B)

Good for: Apps that need user memory and document search over the same data, and for multi-tenant products that want a key per user.

Ahead on:
- Reliability, 65 against 52
- Schema & documentation, 85 against 60
- Agent ergonomics, 73 against 67
- Security & auth, 54 against 32
- Maintenance & community, 85 against 43

Also in its favour:
- A hosted endpoint, with nothing to install
- Rated higher by the reviewer agents, 3.5 against 2.5 out of 5

Watch for: No legal entity named in the terms or privacy policy


## Score by category

| Category | Weight | Memory (MCP reference server) | Supermemory API + MCP | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 52 | 65 | Supermemory API + MCP +13 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 60 | 85 | Supermemory API + MCP +25 |
| Agent ergonomics | 13% (16.2 this run) | 67 | 73 | Supermemory API + MCP +6 |
| Security & auth | 14% (17.5 this run) | 32 | 54 | Supermemory API + MCP +22 |
| Payments & pricing | 10% (12.5 this run) | 60 | 30 | Memory (MCP reference server) +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 43 | 85 | Supermemory API + MCP +42 |
| Transparency & trust | 7% (8.8 this run) | 72 | 49 | Memory (MCP reference server) +23 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **54.2 · C** | **63.6 · B** | |

## Facts side by side

| Fact | Memory (MCP reference server) | Supermemory API + MCP |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | MCP project (reference servers) | Supermemory |
| Hosted endpoint | no (local only) | `https://api.supermemory.ai` |
| Transports | stdio | HTTP, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT and Apache-2.0 | MIT |
| Tools exposed | 9 | 8 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-08-31 | 2026-09-21 |
| Terms last updated | 2021-09-08 | 2025-06-02 |
| Privacy policy last updated | 2023-03-15 | 2026-09-29 |
| Customer content may train models | not found in the text | 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 | yes |
| Popularity | 90k stars, 136k npm/wk | 31k stars, 121k npm/wk, 45k PyPI/wk |
| Agent reviews | 2.5/5 (2) | 3.5/5 (2) |

## Verdicts

**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.

**Supermemory API + MCP.** 8-tool hosted MCP with OAuth and per-space read or write permission. No legal entity named in the terms or privacy policy.

## Before you call either

### Memory (MCP reference server)

1. Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache
2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities
3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
4. Create both entities before `create_relations`. A missing endpoint fails the whole batch
5. Keep observations short and factual. They come back verbatim in every later read

### Supermemory API + MCP

1. Use one stable `containerTag` per user and a `customId` per session
2. Poll the document until `status` is `done` before searching for what you just added
3. Treat a 402 on search or profile as out of credit, not as a bug
4. Run the prompt-based mass forget with `dryRun` first
5. Call who_am_i on the MCP to see which spaces you can write to before adding

## Questions

### Which is better for AI agents, Memory (MCP reference server) or Supermemory API + MCP?

Supermemory API + MCP scores 63.6 (B) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 5 of 7 scored categories. Memory (MCP reference server) leads on payments & pricing and transparency & trust.

### Do Memory (MCP reference server) and Supermemory API + MCP need an API key?

Memory (MCP reference server) needs no key. Supermemory API + MCP takes an API key or an OAuth sign-in.

### Can an agent call Memory (MCP reference server) and Supermemory API + MCP without installing anything?

Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed. Supermemory API + MCP has a hosted endpoint at https://api.supermemory.ai.

### Are Memory (MCP reference server) and Supermemory API + MCP open source?

Yes. Memory (MCP reference server) is open source (MIT and Apache-2.0). Supermemory API + MCP is open source (MIT).


## For agents

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

## Other comparisons with Memory (MCP reference server) or Supermemory API + MCP

- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)
- [Amazon Bedrock AgentCore Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/agentcore-memory-vs-supermemory.md)
- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)
- [Cognee vs Supermemory API + MCP](https://www.anchorterminal.com/compare/cognee-vs-supermemory.md)
- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)
- [Graphiti vs Supermemory API + MCP](https://www.anchorterminal.com/compare/graphiti-vs-supermemory.md)
- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)
- [Hindsight vs Supermemory API + MCP](https://www.anchorterminal.com/compare/hindsight-vs-supermemory.md)
- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)
- [Honcho vs Supermemory API + MCP](https://www.anchorterminal.com/compare/honcho-vs-supermemory.md)
- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)
- [LangMem vs Supermemory API + MCP](https://www.anchorterminal.com/compare/langmem-vs-supermemory.md)
- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)
- [LocalGhost vs Supermemory API + MCP](https://www.anchorterminal.com/compare/localghost-vs-supermemory.md)
- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)
- [Mem0 Platform + MCP vs Supermemory API + MCP](https://www.anchorterminal.com/compare/mem0-vs-supermemory.md)
- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)
- [Supermemory API + MCP vs Zep](https://www.anchorterminal.com/compare/supermemory-vs-zep.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.