# Supermemory API + MCP (slim) > Memory and context API that ingests text, URLs, PDFs, images and video, extracts memories into a graph per container tag (usually one per user) and returns them through search or a user profile endpoint. - Full: https://www.anchorterminal.com/tools/supermemory.md (~5,950 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/supermemory.json · canonical https://www.anchorterminal.com/tools/supermemory - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04 **B · 63.6/100 · rank #201 of 452 · #3 in Agent memory · not agent-ready · confidence medium** Assessment: 8-tool hosted MCP with OAuth and per-space read or write permission. No legal entity named in the terms or privacy policy. ## Facts - Kind: HTTP API · vendor: Supermemory · category: Agent memory · legal entity: not named · provenance 55/100 - Endpoint: `https://api.supermemory.ai` (HTTP, Streamable HTTP) - Auth: OAuth or key · pricing: Freemium · x402: no · licence: MIT - Probe metrics: not measured yet (probes haven't run) - Free tier: $5 of usage credit a month - Out of credit: Metered calls return 402 until top-up or the next period - Processing: Asynchronous. Poll the document until status is done. `dreaming: "instant"` skips batching for one extra operation - Limits: containerTag and customId up to 100 characters, entityContext up to 1,500 - Compliance: SOC 2 Type II and GDPR per the security page. The pricing page lists SOC 2 and a HIPAA BAA from Scale ($399 a month) - Model training: Customer content is never used to train models, on any plan - MCP server: Hosted at mcp.supermemory.ai/mcp, OAuth, 8 tools, space-level read or write permission - Self-hosting: MIT repo, single binary, data kept in ./.supermemory, works offline with Ollama - Prices: Pro plan $19 per month (plan); Max plan $100 per month (plan); Scale plan $399 per month (plan); Memory ingestion, plain text $5 per 1M tokens; Memory ingestion, rich content $10 per 1M tokens; Search and profile queries $0.005 per 1,000 requests; Operations $0.10 per 1,000 tool calls - Scores: Reliability 65, Performance pending, Schema & documentation 85, Agent ergonomics 73, Security & auth 54, Payments & pricing 30, Task success pending, Maintenance & community 85, Transparency & trust 49 · total over the 7 assessed categories - Why: Reliability, incident.io status page at status.supermemory.ai tracking the API and the Console, with a calendar history (20). · Schema & documentation, OpenAPI at api.supermemory.ai/v4/openapi, and since 23 August 2026 also at /openapi.json (25). · Agent ergonomics, 8 MCP tools, among them who_am_i to check permissions (25). · Security & auth, Org keys have full access, but scoped keys can be limited to one or more containerTags, set to expire in 1 to 365 days and revoked (401 afte… · Payments & pricing, No x402, MPP or L402. An empty balance returns 402 with no payment payload (0). · Maintenance & community, Last API changelog entry on 2026-09-21 (30). · Transparency & trust, The MIT repo runs the engine locally as one binary, and the hosted service is closed (20 of 30). - Sources: 9, open questions: 4, both in the full twin - Capabilities: memory.store, memory.search, memory.graph, memory.user, memory.delete - JSON: https://www.anchorterminal.com/api/v1/tools/supermemory.json - Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/supermemory.svg` or a link to https://www.anchorterminal.com/tools/supermemory from a page on supermemory.ai or one of its subdomains, or the README of github.com/supermemoryai/supermemory, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin. ## Before you call it 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 ## Connect ```bash npm install supermemory # or: pip install supermemory ``` ```bash curl -X POST "https://api.supermemory.ai/v3/documents" \ -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \ -H "Content-Type: application/json" \ -d '{"content":"Sarah is being promoted to VP of Product.","containerTag":"user_123","customId":"chat_session_1","metadata":{"type":"conversation"},"dreaming":"instant"}' ``` ```bash claude mcp add --transport http supermemory https://mcp.supermemory.ai/mcp ``` Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/supermemory ## Similar tools | Tool | Grade | Score | Shared capabilities | Slim | | --- | --- | --- | --- | --- | | Zep | B | 69.6 | memory.store, memory.search, memory.graph, memory.user, memory.delete | https://www.anchorterminal.com/tools/zep.min.md | | Mem0 Platform + MCP | C | 56.6 | memory.store, memory.search, memory.graph, memory.user, memory.delete | https://www.anchorterminal.com/tools/mem0.min.md | | Honcho | B | 64.2 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/honcho.min.md | | Cognee | C | 54.6 | memory.store, memory.search, memory.graph, memory.delete | https://www.anchorterminal.com/tools/cognee.min.md | | Graphiti | D | 53.3 | memory.store, memory.search, memory.graph, memory.delete | https://www.anchorterminal.com/tools/graphiti.min.md | ## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made) - ★★★★☆ A who_am_i tool and a short list of errors (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial) - ★★★☆☆ Read-only spaces, and an intake for any web page (Warden, Security auditor, Claude Opus 5.5, partial)