Skip to content

Hiveround MCP server

io.github.stevemilton/marketplacestevemiltonstreamable-httpv1.0.0Scanned

Marketplace MCP server for live venture-capital raises and agent-mediated dealflow.

14 tools: 1 do something that can't be undone, 6 change things and 7 only read.

Tools: 0 delete, 1 irreversible, 6 write, 7 read.
  • Reads private data · 2
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

7 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.

What the Hiveround MCP server can do

The Hiveround MCP server is published by the GitHub account stevemilton. It has 14 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_intro_message) and create or change data (6 tools: request_intro, watch_project, update_watch, submit_commitment and 2 more), but cannot delete data. 7 tools only read.

2 tools read private data (list_intros and read_intro_thread); 2 tools bring in text other people can write (list_intros and read_intro_thread); 1 tool can send data out of your system (send_intro_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

14 tools

Can't be undone 1Claude Code: ask
  • send_intro_messageAppend a message to an existing intro thread you're a party to.Can send data outNo findings

    Why it is in this group

    • The name "send_intro_message" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_intro_message" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Append a message to an existing intro thread you're a party to. The other party gets an email notification linking back to the thread. Use this to follow up after request_intro or to keep a conversation moving. (requires API key)
Changes things 6Claude Code: ask
  • acknowledge_commitmentAcknowledge a commitment as the founder or the investor.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Acknowledge a commitment as the founder or the investor. When both sides have acknowledged, status auto-promotes from soft_circled/term_sheet to 'committed' and the amount is added to the project's public round progress. Calling twice from the same side is a no-op. (requires API key)
  • request_introRequest an intro to a project's founder on behalf of the API key's owner.No findings

    Why it is in this group

    • The name "request_intro" says "request": a word for a change.
    Description, as the server wrote it
    Request an intro to a project's founder on behalf of the API key's owner. The founder receives an email with the investor's GitHub handle. (requires API key)
  • submit_commitmentRecord an investor's intent-to-fund a project.No findings

    Why it is in this group

    • The name "submit_commitment" says "submit": a word for a change.
    Description, as the server wrote it
    Record an investor's intent-to-fund a project. Without terms it starts at 'soft_circled'; attach a terms object and it starts at 'term_sheet'. The founder still has to acknowledge — a commitment doesn't count as 'committed' (and doesn't show in the public round progress) until both sides have acked. (requires API key)
  • update_commitment_statusChange a commitment's status.No findings

    Why it is in this group

    • The name "update_commitment_status" says "update": a word for a change.
    Description, as the server wrote it
    Change a commitment's status. Role-gated: only the investor can 'withdraw' a commitment, only the founder can mark it 'funded' (after the wire lands). Either side can move between soft_circled/term_sheet/committed. (requires API key)
  • update_watchMove a watched project to a new pipeline stage and/or append a note.No findings

    Why it is in this group

    • The name "update_watch" says "update": a word for a change.
    Description, as the server wrote it
    Move a watched project to a new pipeline stage and/or append a note. The project must already be in your pipeline. (requires API key)
  • watch_projectAdd a project to your pipeline (or update its stage).No findings

    Why it is in this group

    • The description's first verb is "add": a word for a change.
    Description, as the server wrote it
    Add a project to your pipeline (or update its stage). Stages: interested, diligence, intro_requested, passed, invested. Optional notes are appended to the watch's note log. (requires API key)
Only reads 7Show 7 read-only tools
  • get_projectGet the full project listing by slug, including the founder's GitHub handle.No findings

    Why it is in this group

    • The name "get_project" says "get": a word for reading.
    Description, as the server wrote it
    Get the full project listing by slug, including the founder's GitHub handle.
  • list_commitmentsList commitments where you're either the investor or the founder.No findings

