mcpField
H
Hiveround

Hiveround

Remote
github.com/stevemiltonFinance0Updated 20w ago
Repository

About Hiveround

Hiveround is a marketplace MCP server for live startup fundraises, aimed at investors using agents to find and review deals. It also supports introductions and investment pipeline management.

Key features

  1. 01Search and filter fundraising projects
  2. 02Read project pitches
  3. 03Request founder introductions
  4. 04Maintain a deal pipeline
  5. 05Manage investment commitments

Use cases

  1. 01Find raises by stage and target amount
  2. 02Review founder pitches through an agent
  3. 03Contact founders through introduction threads
  4. 04Track and update prospective investments

MCP support

The remote MCP server exposes project search, pitch access, introductions, and deal-management tools to clients. Read tools allow anonymous access; write tools require a Bearer API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://hiveround.com/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

14
ParameterTypeRequiredDescription
limitnumberNo
stageenumNoidea | prototype | mvp | launched | revenue

Details

From the project README

Hiveround — MCP server for live venture-capital raises

Hiveround is a marketplace for live startup fundraises, built MCP-first. Founders publish a markdown pitch (pitch.md); investors point any MCP-aware agent — Claude, Cursor, a custom loop — at the marketplace, and the agent scouts raises, reads pitches, requests introductions, and maintains a pipeline.

This repository hosts the public metadata for the hosted server. There is nothing to install or run from here — the server is remote.

Try it (no API key needed)

curl -X POST https://hiveround.com/api/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"list_projects","arguments":{"limit":3}}}'

Connect a client

Claude Code

claude mcp add --transport http hiveround https://hiveround.com/api/mcp

Cursor / generic MCP client config

{
  "mcpServers": {
    "hiveround": {
      "type": "streamable-http",
      "url": "https://hiveround.com/api/mcp"
    }
  }
}

For write tools, add an Authorization: Bearer hr_sk_… header with a key from https://hiveround.com/mcp.

Tools (14)

ToolAuthWhat it does
list_projectsanonymousNewest open raises on the marketplace
search_projectsanonymousKeyword search with stage and max-raise filters
get_projectanonymousFull listing by slug, including the founder's pitch
request_introAPI keyRequest an intro to a founder
watch_projectAPI keyAdd a project to your pipeline
update_watchAPI keyMove pipeline stage / append a note
list_watchesAPI keyReturn your pipeline
list_introsAPI keyList intro threads you're a party to
read_intro_threadAPI keyRead messages in a thread
send_intro_messageAPI keyFollow up in an existing thread
submit_commitmentAPI keyRecord an intent-to-fund (soft-circled / term sheet)
acknowledge_commitmentAPI keyAcknowledge a commitment; both sides acked → committed
update_commitment_statusAPI keyWithdraw, mark funded, etc. (role-gated)
list_commitmentsAPI keyCommitments where you're investor or founder

Discovery surfaces

The same data feeds every surface an agent might arrive from:

Registry

Published to the official MCP Registry as io.github.stevemilton/marketplace — see server.json.

Contact

[email protected] — or, fittingly, call request_intro on the hiveround slug.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.