Bragproof

← Reports

@agenthive-sh/mcp

Starts with no setup0.6.0npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 2 of 2 tools tried
Contacts while installing and starting: nothing

5tools listed
0hosts contacted
0files written
0.2 sto start
96dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y @agenthive-sh/mcp@0.6.0

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

2 tools that take no input and look read-only were called once with nothing. 2 returned a result.

search_agentsReturned a result 3.6 s · 3,868 characters
get_leaderboardReturned a result 7.6 s · 210 characters

During the calls (not necessarily because of them) it first contacted: agenthive.sh.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

search_agents query, framework, category, grade, limit
Find AI agents on agenthive.sh by keyword, framework, category or security grade. Returns name, version, framework, grade, benchmark and install hint. Use get_agent for full details.
get_agent name
Full A2A agent card for one agent: skills, tools, model, license, benchmark, input/output JSON schemas.
get_manifest name
AgentHive manifest for one agent: transport, endpoint, capabilities, tools, security grade, A2A agent card URL.
get_leaderboard category
Agents ranked per category from numbers the registry measured (benchmark pass rate, audit score, gateway availability). Optional category filter.
install_snippet name, target
The command that gets an agent: packages are pulled into Claude Code (.claude/agents, .claude/skills, .mcp.json) or Cursor (.cursor/rules, .cursor/mcp.json); agents hosted by their author are called through the registry gateway.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseApache-2.0
Needsnode >=20
Sourcegithub.com/surpriz/AgentHive
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-lpQ6FjLIJIC0guWPfk6f6r7g7F+vJEa6NszVj+bPlqmWkCTc7yiBUdJ8UtN/4tIYI+DSVD3tDlj1hC1spISh8g==

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/@agenthive-sh/mcp.svg)](https://bragproof.smaverk.com/r/%40agenthive-sh/mcp)

New version out? Ask for a fresh report.