Evidence row 44688

What was observed

{
  "endpoints": [
    [
      "web",
      "https://github.com/nikships/gemdex"
    ]
  ],
  "name": "Gemdex",
  "owner_address": null,
  "raw": {
    "_meta": {
      "io.modelcontextprotocol.registry/official": {
        "isLatest": true,
        "publishedAt": "2026-09-23T10:26:06.975218Z",
        "status": "active",
        "statusChangedAt": "2026-09-23T10:26:06.975218Z",
        "updatedAt": "2026-09-23T10:26:06.975218Z"
      }
    },
    "server": {
      "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
      "description": "Persistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB",
      "name": "io.github.nikships/gemdex",
      "packages": [
        {
          "environmentVariables": [
            {
              "description": "Google AI Studio key for local mode, or the exact value 'local' for on-device MLX text embeddings. Not needed in remote mode.",
              "format": "string",
              "isRequired": true,
              "isSecret": true,
              "name": "GEMINI_API_KEY"
            },
            {
              "choices": [
                "local",
                "remote"
              ],
              "default": "local",
              "description": "Memory backend: embedded local LanceDB or a self-hosted Gemdex Server",
              "format": "string",
              "name": "GEMDEX_MODE"
            },
            {
              "default": "~/.gemdex/lance",
              "description": "Directory for the embedded LanceDB store",
              "format": "filepath",
              "name": "LANCEDB_PATH"
            },
            {
              "choices": [
                "gemini-embedding-2",
                "gemini-embedding-001"
              ],
              "default": "gemini-embedding-2",
              "description": "Gemini text embedding model",
              "format": "string",
              "name": "EMBEDDING_MODEL"
            },
            {
              "description": "Gemdex Server root URL (required in remote mode)",
              "format": "string",
              "name": "GEMDEX_REMOTE_URL"
            },
            {
              "description": "Gemdex Server bearer token (required in remote mode)",
              "format": "string",
              "isSecret": true,
              "name": "GEMDEX_REMOTE_TOKEN"
            },
            {
              "description": "Human-readable name for the remote server",
              "format": "string",
              "name": "GEMDEX_REMOTE_NAME"
            },
            {
              "default": "false",
              "description": "Re-rank recall results by recorded worked/failed/stale outcomes",
              "format": "boolean",
              "name": "GEMDEX_TRUST_RANKING"
            }
          ],
          "identifier": "gemdex-mcp",
          "registryType": "npm",
          "runtimeArguments": [
            {
              "type": "positional",
              "value": "-y",
              "valueHint": "auto-confirm install"
            },
            {
              "type": "positional",
              "value": "gemdex-mcp@1.0.47",
              "valueHint": "package spec"
            }
          ],
          "runtimeHint": "npx",
          "transport": {
            "type": "stdio"
          },
          "version": "1.0.47"
        }
      ],
      "repository": {
        "id": "1249655672",
        "source": "github",
        "url": "https://github.com/nikships/gemdex"
      },
      "title": "Gemdex",
      "version": "1.0.47",
      "websiteUrl": "https://github.com/nikships/gemdex"
    }
  },
  "source": "mcp_registry",
  "summary": "Persistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB"
}

What the leaf hashes

{"body":"2cfc866cec783e865fe96c4e3cb5b7c4134513d4f18b988fb225778984cf89fa","id":44688,"kind":"listing","method":"baseline/1","observed_us":1793025405113565,"prev":null,"subject":"mcp_registry:io.github.nikships/gemdex","subject_kind":"source_record"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-26 (296695 rows).

1. 0x635674eaeb25a0c93017b68cc539a944ed03536040f005f629dff039f5e33b9b
2. 0x4d02742fb0dc10582c9903093f3f1bacbc26320b458fc53f3a67584d3e19e247
3. 0x95e2a4f78829884e38ad921e982a35731b4a5885ce49a0c78a9fcc333880b497
4. 0xa0d8427ce7cb3293fd0739a4f1cc01126bee9b508343f25369c393e0c40a5851
5. 0x37a89d3f2362b251a9ce01ecc6f243c4ff2aee61b5c3aaf11e90ddd300ed5dd1
6. 0x2195c7f3e92a1a958a3df5b984bd819da6c70d7156efb8e9da0184d1f44138e4
7. 0x7d435ff6e05d8be22ecd2db7a07662fe8fc09059652b2c37a9ab01acad45cce4
8. 0xe89ce62aa82c8d97dddb6f684deb1f77d284d33e6bb43b3e5af44febe0194ae5
9. 0x96fc73ca2ee9b3bcd67b8f32c528ff1640c43f28d9945754e11df81a78865be4
10. 0x805c08486b6cd1b041c9a402e5b3eb6f97649952efcabb97e1817185a4ce7572
11. 0xde5ff34fc9e6ff297fede5d3c4b4de6828c65b98246109399106064f912afa82
12. 0x3c8355143bb13802401d5a80f8a70809a59f429bc298f4912731fc8d207e4f43
13. 0x13f4b94ecf613d585c952b5363dad2b247a55371eb8e358bb89dc033e83128b1
14. 0x9a79c65e077cd9da9d436b3ade6f5ddc0d244510c4d5903ef2f02d81205f7666
15. 0xa2d436d488e3600b0e5c3e3ed9c9234cd52853c59830b786334fd0c4292d9f40
16. 0x47b89901b0f07938a6b9a66ddf35683903f79d756a7c7763665fd632758b08d0
17. 0x9a83be955a206deb65b995adfd92c58fa31c95fbbf926bd199d300e70b08b26d
18. 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae