io.github.cyanheads/libofcongress-mcp-server
Search LOC digital collections, Chronicling America newspapers (full OCR), and LC Subject Headings.
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.
{
"mcpServers": {
"libofcongress-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/libofcongress-mcp-server"
],
"env": {
"LOC_USER_AGENT": "libofcongress-mcp-server/0.2.4",
"LOC_REQUEST_DELAY_MS": "3100",
"MCP_LOG_LEVEL": "info",
"MCP_HTTP_HOST": "127.0.0.1",
"MCP_HTTP_PORT": "3010",
"MCP_HTTP_ENDPOINT_PATH": "/mcp",
"MCP_AUTH_MODE": "none"
}
}
}
}{
"mcpServers": {
"libofcongress-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/libofcongress-mcp-server"
],
"env": {
"LOC_USER_AGENT": "libofcongress-mcp-server/0.2.4",
"LOC_REQUEST_DELAY_MS": "3100",
"MCP_LOG_LEVEL": "info",
"MCP_HTTP_HOST": "127.0.0.1",
"MCP_HTTP_PORT": "3010",
"MCP_HTTP_ENDPOINT_PATH": "/mcp",
"MCP_AUTH_MODE": "none"
}
}
}
}npx -y @cyanheads/libofcongress-mcp-serverLOC_USER_AGENTUser-Agent header sent with LOC API requests. LOC recommends a descriptive value for polite access.
LOC_REQUEST_DELAY_MSDelay in milliseconds between LOC API requests to stay under the 20 req/min rate limit.
MCP_LOG_LEVELSets the minimum log level for output (e.g., 'debug', 'info', 'warn').
LOC_USER_AGENTUser-Agent header sent with LOC API requests. LOC recommends a descriptive value for polite access.
LOC_REQUEST_DELAY_MSDelay in milliseconds between LOC API requests to stay under the 20 req/min rate limit.
MCP_HTTP_HOSTThe hostname for the HTTP server.
MCP_HTTP_PORTThe port to run the HTTP server on.
MCP_HTTP_ENDPOINT_PATHThe endpoint path for the MCP server.
MCP_AUTH_MODEAuthentication mode to use: 'none', 'jwt', or 'oauth'.
MCP_LOG_LEVELSets the minimum log level for output (e.g., 'debug', 'info', 'warn').
Run 150+ AI apps — image, video, audio, LLMs, 3D and more. Browse, execute, stream results.
Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.
Contabo API (v1.0.0) as MCP tools for cloud provisioning, and management. Powered by HAPI MCP server