protogrid

Search / com.memxus/memxus

memxus

R2· OAuth, once

Persistent memory layer that saves and recalls your project context and preferences.

v1.3.2 · active · repository · descriptor JSON · versions

An agent can connect after a one-time OAuth consent by a human.Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.
Quality83good
Trust90of 100
Uptime, 30 days100%
Latency p50320 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "memxus": {
      "type": "http",
      "url": "https://mcp.memxus.com/mcp"
    }
  }
}
claude mcp add --transport http memxus https://mcp.memxus.com/mcp
[mcp_servers.memxus]
url = "https://mcp.memxus.com/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "memxus": {
      "type": "remote",
      "url": "https://mcp.memxus.com/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "memxus": {
      "type": "http",
      "url": "https://mcp.memxus.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=memxus&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLm1lbXh1cy5jb20vbWNwIn0%3D"
}
{
  "servers": {
    "memxus": {
      "type": "http",
      "url": "https://mcp.memxus.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "memxus": {
      "httpUrl": "https://mcp.memxus.com/mcp"
    }
  }
}
extensions:
  "memxus":
    enabled: true
    name: "memxus"
    type: streamable_http
    uri: "https://mcp.memxus.com/mcp"
    timeout: 300

Quality 83 / 100good

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorization83 · weight 15
  • pass
    auth.prmProtected Resource Metadata (RFC 9728) published
  • pass
    auth.as_metadataauthorization server metadata reachable
  • warn
    auth.cimdonly Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
  • n/a
    auth.secret_in_urlno templated URL
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

Tool list unknown · checked 2026-10-19 10:52 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 90 / 100

provenance75
liveness100
freshness85
hygiene100

+repository +dns-namespace +reachable +uptime-100% ~updated-81d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.memxus.com/mcp streamable-httpoauth2 AS: https://mcp.memxus.comyes100%320 ms–2026-10-19

Tools (0)

No tools observed. Tools appear once a credential-free probe can list them.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "com.memxus/memxus",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "auth": {
        "type": "oauth2",
        "scopes": [
          "memories:read",
          "memories:write",
          "memories:delete",
          "sources:read",
          "sources:write"
        ],
        "tokenUrl": "https://mcp.memxus.com/oauth/token",
        "wellKnownUrl": "https://mcp.memxus.com/.well-known/oauth-authorization-server/mcp",
        "registrationUrl": "https://mcp.memxus.com/oauth/register",
        "authorizationUrl": "https://mcp.memxus.com/oauth/authorize"
      },
      "tags": [
        "memory",
        "context-engine",
        "persistent-memory",
        "github-integration",
        "notion-integration",
        "portable-context",
        "cross-platform",
        "claude",
        "chatgpt",
        "cursor",
        "vscode",
        "gemini",
        "slack",
        "oauth",
        "mcp",
        "context",
        "recall",
        "teams",
        "groups",
        "workforce",
        "remote"
      ],
      "links": {
        "install": "https://memxus.com/install",
        "pricing": "https://memxus.com/pricing",
        "privacy": "https://memxus.com/privacy",
        "support": "https://github.com/gpitrella/memxus-remote-mcp/issues",
        "reviewer": "https://github.com/gpitrella/memxus-remote-mcp/blob/main/REVIEWER.md",
        "changelog": "https://github.com/gpitrella/memxus-remote-mcp/releases",
        "dashboard": "https://dashboard.memxus.com",
        "documentation": "https://memxus.com/docs"
      },
      "tools": [
        {
          "name": "remember",
          "description": "Save context to persistent memory — from GitHub commits, Notion pages, or manual input. Visibility can be private or shared with groups. Returns memory ID and confirmation."
        },
        {
          "name": "recall",
          "description": "Retrieve context from memory using semantic search. Searches across private memories and shared group memories. GitHub/Notion synced content available via project collections."
        },
        {
          "name": "get_context",
          "description": "Builds a formatted context block for a topic from stored memories; use when the user asks to load or recall project context. Ideal for injecting relevant memory from GitHub, Notion, and saved decisions into agent prompts."
        },
        {
          "name": "list_memories",
          "description": "List your memories with filtering by visibility, type, collection, or group. Useful for auditing what's saved and managing your context."
        },
        {
          "name": "get_memory",
          "description": "Retrieve a single memory by ID. Returns full content, metadata, and source."
        },
        {
          "name": "list_collections",
          "description": "List your memory collections (projects, scopes). Shows where context is organized — GitHub/Notion syncs appear under project:<slug>."
        },
        {
          "name": "forget",
          "description": "Delete a memory permanently. Useful for removing outdated or incorrect context."
        },
        {
          "name": "memory_stats",
          "description": "Show statistics about stored memories by type and collection — audit your context footprint."
        },
        {
          "name": "update",
          "description": "Update existing memory content, tags, visibility, or type. Useful for refining saved context as your project evolves."
        }
      ],
      "license": "AGPL-3.0",
      "categories": [
        "memory",
        "context",
        "productivity",
        "ai-tools",
        "collaboration"
      ],
      "screenshots": [
        {
          "url": "https://memxus.com/og-image.png",
          "description": "Memxus — AI Context Engine: persistent context from GitHub, Notion, and memory for any AI tool"
        }
      ],
      "extendedDescription": "Multiply your productivity by putting your context to work. The AI context engine for developers. Automatically builds persistent context from your GitHub repos, Notion docs, commits, PRs, and decisions — then delivers it to any MCP-compatible AI client. Nine core tools are always available; GitHub/Notion in-app connect is opt-in per account. Not a memory tool. A context engine that reads your real work. Cross-platform, encrypted, portable."
    }
  },
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.memxus.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.3.2",
  "repository": {
    "url": "https://github.com/gpitrella/memxus-remote-mcp",
    "source": "github"
  },
  "description": "Persistent memory layer that saves and recalls your project context and preferences."
}