Search / io.github.steveweltman/4q-tokenz
4q-tokenz
L0· runs locallyIntelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call.
v1.14.1 · active · repository · descriptor JSON · versions
Search / io.github.steveweltman/4q-tokenz
L0· runs locallyIntelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call.
v1.14.1 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"4q-tokenz": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}claude mcp add 4q-tokenz -- npx -y [email protected][mcp_servers.4q-tokenz]
command = "npx"
args = ["-y", "[email protected]"]
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"4q-tokenz": {
"type": "local",
"command": [
"npx",
"-y",
"[email protected]"
],
"enabled": true
}
}
}{
"mcpServers": {
"4q-tokenz": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=4q-tokenz&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIjRxLXRva2VuekAxLjE1LjAiXX0%3D"
}{
"servers": {
"4q-tokenz": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}{
"mcpServers": {
"4q-tokenz": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}extensions:
"4q-tokenz":
enabled: true
name: "4q-tokenz"
type: stdio
cmd: "npx"
args:
- "-y"
- "[email protected]"
timeout: 300
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_vulns9 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-66ff-xgx4-vchm in [email protected] (indirect, fixed in 7.5.6), GHSA-685m-2w69-288q in [email protected] (indirect, fixed in 7.5.6), GHSA-75px-5xx7-5xc7 in [email protected] (indirect, fixed in 7.5.6), ...; 5 more of lower severity or without a fixdeps.mcp_sdk_version@modelcontextprotocol/sdk 1.22.0 has 4 known advisories (GHSA-345p-7cg4-v4c7, GHSA-6qxp-vccf-f47h, GHSA-8r9q-7v3j-jr4g, ...); update @modelcontextprotocol/sdk to 1.31.0 or laterdeps.resolvable[email protected] resolved: 170 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 ~liveness-unmeasured ~updated-164d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] npm169 dependencies, resolved · MCP SDK @modelcontextprotocol/sdk 1.22.0 · advisories checked 2026-10-19
| advisory | severity | package | fixed in |
|---|---|---|---|
| GHSA-xq3m-2v4x-88ggArbitrary code execution in protobufjs | critical | [email protected]indirect | fixed in 7.5.5 |
| GHSA-345p-7cg4-v4c7@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse | high | @modelcontextprotocol/[email protected]MCP SDK, direct | fixed in 1.26.0 |
| 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-8r9q-7v3j-jr4gAnthropic's MCP TypeScript SDK has a ReDoS vulnerability | high | @modelcontextprotocol/[email protected]MCP SDK, direct | fixed in 1.25.2 |
| GHSA-w48q-cv73-mx4wModel Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default | high | @modelcontextprotocol/[email protected]MCP SDK, direct | fixed in 1.24.0 |
| GHSA-66ff-xgx4-vchmprotobuf.js: Code injection through bytes field defaults in generated toObject code | high | [email protected]indirect | fixed in 7.5.6 |
| GHSA-685m-2w69-288qprotobuf.js: Denial of service through unbounded protobuf recursion | high | [email protected]indirect | fixed in 7.5.6 |
| GHSA-75px-5xx7-5xc7protobuf.js: Code generation gadget after prototype pollution | high | [email protected]indirect | fixed in 7.5.6 |
| GHSA-jvwf-75h9-cwggprotobuf.js: Process-wide denial of service through unsafe option paths | high | [email protected]indirect | fixed in 7.5.6 |
| GHSA-wcpc-wj8m-hjx6protobufjs: Denial of service through unbounded Any expansion during JSON conversion | high | [email protected]indirect | fixed in 7.6.1 |
8 more advisories in the dependencies endpoint.
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 |
|---|---|---|---|---|
4q-tokenz | npm | 1.15.0 | – |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
{
"name": "io.github.steveweltman/4q-tokenz",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.14.1",
"packages": [
{
"version": "1.15.0",
"transport": {
"type": "stdio"
},
"identifier": "4q-tokenz",
"registryType": "npm"
}
],
"repository": {
"url": "https://github.com/steveweltman/4q-tokens",
"source": "github"
},
"description": "Intelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call."
}