Understanding MCP Tools
The Model Context Protocol (MCP) lets other AI clients call tools from Corbis.
That means you can use Corbis research and data tools inside products like Cursor, Claude Code, ChatGPT, and other MCP-compatible clients instead of staying only inside the Corbis web app.
Why People Use MCP
MCP is useful when you want to:
- run Corbis tools from your editor or another AI interface
- keep your research flow in one place
- bring source-backed paper search and economic data into another client
- avoid copying results back and forth by hand
Client setup
Claude
https://www.corbis.ai/api/mcp/universalChatGPT
https://www.corbis.ai/api/mcp/universalCursor
{
"mcpServers": {
"corbis": {
"url": "https://www.corbis.ai/api/mcp/universal"
}
}
}Claude Code
claude mcp add --transport http corbis https://www.corbis.ai/api/mcp/universal --header "Authorization: Bearer ${CORBIS_MCP_API_KEY}"MCP Tool Catalog
This catalog is generated from Corbis's canonical MCP registry. Access depends on your account and key configuration.
| Tool | Name | Description | Category |
|---|---|---|---|
| search_papers | Search Papers | Hybrid academic paper search. | research |
| get_paper_details | Get Paper Details | Fetch full metadata for a single paper. | research |
| get_paper_details_batch | Get Paper Details Batch | Fetch full metadata for multiple papers in one call. | research |
| literature_search | Literature Search | Managed staged literature review and synthesis pipeline. | research |
| research_opportunity_map | Research Opportunity Map | Embedding-based candidate gap, bridge, and conflict mapper for research ideation. | research |
| literature_retrieve | Literature Retrieve | Retrieve paper candidates for local external-agent synthesis. | research |
| paper_discovery | Paper Discovery | Multi-facet paper discovery and deduped triage over the paper layer. | research |
| literature_positioning | Literature Positioning | Position a thesis against nearby paper-layer literature with verification-needed signals. | research |
| evidence_pack | Evidence Pack | Build paper-level evidence packs for claim-specific review. | research |
| claim_verification | Claim Verification | Premium paper-layer claim verification precheck with fail-closed sparse retrieval. | research |
| fred_search | FRED Search | Search FRED economic series metadata. | economic |
| fred_series_batch | FRED Series Batch | Fetch multiple FRED series in one call. | economic |
| get_market_data | Get Market Data | Get a CRE market snapshot. | market |
| get_metric_definitions | Get Metric Definitions | Return schema and definitions for CRE market metrics. | market |
| compare_markets | Compare Markets | Compare multiple CRE markets side by side. | market |
| search_markets | Search Markets | Rank or search markets by metric. | market |
| screen_markets | Screen Markets | Multi-factor CRE market screening. | market |
| get_national_macro | Get National Macro | Fetch national macroeconomic indicators. | market |
| get_market_trends | Get Market Trends | Fetch metro-level historical trend series. | market |
| get_cre_market | Get CRE Market | CRE market snapshot by property type with national benchmarks. | market |
| search_cre_markets | Search CRE Markets | Rank metros by a CRE metric within a property type. | market |
| get_cre_trend | Get CRE Trend | Annual CRE transaction trend for a metro. | market |
| search_cre_listings | Search CRE Listings | Live for-sale / for-lease CRE inventory. | market |
| get_cre_comps | Get CRE Comps | Individual securitized (CMBS) property comps. | market |
| get_cre_operating | Get CRE Operating Fundamentals | Same-store rent/NOI growth + occupancy by metro × sector (REIT supplementals). | market |
| get_reit_transaction_caps | Get REIT Transaction Caps | National by-sector REIT acquisition/disposition cap rates. | market |
| internet_search | Web Search | Managed web search with Corbis-side summary. | web |
| read_web_page | Read Web Page | Extract a web page for analysis. | web |
| web_search_retrieve | Web Search Retrieve | Retrieve web result cards for local external-agent synthesis. | web |
| web_pages_retrieve | Web Pages Retrieve | Retrieve bounded page extracts for local external-agent synthesis. | web |
| deep_research | Deep Research | Run a managed multi-engine web research synthesis pass. | web |
| export_citations | Export Citations | Format supplied citation metadata into export files for MCP clients. | citation |
| render_citations | Render Citations | Render corpus-verified citations from OpenAlex IDs, DOI IDs, chat citation sets, document snapshots, or run IDs. | citation |
| top_cited_articles | Top Cited Articles | Rank highly cited papers within journals. | research |
| format_citation | Format Citation | Format citations in multiple styles. | citation |
| search_datasets | Search Datasets | Discover relevant external datasets. | research |
| find_academic_identity | Find Research Identity | Search for the user research profile candidate. | identity |
| confirm_academic_identity | Confirm Research Identity | Link or unlink public research profile anchors. | identity |
| get_research_pulse | Get Research Pulse | Return the authenticated user research pulse for ResearchBar and MCP clients. | identity |
| get_data_freshness | Get Data Freshness | Aggregate data-through and last-refreshed signals for Corbis data sources. | market |
| retrieve_document | Retrieve Document | Retrieve an existing artifact document. | document |
| query_corbis | Query Corbis | Delegate a managed tool-grounded sub-query to Corbis. | workflow |
| query_corbis_retrieve | Query Corbis Retrieve | Retrieve compact Corbis evidence packets for local external-agent synthesis. | workflow |
| referee_report_evaluate | Evaluate Referee Report | Evaluate local external-agent referee report inputs and return a calibrated deliverable. | workflow |
| technical_audit_evaluate | Evaluate Technical Audit | Evaluate local external-agent technical audit findings and return a calibrated deliverable. | workflow |
| verify_bibtex | Verify BibTeX | Audit BibTeX reference lists for correctness and completeness. | citation |
The Easiest Setup
For most users, the simplest setup is a personal MCP API key from Corbis.