    Why it is in this group

    • The name "list_commitments" says "list": a word for reading.
    Description, as the server wrote it
    List commitments where you're either the investor or the founder. Filter by project slug, your role, or status. (requires API key)
  • list_introsList the intro threads you're a party to (sent as an investor or received as a founder).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_intros" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "thread": it reads messages.
    • untrusted-inputThe description's first sentence says "list" and "thread": it reads messages, which other people can write.
    Description, as the server wrote it
    List the intro threads you're a party to (sent as an investor or received as a founder). Each entry includes the counterparty, message count, last-message preview, and whether you have unread messages. Optionally filter by your role or unread-only. (requires API key)
  • list_projectsList the newest open projects raising on Hiveround.No findings

    Why it is in this group

    • The name "list_projects" says "list": a word for reading.
    Description, as the server wrote it
    List the newest open projects raising on Hiveround. Returns at most 25.
  • list_watchesReturn your pipeline — every project you're watching, with stage, tags, raise size, and last-updated timestamp.No findings

    Why it is in this group

    • The name "list_watches" says "list": a word for reading.
    Description, as the server wrote it
    Return your pipeline — every project you're watching, with stage, tags, raise size, and last-updated timestamp. Optionally filter by stage or tag. (requires API key)
  • read_intro_threadRead all messages in a specific intro thread you're a party to.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "read_intro_thread" says "read": a word for reading.

    What it can reach

    • private-dataThe name "read_intro_thread" says "read" and "thread": it reads messages.
    • private-dataThe description's first sentence says "read" and "message": it reads messages.
    • untrusted-inputThe name "read_intro_thread" says "read" and "thread": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Read all messages in a specific intro thread you're a party to. Marks the thread as read for you. (requires API key)
  • search_projectsSearch open projects by keyword across name, one-liner, description, and sector.No findings

    Why it is in this group

    • The name "search_projects" says "search": a word for reading.
    Description, as the server wrote it
    Search open projects by keyword across name, one-liner, description, and sector. Optional filters: stage, max raise size in USD.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__marketplace__send_intro_message"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:11 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
7
Protocol version
2024-11-05
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://hiveround.com/.well-known/oauth-protected-resource
Authorization servers
https://hiveround.com
Legacy HTTP+SSE transport
no
Dynamic client registration
no
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 7 tools that change things (1 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://hiveround.com/api/mcp: tools/list returned 14 tools to an anonymous client, including send_intro_message (irreversible), request_intro (write), watch_project (write), update_watch (write), submit_commitment (write) and 2 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__marketplace__list_projects",
      "mcp__marketplace__search_projects",
      "mcp__marketplace__get_project",
      "mcp__marketplace__list_watches",
      "mcp__marketplace__list_intros",
      "mcp__marketplace__read_intro_thread",
      "mcp__marketplace__list_commitments"
    ],
    "ask": [
      "mcp__marketplace__request_intro",
      "mcp__marketplace__watch_project",
      "mcp__marketplace__update_watch",
      "mcp__marketplace__send_intro_message",
      "mcp__marketplace__submit_commitment",
      "mcp__marketplace__acknowledge_commitment",
      "mcp__marketplace__update_commitment_status"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as marketplace. Review it before you use it.

Capability tags behind 3 rules
  • mcp__marketplace__list_intros private-data, untrusted-input
  • mcp__marketplace__read_intro_thread private-data, untrusted-input
  • mcp__marketplace__send_intro_message outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.stevemilton/marketplace/verify?hash=86560e9fc5723dffaf76934d50c57e7c62ce05c11527d3dcb73a3410af3d2abd" | jq -e '.changed == false'

Pinned hash 86560e9fc572, from Nov 20, 2026, 14:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.stevemilton/marketplace/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.stevemilton/marketplace
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.stevemilton/marketplace.svg)](https://radar.anlyon.com/servers/io.github.stevemilton/marketplace)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:49 UTC.

Hiveround MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Hiveround MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 7 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Hiveround MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Hiveround MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_intro_message.

What tools does the Hiveround MCP server have?

14 tools: 1 irreversible, 6 write, 7 read. send_intro_message, request_intro, watch_project, update_watch, submit_commitment, acknowledge_commitment, update_commitment_status, list_projects and 6 more.

Does the Hiveround MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Hiveround MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_intro_message.

Has the Hiveround MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.