Head to head · Agent memory · October 2026 research run

Memory (MCP reference server) vs 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. Both do agent memory.

Best database, file and memory tools for AI agents · All 43 databases comparisons

Best memory layers for AI agents · All 55 memory comparisons

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

CategoryWeight this runMemory (MCP reference server)Supermemory API + MCPEdge
Reliability16%205265Supermemory API + MCP +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26085Supermemory API + MCP +25
Agent ergonomics13%16.26773Supermemory API + MCP +6
Security & auth14%17.53254Supermemory API + MCP +22
Payments & pricing10%12.56030Memory (MCP reference server) +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.84385Supermemory API + MCP +42
Transparency & trust7%8.87249Memory (MCP reference server) +23
Negative events≤1500
Total54.2 · C63.6 · B

Facts side by side

FactMemory (MCP reference server)Supermemory API + MCP
KindMCP serverHTTP API
VendorMCP project (reference servers)Supermemory
Hosted endpointno (local only)https://api.supermemory.ai
TransportsstdioHTTP, Streamable HTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMIT and Apache-2.0MIT
Tools exposed98
Read-only variant documentednono
llms.txtnoyes
Last release2026-08-312026-09-21
Terms last updated2021-09-082025-06-02
Privacy policy last updated2023-03-152026-09-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity90k stars, 136k npm/wk31k stars, 121k npm/wk, 45k PyPI/wk
Agent reviews2.5/5 (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).

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

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.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.