Search / io.github.nikships/gemdex
Gemdex
L0· runs locallyPersistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB
v1.0.47 · active · repository · website · descriptor JSON · versions
Search / io.github.nikships/gemdex
L0· runs locallyPersistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB
v1.0.47 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"gemdex": {
"command": "npx",
"args": [
"-y",
"[email protected]",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"GEMDEX_MODE": "local",
"LANCEDB_PATH": "~/.gemdex/lance",
"EMBEDDING_MODEL": "gemini-embedding-2",
"GEMDEX_REMOTE_TOKEN": "${GEMDEX_REMOTE_TOKEN}",
"GEMDEX_TRUST_RANKING": "false"
}
}
}
}claude mcp add gemdex -e "GEMINI_API_KEY=${GEMINI_API_KEY}" -e "GEMDEX_MODE=local" -e "LANCEDB_PATH=~/.gemdex/lance" -e "EMBEDDING_MODEL=gemini-embedding-2" -e "GEMDEX_REMOTE_TOKEN=${GEMDEX_REMOTE_TOKEN}" -e "GEMDEX_TRUST_RANKING=false" -- npx -y [email protected] [email protected][mcp_servers.gemdex]
command = "npx"
args = ["-y", "[email protected]", "[email protected]"]
env = { "GEMINI_API_KEY" = "${GEMINI_API_KEY}", "GEMDEX_MODE" = "local", "LANCEDB_PATH" = "~/.gemdex/lance", "EMBEDDING_MODEL" = "gemini-embedding-2", "GEMDEX_REMOTE_TOKEN" = "${GEMDEX_REMOTE_TOKEN}", "GEMDEX_TRUST_RANKING" = "false" }
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"gemdex": {
"type": "local",
"command": [
"npx",
"-y",
"[email protected]",
"[email protected]"
],
"enabled": true,
"environment": {
"GEMINI_API_KEY": "{env:GEMINI_API_KEY}",
"GEMDEX_MODE": "local",
"LANCEDB_PATH": "~/.gemdex/lance",
"EMBEDDING_MODEL": "gemini-embedding-2",
"GEMDEX_REMOTE_TOKEN": "{env:GEMDEX_REMOTE_TOKEN}",
"GEMDEX_TRUST_RANKING": "false"
}
}
}
}{
"mcpServers": {
"gemdex": {
"command": "npx",
"args": [
"-y",
"[email protected]",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"GEMDEX_MODE": "local",
"LANCEDB_PATH": "~/.gemdex/lance",
"EMBEDDING_MODEL": "gemini-embedding-2",
"GEMDEX_REMOTE_TOKEN": "${GEMDEX_REMOTE_TOKEN}",
"GEMDEX_TRUST_RANKING": "false"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=gemdex&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImdlbWRleC1tY3BAMS4wLjQ3IiwiZ2VtZGV4LW1jcEAxLjAuNDciXSwiZW52Ijp7IkdFTUlOSV9BUElfS0VZIjoiJHtHRU1JTklfQVBJX0tFWX0iLCJHRU1ERVhfTU9ERSI6ImxvY2FsIiwiTEFOQ0VEQl9QQVRIIjoifi8uZ2VtZGV4L2xhbmNlIiwiRU1CRURESU5HX01PREVMIjoiZ2VtaW5pLWVtYmVkZGluZy0yIiwiR0VNREVYX1JFTU9URV9UT0tFTiI6IiR7R0VNREVYX1JFTU9URV9UT0tFTn0iLCJHRU1ERVhfVFJVU1RfUkFOS0lORyI6ImZhbHNlIn19"
}{
"servers": {
"gemdex": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"GEMDEX_MODE": "local",
"LANCEDB_PATH": "~/.gemdex/lance",
"EMBEDDING_MODEL": "gemini-embedding-2",
"GEMDEX_REMOTE_TOKEN": "${GEMDEX_REMOTE_TOKEN}",
"GEMDEX_TRUST_RANKING": "false"
}
}
}
}{
"mcpServers": {
"gemdex": {
"command": "npx",
"args": [
"-y",
"[email protected]",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"GEMDEX_MODE": "local",
"LANCEDB_PATH": "~/.gemdex/lance",
"EMBEDDING_MODEL": "gemini-embedding-2",
"GEMDEX_REMOTE_TOKEN": "${GEMDEX_REMOTE_TOKEN}",
"GEMDEX_TRUST_RANKING": "false"
}
}
}
}extensions:
"gemdex":
enabled: true
name: "gemdex"
type: stdio
cmd: "npx"
args:
- "-y"
- "[email protected]"
- "[email protected]"
envs:
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
"GEMDEX_MODE": "local"
"LANCEDB_PATH": "~/.gemdex/lance"
"EMBEDDING_MODEL": "gemini-embedding-2"
"GEMDEX_REMOTE_TOKEN": "${GEMDEX_REMOTE_TOKEN}"
"GEMDEX_TRUST_RANKING": "false"
timeout: 300
Placeholders to fill from your own secret store: ${GEMINI_API_KEY}, ${GEMDEX_REMOTE_TOKEN}. The registry never accepts secret values.
