Caplia
@Caplia-Tech
About Caplia
Caplia is an MCP server for venture-capital pitch-deck scoring and deal-flow management. AI agents — Claude Desktop, Cursor, ChatGPT, Windsurf, or any MCP client — submit pitch decks, get back CRI (Caplia Readiness Index) quality scores plus thesis-fit scores, list companies in t
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"caplia": {
"url": "https://mcp.venture.caplia.ai/",
"headers": {
"Authorization": "Bearer cap_inv_live_YOUR_KEY_HERE"
}
}
}
}Tools
13Search Caplia for companies in the caller's pipeline by name. Returns up to 25 matches with id, name, website, industry, and stage. Use this to find a company before fetching its full profile.
List companies in the caller's pipeline. Supports cursor pagination (`cursor` from the previous response's `next_cursor`) and filtering by `stage` or by named `view`. Use `limit` (default 25, max 100) to bound the page size.
Fetch the full profile of one company by UUID: name, problem statement, industry, stage, website, founders, fundraising round, etc.
Get the CRI score and per-thesis match scores for a company. Returns `{ cri: { score, scored_at, domains }, thesis_matches: [{ thesis_id, thesis_name, match_score, thesis_fit_score, scoring_status }] }` — one entry per investment thesis of the key's team (a team with several theses gets several entries). `match_score` is the headline number shown on the portal's deal card; `thesis_fit_score` is the secondary mandate-fit gauge.
Get traction and key metrics for a company: revenue, growth, headcount, fundraising round milestones, etc.
List all data-room documents attached to a company: pitch decks, financial models, founder updates, term sheets. Each entry has id, name, folder, type, size, and created_at.
Get a 1-hour signed download URL for a specific data-room document. The agent can fetch the bytes directly from the returned URL — file content does not pass through the API.
List the active investment theses of the team this API key belongs to, with their descriptions. Useful for an agent that's reasoning about whether a deal fits a thesis.
List the team's custom properties with their `type` and selectable options. Types: `select` (answer with ONE option label/id), `multi_select` (answer with an ARRAY of option labels/ids — e.g. several award categories), `text` (answer with a freeform string, e.g. an application-form question like "What gives you an unfair advantage?"; options is empty). Properties are configured per team in the Caplia Staff Console, so call this before caplia_submit_deck when you want to tag a submission — pass answers via its `properties` argument using option ids (rename-proof) or labels.
List the team's configured pipeline views (e.g. Deal Flow, My Pipeline, Screening). Each view has a key that can be used as the `view` argument on caplia_list_companies.
Fetch the companies belonging to a named pipeline view (e.g. `deal-flow`, `my-pipeline`).
Poll the status of an async job (typically the result of a deck submission). Returns `{ status, company_id, results, errors }`. Recommended polling cadence: every 3 seconds.
Submit a pitch deck (PDF) to the caller's Caplia pipeline. The deck flows through the same intake pipeline as web uploads and email forwards: text extraction → company shell creation → CRI scoring → thesis matching. Returns `{ job_id, status: "queued", poll_url }` immediately; use `caplia_get_job` with the returned id to watch the company and scores land (typically 30s-2min). Requires a key with the `write` scope.
Overview
What is Caplia?
Caplia is an MCP server for venture-capital pitch-deck scoring and deal-flow management. AI agents—Claude Desktop, Cursor, ChatGPT, Windsurf, or any custom MCP client—submit pitch decks, receive CRI quality scores plus thesis-fit scores, list companies in the caller’s pipeline, pull data-room contents, and poll asynchronous jobs. It is built for VC funds, accelerators, angel networks, and corporate-development teams.
How to use Caplia?
Configure Caplia as an MCP server in your client’s JSON configuration, providing the production or sandbox endpoint and a bearer token. For Claude Desktop, add an entry to claude_desktop_config.json with the URL and Authorization header. Tools appear automatically after restart. Use caplia_submit_deck to upload a PDF (max 50 MB) for scoring; other tools list, search, and retrieve company data.
Key features of Caplia
- 12 tools grouped into read and write scopes
- CRI (Caplia Readiness Index) 0–100 quality score
- Thesis-fit score against active investment theses
- Pipeline views for organizing companies
- Secure data-room access with signed download URLs
- Async job polling for deck submissions
Use cases of Caplia
- Score incoming pitch decks with proprietary CRI and thesis-fit metrics
- Search and filter your deal pipeline by stage or view
- Retrieve full company profiles, traction metrics, and data-room documents
- Evaluate companies against active investment theses
FAQ from Caplia
What is CRI?
CRI (Caplia Readiness Index) is Caplia’s proprietary 0–100 quality score for a company. It summarizes signals across team, market, product, traction, financials, defensibility, and execution, with per-domain breakdowns.
How do I get an API key?
Mint a bearer token from the Caplia portal under Settings → API Keys. Production keys are prefixed cap_inv_live_*; sandbox keys are prefixed cap_inv_test_*.
What transport does Caplia use?
Caplia uses Streamable HTTP with a single POST endpoint and JSON‑RPC 2.0, protocol version 2024-11-05.
Are there separate environments?
Yes. Production: https://mcp.venture.caplia.ai/ (keys prefixed cap_inv_live_*). Sandbox: https://mcp-sandbox.venture.caplia.ai/ (keys prefixed cap_inv_test_*).
What file size limits apply?
Deck submissions via caplia_submit_deck are limited to PDFs of maximum 50 MB.
Frequently asked questions
What is CRI?
CRI (Caplia Readiness Index) is Caplia’s proprietary 0–100 quality score for a company. It summarizes signals across team, market, product, traction, financials, defensibility, and execution, with per-domain breakdowns.
How do I get an API key?
Mint a bearer token from the Caplia portal under **Settings → API Keys**. Production keys are prefixed `cap_inv_live_*`; sandbox keys are prefixed `cap_inv_test_*`.
What transport does Caplia use?
Caplia uses Streamable HTTP with a single POST endpoint and JSON‑RPC 2.0, protocol version `2024-11-05`.
Are there separate environments?
Yes. Production: `https://mcp.venture.caplia.ai/` (keys prefixed `cap_inv_live_*`). Sandbox: `https://mcp-sandbox.venture.caplia.ai/` (keys prefixed `cap_inv_test_*`).
What file size limits apply?
Deck submissions via `caplia_submit_deck` are limited to PDFs of maximum 50 MB.
Basic information
More AI & Agents MCP servers
XDC AI
XDC AI is a remote MCP server available at https://xdcai.tech.
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

Agentery
ntlgncFree MCP for live and historical pricing for 13,000+ agents and MCPs. Never knowingly pay too much... or charge too little. Know the going rate. https://agentery.com.
PDI Bridge for Claude
jxrlabsConnect Claude Desktop to your ServiceNow PDI. Query records, inspect Business Rules, review ACLs, and troubleshoot against your live instance.
Comments