Step 1: Create a key
In Corbis, open Settings → API Keys, create an MCP key, and copy it when it is shown.
Important:
- copy the token when it is shown
- tokens are only revealed once
- revoke and replace a key if you think it has been exposed
Step 2: Point your client at the universal endpoint
Use your Corbis origin (the same host you use in the browser for the app—not a marketing URL unless that is where the app actually runs). The MCP path you need is:
/api/mcp/universal
Build the full URL as: the same origin you use for the web app (scheme, host, and port if any) plus the path /api/mcp/universal.
Most clients connect with that URL plus your MCP key.
Step 3: Use the connection method your client expects
Corbis already helps with the common cases:
- Cursor: one-click install or downloadable JSON config
- Claude Code: copyable CLI command
- Other MCP clients: universal endpoint plus your key
If you are not sure which transport to use, prefer the streamable HTTP setup against /api/mcp/universal unless your client docs require something else.
Authentication (API key vs OAuth)
-
Personal MCP API keys — Created in Settings → API Keys. This is the default path for clients that let you set a custom header (Claude Code, Codex, and similar): send the key as an
Authorization: Bearer …header. -
OAuth — Used when the client signs you in and approves access in the web app. Cursor, and hosted assistant connectors such as ChatGPT and Claude, use this path: they take the MCP URL alone and run the sign-in flow themselves, so their config carries no key.
OAuth access tokens use the same Authorization: Bearer … header style after you complete the client's login flow.
Security: Credentials in the URL query string (?apikey= / ?token=) are rejected in production — they leak through logs, referrers, and shared links. They work only against a local development server. Always use a Bearer header or OAuth.
OAuth scope and consent details for implementers are documented in lib/mcp/OAUTH2_IMPLEMENTATION.md in the repository (not required reading for basic API-key setup).
Advanced / other surfaces
Prefer /api/mcp/universal for new setups. Other routes exist for compatibility and discovery:
/api/mcp/sseand/api/mcp/message— Legacy SSE transport pair for clients that need a dedicated SSE URL instead of streamable HTTP on the universal route./.well-known/oauth-protected-resource,/.well-known/oauth-authorization-server,/.well-known/openid-configuration— OAuth / OpenID discovery metadata for clients that probe well-known URLs./api/mcp/oauth/register,/api/mcp/oauth/authorize,/api/mcp/oauth/token— Dynamic registration, authorization, and token exchange for supported OAuth integrations.
This section names routes only; it is not a full OAuth tutorial.
Practical Tips
- Create separate keys for separate devices or clients.
- Name keys clearly so you can revoke the right one later.
- Treat MCP keys like passwords.
- If a tool seems missing, check your plan and the key configuration first.
- If a client offers both modern HTTP MCP and older SSE-based options, prefer HTTP on
/api/mcp/universalunless you know you need the legacy path.
Common Questions
Do I need a paid plan to use MCP?
Tool access depends on your account entitlements and key configuration. The safest answer is to check your current plan and limits in Corbis.
Can I use Corbis from my editor?
Yes. That is one of the main MCP use cases.
Can I connect more than one client?
Yes. Many users create separate keys for different clients so they can revoke them independently.
Where do I get help if the connection fails?
Start in Settings → API Keys and make sure you are using the right endpoint and token. If that still fails, contact support.
Further reading (repository)
If you are working from a checkout of the Corbis codebase:
docs/ai-sdk/mcp/— Corbis MCP guides (Cursor plugin, Claude Code, Codex, and related).lib/mcp/CHATGPT_GUIDE.md— ChatGPT-oriented setup notes.