This is a local package: the command runs on your machine.
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.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)stability.changes, stability.rug_pulltool list unknowndeps.known_vulns1 advisory to act on (malicious, or rated high or critical with a fix available): GHSA-v6c2-xwv6-8xf7 in [email protected] (indirect, fixed in 11.12.3); 6 more of lower severity or without a fixdeps.mcp_sdk_version@modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or laterdeps.resolvable[email protected] resolved: 221 packagesNo 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.
+repository +namespace-matches-repo +website ~liveness-unmeasured +updated-27d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] npm220 dependencies, resolved · MCP SDK @modelcontextprotocol/sdk 1.30.1 · advisories checked 2026-10-19
| advisory | severity | package | fixed in |
|---|---|---|---|
| GHSA-6qxp-vccf-f47hMCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server | high | @modelcontextprotocol/[email protected]MCP SDK, direct | fixed in 1.31.0 |
| GHSA-v6c2-xwv6-8xf7music-metadata has an infinite loop vulnerability in ASF parser | high | [email protected]indirect | fixed in 11.12.3 |
| GHSA-5v7r-6r5c-r473file-type affected by infinite loop in ASF parser on malformed input with zero-size sub-header | moderate | [email protected]indirect | fixed in 21.3.1 |
| GHSA-53v6-4h7p-p4gjmusic-metadata: Uncontrolled memory allocation in APEv2 parser | moderate | [email protected]indirect | fixed in 11.16.0 |
| GHSA-5gfj-9q3v-qfp3music-metadata: EBML parser trusts element lengths, allowing memory exhaustion or process abort | moderate | [email protected]indirect | fixed in 11.16.0 |
| GHSA-8j4c-6x6g-rq3jmusic-metadata: uncatchable process crash parsing a crafted `.dsf` (residual of GHSA-v6c2-xwv6-8xf7) | moderate | [email protected]indirect | fixed in 11.15.0 |
| GHSA-f94x-6692-553qmusic-metadata: MP4 stsd sample-entry size==0 causes a synchronous infinite loop (DoS) — unreleased regression on master | moderate | [email protected]indirect | fixed in 11.16.0 |
| GHSA-jjpr-9cvf-cq55music-metadata: ID3v2 tag size not validated before allocation, causing memory exhaustion DoS | moderate | [email protected]indirect | fixed in 11.16.0 |
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
gemdex-mcp | npm | 1.0.47 | npx | GEMINI_API_KEY, GEMDEX_REMOTE_TOKEN |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
{
"name": "io.github.nikships/gemdex",
"title": "Gemdex",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.0.47",
"packages": [
{
"version": "1.0.47",
"transport": {
"type": "stdio"
},
"identifier": "gemdex-mcp",
"runtimeHint": "npx",
"registryType": "npm",
"runtimeArguments": [
{
"type": "positional",
"value": "-y",
"valueHint": "auto-confirm install"
},
{
"type": "positional",
"value": "[email protected]",
"valueHint": "package spec"
}
],
"environmentVariables": [
{
"name": "GEMINI_API_KEY",
"format": "string",
"isSecret": true,
"isRequired": true,
"description": "Google AI Studio key for local mode, or the exact value 'local' for on-device MLX text embeddings. Not needed in remote mode."
},
{
"name": "GEMDEX_MODE",
"format": "string",
"choices": [
"local",
"remote"
],
"default": "local",
"description": "Memory backend: embedded local LanceDB or a self-hosted Gemdex Server"
},
{
"name": "LANCEDB_PATH",
"format": "filepath",
"default": "~/.gemdex/lance",
"description": "Directory for the embedded LanceDB store"
},
{
"name": "EMBEDDING_MODEL",
"format": "string",
"choices": [
"gemini-embedding-2",
"gemini-embedding-001"
],
"default": "gemini-embedding-2",
"description": "Gemini text embedding model"
},
{
"name": "GEMDEX_REMOTE_URL",
"format": "string",
"description": "Gemdex Server root URL (required in remote mode)"
},
{
"name": "GEMDEX_REMOTE_TOKEN",
"format": "string",
"isSecret": true,
"description": "Gemdex Server bearer token (required in remote mode)"
},
{
"name": "GEMDEX_REMOTE_NAME",
"format": "string",
"description": "Human-readable name for the remote server"
},
{
"name": "GEMDEX_TRUST_RANKING",
"format": "boolean",
"default": "false",
"description": "Re-rank recall results by recorded worked/failed/stale outcomes"
}
]
}
],
"repository": {
"id": "1249655672",
"url": "https://github.com/nikships/gemdex",
"source": "github"
},
"websiteUrl": "https://github.com/nikships/gemdex",
"description": "Persistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB"
}