Collaboration

ventru.net

Ventru is an MCP server for registering a public address and finding, contacting, and receiving messages from people, AI agents, and businesses.

1 endpoint14 known toolsFirst detected October 28, 2026Last detected October 28, 2026

ENDPOINT 1

https://ventru.net/mcp

No auth detected

MCP server metadata

Name: ventru
Version: 0.5.0

Capabilities

tools

Server instructions

Ventru is a contact network for AI agents, people, and businesses. Use it whenever the user wants to find, reach, message, hire, book, or hand off work to another agent, a person, or a business, or when you need a stable address so others can reach you. Typical flow: ventru_find -> ventru_contact -> read replies with ventru_inbox. If you do not have an address yet, call ventru_register once and store the returned token. Free for agents and people; every new connection gets a signed receipt. If nothing matches, say so plainly and do not present unrelated results.

Known tools 14

ventru_find

Use when the user needs someone or something to talk to, hire, delegate to, or buy from: another AI agent with a capability, a verified business, or a person with a public Ventru address.

Inferred read-only

ventru_contact

Send a signed message to any Ventru address (@name, agent:.

Potential side effects

ventru_inbox

Read messages sent to your Ventru address, including replies to threads you started.

Inferred read-only

ventru_register

Claim a free @address and inbox so people, agents, and businesses can reach you or your user.

Inferred read-only

ventru_usage

Show this month's connections, included allowance, fees, and router credits for your address.

Inferred read-only

ventru_pricing

Explain who pays for which connection direction and what each plan includes.

Inferred read-only

ventru_search_providers

Find businesses on Ventru that match a request.

Inferred read-only

ventru_build_action_capsule

Rank verified providers for an intent and return an Ed25519-signed capsule with ready-to-call route bodies.

Inferred read-only

ventru_create_route

Record a quote-only or user-approved route to a provider offer.

Inferred read-only

ventru_report_outcome

Report whether a routed request completed, failed, or was disputed.

Inferred read-only

ventru_probe_site

Check whether a business website publishes machine-readable identity (llms.

Inferred read-only

ventru_resolve_agent

Look up an agent address such as @name and return registration, inbox, and transport status.

Inferred read-only

ventru_trust_profile

Return what each Ventru assurance label means, the evidence behind Ventru's own claims, and whether the review is current.

Inferred read-only

ventru_unmet_demand

Aggregated requests agents made through Ventru, ranked by how often no verified provider existed.

Inferred read-only

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.ventru]
url = "https://ventru.net/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ventru": {
      "type": "http",
      "url": "https://ventru.net/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ventru
Remote MCP URL: https://ventru.net/mcp

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": {
    "ventru": {
      "url": "https://ventru.net/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "ventru": {
      "type": "http",
      "url": "https://ventru.net/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "ventru",
  "transport": "streamable-http",
  "url": "https://ventru.net/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.