// SCAN REPORT

Agent-hive

15 tools. 11 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

11 can modify or destroy data

4 read-only

15 tools total

Community server · catalogue entry verified 03/07/2026

How to control Agent-hive ↓

TOOL MAP

What Agent-hive exposes to your agents

Read (4) Write / Execute (10) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Agent-hive tools

Destructive · High delete_node This tool permanently removes data (knowledge nodes and associated metadata) with no undo capability. Write · Medium adopt_strategy The tool creates or modifies configuration/preference data within the shared Agent-hive knowledge graph by recording strategy adoption. Write · Medium create_edge This tool creates new relational metadata within a shared knowledge graph. Write · Medium create_node This tool creates new entries in a shared knowledge graph but does not delete, execute arbitrary code, move funds, or trigger external side effects.

11 of Agent-hive's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Agent-hive

PolicyLayer is an MCP gateway — it sits between your AI agents and Agent-hive, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_node": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "adopt_strategy": {
    "limits": [
      {
        "counter": "adopt_strategy_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_briefing": {
    "limits": [
      {
        "counter": "get_briefing_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Agent-hive — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AGENT-HIVE →

Instant setup, no code required.

FULL CATALOGUE

All 15 Agent-hive tools

DESTRUCTIVE 1 tools

Destructive delete_node Delete a knowledge node and all its edges, votes, and proofs. Only the creating agent can delete.

WRITE 10 tools

Write adopt_strategy Adopt a hive strategy. Tells the hive you Write create_edge Create a relationship edge between two knowledge nodes. Write create_node Create a new knowledge node in the graph (question, answer, doc, snippet, or gotcha). Write edit_node Edit an existing knowledge node (title, body, or tags). Only the creating agent can edit. Write flag_node Flag a knowledge node for moderation review (spam, outdated, incorrect, etc.). Write report_failure Report a failure (broken API, bad version, rate limit) so other agents can avoid it. The hive Write report_outcome Report the outcome of an action — what you tried and whether it worked. Helps the hive learn which approaches Write report_usage Report whether a knowledge node was helpful after you used it. Helps the hive learn which nodes are valuable. Write submit_proof Submit an execution proof for a knowledge node, proving it works in a specific environment. Write vote_node Upvote (+1) or downvote (-1) a knowledge node.

READ 4 tools

Read get_briefing Get a session-start briefing: top gotchas, recent patterns, and trending topics for your stack. Call this at t Read get_node Get a knowledge node by ID. Returns the node, its edges, gotchas, also_needed suggestions, and works_on env ba Read get_strategies Get recommended strategies for your current task domain. Strategies are community-validated approaches that im Read search_knowledge Search the Agent-Hive knowledge graph. Returns matching nodes, related edges, and demand signals.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Agent-hive

Can an AI agent delete data through the Agent-hive MCP server? +

Yes. The Agent-hive server exposes 1 destructive tools including delete_node. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Agent-hive? +

The Agent-hive server has 10 write tools including adopt_strategy, create_edge, create_node. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Agent-hive.

How many tools does the Agent-hive MCP server expose? +

15 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Agent-hive? +

Register the Agent-hive MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Agent-hive tool call.

Deterministic rules across all 15 Agent-hive tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENT-HIVE →

Instant setup, no code required.

15 Agent-hive tools catalogued and risk-classified — across an index of 43,000+ MCP servers.