← corbis.ai
INDIVIDUAL MCP TOOL
evidence_pack
Build a paper-level evidence pack for a claim from selected paper IDs or bounded paper retrieval, with citation-ready metadata and retained document IDs.
Input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent endpoint
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.corbis-mcp-server]
url = "https://www.corbis.ai/api/mcp/universal"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"corbis-mcp-server": {
"type": "http",
"url": "https://www.corbis.ai/api/mcp/universal"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: corbis-mcp-server
Remote MCP URL: https://www.corbis.ai/api/mcp/universal
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"corbis-mcp-server": {
"url": "https://www.corbis.ai/api/mcp/universal"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"corbis-mcp-server": {
"type": "http",
"url": "https://www.corbis.ai/api/mcp/universal"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "corbis-mcp-server",
"transport": "streamable-http",
"url": "https://www.corbis.ai/api/mcp/universal"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
search_papers— Search academic and industry research papers using hybrid semantic-keyword search.get_paper_details— Retrieve comprehensive details for a specific paper by ID.get_paper_details_batch— Retrieve details for multiple papers in a single call.research_opportunity_map— Map candidate research gaps, bridge opportunities, conservative conflict probes, and frontier papers inside a bounded academic embedding neighborhood.literature_retrieve— Retrieve bounded academic paper candidates for local Claude Code/Codex synthesis.paper_discovery— Fan out a research question into bounded paper-layer searches, deduplicate the candidates, and return stable document IDs for downstream paper-grain workflows.literature_positioning— Position a thesis against nearby paper-layer literature, returning close papers, citation-anchor candidates, and verification-needed positioning signals.fred_search— Search FRED (Federal Reserve Economic Data) series by text and return candidate series IDs with titles, frequency, and units.