# Caplia (remote · mcp.venture.caplia.ai)

MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.

- Trust score: 34/100 (low)
- Change this week: −28
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.venture.caplia.ai`: 34/100 (this document), [markdown](https://verifymcp.io/servers/caplia-tech-caplia/mcp.md), [page](https://verifymcp.io/servers/caplia-tech-caplia/mcp)
- remote · `mcp-sandbox.venture.caplia.ai`: 34/100, [markdown](https://verifymcp.io/servers/caplia-tech-caplia/mcp-sandbox.md), [page](https://verifymcp.io/servers/caplia-tech-caplia/mcp-sandbox)

## Channel facts

- Endpoint: `https://mcp.venture.caplia.ai/`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 86/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http caplia-tech-caplia https://mcp.venture.caplia.ai/
```

### Codex

```toml
[mcp_servers.caplia-tech-caplia]
url = "https://mcp.venture.caplia.ai/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "caplia-tech-caplia": {
      "type": "remote",
      "url": "https://mcp.venture.caplia.ai/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add caplia-tech-caplia --url https://mcp.venture.caplia.ai/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  caplia-tech-caplia:
    url: "https://mcp.venture.caplia.ai/"
```

### Other

```json
{
  "mcpServers": {
    "caplia-tech-caplia": {
      "type": "http",
      "url": "https://mcp.venture.caplia.ai/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 34, 0)

- [security regression] HTTPS: unverified → fail

### 2026-08-01 (score 34, 0)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] HTTPS: fail → unverified

### 2026-07-31 (score 34, +12)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 22, −42)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 62, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 62)

First indexed and scored.

## MCP tools (13)

### `caplia_search` (~71 tokens)

Search 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.

Input parameters:

- `limit` (integer)
- `q` (string, required): Search query (company name)

### `caplia_list_companies` (~117 tokens)

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.

Input parameters:

- `cursor` (string): Pagination cursor from a previous response
- `limit` (integer)
- `stage` (string): Filter to one pipeline stage
- `view` (string): Filter to a named pipeline view (e.g. my-pipeline)

### `caplia_get_company` (~47 tokens)

Fetch the full profile of one company by UUID: name, problem statement, industry, stage, website, founders, fundraising round, etc.

Input parameters:

- `id` (string, required): Company UUID

### `caplia_get_company_scores` (~70 tokens)

Get the CRI score and per-thesis match scores for a company. Returns `{ cri: { score, scored_at, domains }, thesis_matches: [...] }`. Useful when an agent needs to reason about how a company fits the team's investment theses.

Input parameters:

- `id` (string, required): Company UUID

### `caplia_get_company_metrics` (~42 tokens)

Get traction and key metrics for a company: revenue, growth, headcount, fundraising round milestones, etc.

Input parameters:

- `id` (string, required): Company UUID

### `caplia_list_company_documents` (~59 tokens)

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.

Input parameters:

- `id` (string, required): Company UUID

### `caplia_get_document_url` (~56 tokens)

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.

Input parameters:

- `id` (string, required): Document UUID

### `caplia_list_theses` (~35 tokens)

List the team's active investment theses with their descriptions. Useful for an agent that's reasoning about whether a deal fits a thesis.

### `caplia_list_properties` (~77 tokens)

List the team's custom properties (e.g. an awards programme's "Award Category") with their selectable options. Properties are configured per team inside Caplia, so call this before caplia_submit_deck when you want to tag a submission — pass selections via its `properties` argument using the option ids (rename-proof) or labels.

### `caplia_list_views` (~50 tokens)

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.

### `caplia_get_view_companies` (~49 tokens)

Fetch the companies belonging to a named pipeline view (e.g. `deal-flow`, `my-pipeline`).

Input parameters:

- `key` (string, required): View key from caplia_list_views

### `caplia_get_job` (~63 tokens)

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.

Input parameters:

- `id` (string, required): Job UUID from POST /v1/decks

### `caplia_submit_deck` (~382 tokens)

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.

Input parameters:

- `company_name` (string): Pre-tag the deck with a company name your CRM already knows. The worker uses it when creating the company shell. Optional.
- `company_url` (string): Pre-tag with the company's website (e.g. "https://tesla.com"). Helps the extraction step. Optional.
- `file_b64` (string, required): Base64-encoded contents of the PDF file. Most MCP clients (Claude Desktop, Cursor) can read a local PDF and base64-encode its bytes. Max 50 MB decoded.
- `filename` (string): Original filename for human-readable display in the intake log (e.g. "tesla-seed-deck.pdf"). Optional but recommended.
- `founder_email` (string): Founder/contact email — becomes the company's primary contact card. Optional.
- `founder_name` (string): Founder/contact name — becomes the company's primary contact card. Optional.
- `notes` (string): Free-form context from your CRM — "Met at YC demo day", "warm intro from X". Surfaces in the intake event payload. Optional.
- `properties` (object): Tag the deal with the team's custom properties, e.g. {"Award Category": "Climate Tech"}. Keys are property names or ids, values are option labels or ids — discover them with caplia_list_properties. U…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/caplia-tech-caplia/mcp#diagnostics

## Score history

- 2026-08-03: 34
- 2026-08-02: 34
- 2026-08-01: 34
- 2026-07-31: 34
- 2026-07-30: 22
- 2026-07-29: 64
- 2026-07-28: 63
- 2026-07-27: 62
- 2026-07-26: 62

## Links

- Remote endpoint: https://mcp.venture.caplia.ai/
- Authorisation metadata: https://mcp.venture.caplia.ai/.well-known/oauth-protected-resource
- Repository: https://github.com/Caplia-Tech/caplia-investor
- Website: https://docs.venture.caplia.ai/integrations/mcp
- Changelog RSS feed: https://verifymcp.io/servers/caplia-tech-caplia/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/caplia-tech-caplia/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/caplia-tech-caplia/mcp