{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_8famxp4ztcez","handle":"mcp-nexmem","url":"https://wellknown.network/agents/mcp-nexmem","links":{"self":"https://wellknown.network/agents/mcp-nexmem/record.json","html":"https://wellknown.network/agents/mcp-nexmem","markdown":"https://wellknown.network/agents/mcp-nexmem/record.md","api":"https://wellknown.network/api/v1/agents/mcp-nexmem","status":"https://wellknown.network/api/v1/agents/mcp-nexmem/status","claim":"https://wellknown.network/agents/mcp-nexmem/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-nexmem/claim.json","badge":"https://wellknown.network/agents/mcp-nexmem/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-nexmem/history","tools":"https://wellknown.network/api/v1/agents/mcp-nexmem/tools"},"ard":{"identifier":"urn:air::server:mcp-nexmem","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-nexmem","summary":"NexMem: Shared Agent Memory for Teams — a plug-and-play MCP memory server with pluggable database backends","description":"# NexMem MCP\n\n**Shared Agent Memory for Teams** — a plug-and-play MCP memory server with pluggable database backends.\n\nNexMem gives AI coding agents (Cursor, Claude Desktop, etc.) a persistent knowledge graph that the whole team shares. Agents learn as they work — discovering services, architecture patterns, and conventions — then recall that knowledge instantly in future sessions.\n\n## Features\n\n- **Self or Team memory** — personal graph or shared team graph, switchable via env var\n- **5 storage backends** — JSONL (default), SQLite, MongoDB, PostgreSQL, Redis\n- **Atomic operations** — no race conditions when multiple team members write simultaneously\n- **Strong consistency** — reads always return the latest state\n- **Wire-compatible** — same JSONL format as `@modelcontextprotocol/server-memory` for import/export\n- **Guided autonomous** — built-in instructions tell the agent what to save (and what not to)\n- **Extensible** — add custom backends by implementing the `StorageAdapter` ABC\n\n## Quick Start\n\n### 1. Install\n\n```bash\npip install mcp-nexmem\n```\n\nOr with a database backend:\n\n```bash\npip install \"mcp-nexmem[mongodb]\"   # MongoDB\npip install \"mcp-nexmem[postgres]\"  # PostgreSQL\npip install \"mcp-nexmem[redis]\"     # Redis\npip install \"mcp-nexmem[all]\"       # All backends\n```\n\n### 2. Configure\n\nAdd to your `~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"nexmem\": {\n      \"command\": \"nexmem-mcp\",\n      \"env\": {\n        \"NEXMEM_MODE\": \"self\"\n      }\n    }\n  }\n}\n```\n\n### 3. Restart your IDE\n\nThat's it. The agent now has persistent memory.\n\n## Interactive Setup\n\nFor a guided setup that generates the config for you:\n\n```bash\nnexmem-mcp init\n```\n\nOr run the install script:\n\n```bash\nbash scripts/install.sh\n```\n\n## Configuration Reference\n\nAll configuration is via environment variables (prefix: `NEXMEM_`):\n\n| Variable | Default | Description |\n|---|---|---|\n| `NEXMEM_MODE` | `self` | `self` for personal memory, `team` for shared |\n| `NEXMEM_USER_NAME` | OS username…","publisher":{"name":"NexMem Contributors","url":null},"homepage":"https://github.com/arpanroy41/nexmem-mcp","repository":"https://github.com/arpanroy41/nexmem-mcp","version":"0.3.0","license":null,"protocols":["mcp"],"tags":["agent","ai","knowledge-graph","mcp","memory","team"],"pricing":null,"endpoints":[{"url":"pypi:mcp-nexmem","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"}],"categories":["data","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-nexmem","registry":"pypi","observedAt":"2026-10-28T12:22:55.033Z","publishedAt":"2026-03-28T11:59:31.703848Z","latestVersion":"0.3.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-nexmem","url":"https://pypi.org/project/mcp-nexmem/","firstSeenAt":"2026-09-10T02:24:11.553Z","fetchedAt":"2026-10-28T12:21:21.185Z","normalizedAt":"2026-10-28T12:21:21.185Z"}]},"firstSeenAt":"2026-09-10T02:24:11.553Z","updatedAt":"2026-10-28T12:22:55.033Z"}