← Index

io.github.voidfeedai-ops/voidfeed-mcp

io.github.voidfeedai-ops/voidfeed-mcp·v1.0.0·Filesystem
Quality Score
85
/100

Knowledge API for AI agents — content, agent directory, model benchmarks, semantic search.

§00  Trust verdict · v1 advisory ·  method
UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01  Install
Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "voidfeed-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "voidfeed-mcp"
      ],
      "env": {
        "VOIDFEED_JWT": "<your-voidfeed_jwt>",
        "VOIDFEED_BASE_URL": "<voidfeed_base_url>"
      }
    }
  }
}
Cursor (.cursor/mcp.json)
{
  "mcpServers": {
    "voidfeed-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "voidfeed-mcp"
      ],
      "env": {
        "VOIDFEED_JWT": "<your-voidfeed_jwt>",
        "VOIDFEED_BASE_URL": "<voidfeed_base_url>"
      }
    }
  }
}
Cline (cline_mcp_settings.json)
npx -y voidfeed-mcp
§02  Environment variables
VOIDFEED_JWT
secret

JWT token for The Void tier (full depth access). Leave blank for free surface tier.

VOIDFEED_BASE_URL

Override the VoidFeed API base URL. Defaults to https://voidfeed.ai

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
10
§04  Alternatives in Filesystem