B+

mcp.venture.caplia.ai

https://mcp.venture.caplia.ai/
89/100 · MCP Trust Grade · checked 6h ago · MCP 2024-11-05
Watched since 2026-06-03 — behavioral baseline locked. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 12 tools · Productivity

caplia_search

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

caplia_list_companies

List companies in the caller's pipeline. Supports cursor pagination (`cursor` from the previous response's `next_cursor`) and filtering by `stage` or

caplia_get_company

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

caplia_get_company_scores

Get the CRI score and per-thesis match scores for a company. Returns `{ cri: { score, scored_at, domains }, thesis_matches: [...] }`. Useful when an a

caplia_get_company_metrics

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

caplia_list_company_documents

List all data-room documents attached to a company: pitch decks, financial models, founder updates, term sheets. Each entry has id, name, folder, type

caplia_get_document_url

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 n

caplia_list_theses

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_views

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 cap

caplia_get_view_companies

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

caplia_get_job

Poll the status of an async job (typically the result of a deck submission). Returns `{ status, company_id, results, errors }`. Recommended polling ca

caplia_submit_deck

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 ext

Spec conformance20%100
Security (OWASP MCP)30%100
Reliability / performance20%92
Tool hygiene15%70
Transparency / provenance15%70

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.
Grade another server

We re-grade mcp.venture.caplia.ai on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — mcp.venture.caplia.ai grade B+
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade B+ · wmcp.sh
[![MCP Trust Grade B+](https://wmcp.sh/mcp/grade/mcp.venture.caplia.ai/badge.svg)](https://wmcp.sh/mcp/grade/mcp.venture.caplia.ai)
<a href="https://wmcp.sh/mcp/grade/mcp.venture.caplia.ai"><img src="https://wmcp.sh/mcp/grade/mcp.venture.caplia.ai/badge.svg" alt="MCP Trust Grade B+ · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.